Datasets:

librarian-bots
/

model_cards_with_metadata

Dataset card Data Studio Files Files and versions Community

Split (1)

train · 686k rows

modelId stringlengths 5 137	author stringlengths 2 42	last_modified unknowndate 2020-02-15 11:33:14 2025-03-27 06:27:00	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 399 values	tags sequencelengths 1 4.05k	pipeline_tag stringclasses 54 values	createdAt unknowndate 2022-03-02 23:29:04 2025-03-27 06:26:25	card stringlengths 11 1.01M
TOMFORD79/VOLVO_X6	TOMFORD79	"2025-02-28T07:04:20Z"	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2025-02-28T04:38:30Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
lesso17/ef044443-441a-4d2d-b56c-be7489fa18dc	lesso17	"2025-03-17T07:20:00Z"	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:NousResearch/Hermes-2-Theta-Llama-3-8B", "base_model:adapter:NousResearch/Hermes-2-Theta-Llama-3-8B", "license:apache-2.0", "region:us" ]	null	"2025-03-17T03:42:01Z"	--- library_name: peft license: apache-2.0 base_model: NousResearch/Hermes-2-Theta-Llama-3-8B tags: - axolotl - generated_from_trainer model-index: - name: ef044443-441a-4d2d-b56c-be7489fa18dc results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: NousResearch/Hermes-2-Theta-Llama-3-8B bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 9681d36d94b80029_train_data.json ds_type: json format: custom path: /workspace/input_data/9681d36d94b80029_train_data.json type: field_input: document_extracted field_instruction: question field_output: answer format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null do_eval: true early_stopping_patience: 3 eval_batch_size: 4 eval_max_new_tokens: 128 eval_steps: 500 evals_per_epoch: null flash_attention: true fp16: false fsdp: null fsdp_config: null gradient_accumulation_steps: 8 gradient_checkpointing: true group_by_length: true hub_model_id: lesso17/ef044443-441a-4d2d-b56c-be7489fa18dc hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.000217 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 50 lora_alpha: 128 lora_dropout: 0.15 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 64 lora_target_linear: true lr_scheduler: cosine max_grad_norm: 1.0 max_steps: 500 micro_batch_size: 4 mlflow_experiment_name: /tmp/9681d36d94b80029_train_data.json model_type: AutoModelForCausalLM num_epochs: 10 optimizer: adamw_torch_fused output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false save_steps: 500 saves_per_epoch: null seed: 170 sequence_len: 1024 strict: false tf32: true tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 939ef766-a047-4760-90e0-9f7681346674 wandb_project: 17a wandb_run: your_name wandb_runid: 939ef766-a047-4760-90e0-9f7681346674 warmup_steps: 100 weight_decay: 0.0 xformers_attention: null ``` </details><br> # ef044443-441a-4d2d-b56c-be7489fa18dc This model is a fine-tuned version of [NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4583 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.000217 - train_batch_size: 4 - eval_batch_size: 4 - seed: 170 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 100 - training_steps: 500 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| No log \| 0.0006 \| 1 \| 4.2959 \| \| 0.4718 \| 0.3174 \| 500 \| 0.4583 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
ehsankhan525/llama_3_1_8b_coder-full	ehsankhan525	"2024-11-29T21:16:24Z"	19	1	transformers	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit", "base_model:quantized:unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	"2024-11-29T21:13:49Z"	--- base_model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - gguf license: apache-2.0 language: - en --- # Uploaded model - Developed by: ehsankhan525 - License: apache-2.0 - Finetuned from model : unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
jurmy24/multi-view-diffusion	jurmy24	"2024-05-07T00:34:01Z"	15	0	diffusers	[ "diffusers", "safetensors", "image-to-3d", "arxiv:2312.02201", "license:openrail", "diffusers:MVDreamPipeline", "region:us" ]	image-to-3d	"2024-11-02T19:22:01Z"	--- license: openrail pipeline_tag: image-to-3d --- This is a copy of [ashawkey/imagedream-ipmv-diffusers](https://huggingface.co/ashawkey/imagedream-ipmv-diffusers). It is hosted here for persistence throughout the ML for 3D course. # MVDream-diffusers Model Card This is a port of https://huggingface.co/Peng-Wang/ImageDream into diffusers. For usage, please check: https://github.com/ashawkey/mvdream_diffusers ## Citation ``` @article{wang2023imagedream, title={ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation}, author={Wang, Peng and Shi, Yichun}, journal={arXiv preprint arXiv:2312.02201}, year={2023} } ``` ## Misuse, Malicious Use, and Out-of-Scope Use The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
RayNguyent/finetuning-sentiment-model	RayNguyent	"2023-07-29T10:46:52Z"	105	0	transformers	[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "generated_from_trainer", "dataset:imdb", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	"2023-07-29T03:56:51Z"	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer datasets: - imdb metrics: - accuracy - f1 model-index: - name: finetuning-sentiment-model results: - task: name: Text Classification type: text-classification dataset: name: imdb type: imdb config: plain_text split: test args: plain_text metrics: - name: Accuracy type: accuracy value: 1.0 - name: F1 type: f1 value: 0.0 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # finetuning-sentiment-model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset. It achieves the following results on the evaluation set: - Loss: 0.0819 - Accuracy: 1.0 - F1: 0.0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results ### Framework versions - Transformers 4.31.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.1 - Tokenizers 0.13.3
karawalla/mistral_b_karawalla_aqtraining24005	karawalla	"2024-01-20T21:44:05Z"	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	"2024-01-20T21:43:55Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
rodri2023/ppo-LunarLander-v2	rodri2023	"2023-04-21T16:41:11Z"	4	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	"2023-04-21T16:40:46Z"	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 263.01 +/- 16.60 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
Arch4ngel/PyramidsRND	Arch4ngel	"2023-01-11T18:10:48Z"	3	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "unity-ml-agents", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]	reinforcement-learning	"2023-01-11T18:10:43Z"	--- tags: - unity-ml-agents - ml-agents - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Pyramids library_name: ml-agents --- # ppo Agent playing Pyramids This is a trained model of a ppo agent playing Pyramids using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://github.com/huggingface/ml-agents#get-started We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: ### Resume the training ``` mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser:. 1. Go to https://huggingface.co/spaces/unity/ML-Agents-Pyramids 2. Step 1: Write your model_id: Arch4ngel/PyramidsRND 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF	mradermacher	"2025-01-18T22:11:50Z"	193	0	transformers	[ "transformers", "gguf", "Safetensors", "text-generation-inference", "merge", "en", "base_model:MaziyarPanahi/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model", "base_model:quantized:MaziyarPanahi/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	"2025-01-18T21:56:03Z"	--- base_model: MaziyarPanahi/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model language: - en library_name: transformers license: apache-2.0 model_creator: MaziyarPanahi model_name: Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model quantized_by: mradermacher tags: - Safetensors - text-generation-inference - merge --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> static quants of https://huggingface.co/MaziyarPanahi/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF/resolve/main/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model.Q2_K.gguf) \| Q2_K \| 2.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF/resolve/main/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model.Q3_K_S.gguf) \| Q3_K_S \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF/resolve/main/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model.Q3_K_M.gguf) \| Q3_K_M \| 3.6 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF/resolve/main/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model.Q3_K_L.gguf) \| Q3_K_L \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF/resolve/main/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model.IQ4_XS.gguf) \| IQ4_XS \| 4.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF/resolve/main/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model.Q4_K_S.gguf) \| Q4_K_S \| 4.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF/resolve/main/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model.Q4_K_M.gguf) \| Q4_K_M \| 4.5 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF/resolve/main/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model.Q5_K_S.gguf) \| Q5_K_S \| 5.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF/resolve/main/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model.Q5_K_M.gguf) \| Q5_K_M \| 5.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF/resolve/main/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model.Q6_K.gguf) \| Q6_K \| 6.0 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF/resolve/main/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model.Q8_0.gguf) \| Q8_0 \| 7.8 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model-GGUF/resolve/main/Experiment26T3qm7xp_Ognoexperiment27Multi_verse_model.f16.gguf) \| f16 \| 14.6 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
lesso01/757c0799-b543-4446-b0ca-2f28f9f26509	lesso01	"2025-01-10T14:04:59Z"	10	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:huggyllama/llama-7b", "base_model:adapter:huggyllama/llama-7b", "license:other", "region:us" ]	null	"2025-01-10T14:02:46Z"	--- library_name: peft license: other base_model: huggyllama/llama-7b tags: - axolotl - generated_from_trainer model-index: - name: 757c0799-b543-4446-b0ca-2f28f9f26509 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: huggyllama/llama-7b bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 1ade7b2e9d8ab2ce_train_data.json ds_type: json format: custom path: /workspace/input_data/1ade7b2e9d8ab2ce_train_data.json type: field_instruction: issue_body field_output: issue_title format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 4 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: lesso01/757c0799-b543-4446-b0ca-2f28f9f26509 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 10 micro_batch_size: 2 mlflow_experiment_name: /tmp/1ade7b2e9d8ab2ce_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 4 sequence_len: 512 special_tokens: pad_token: </s> strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: a76eefd0-5d33-4038-a018-7c42b4d6924a wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: a76eefd0-5d33-4038-a018-7c42b4d6924a warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # 757c0799-b543-4446-b0ca-2f28f9f26509 This model is a fine-tuned version of [huggyllama/llama-7b](https://huggingface.co/huggyllama/llama-7b) on the None dataset. It achieves the following results on the evaluation set: - Loss: nan ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.0 \| 0.0017 \| 1 \| nan \| \| 0.0 \| 0.0052 \| 3 \| nan \| \| 0.0 \| 0.0104 \| 6 \| nan \| \| 0.0 \| 0.0156 \| 9 \| nan \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
Trelis/Llama-3.2-1B-Instruct-touch-rugby-synth-1epochs-20241010-102944	Trelis	"2024-10-10T10:33:35Z"	128	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "trl", "sft", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-10-10T10:32:56Z"	--- library_name: transformers tags: - trl - sft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
alexbeta80/DDTdonut-TeresaConFESTO-aggiunto38	alexbeta80	"2024-03-18T13:49:15Z"	25	0	transformers	[ "transformers", "safetensors", "vision-encoder-decoder", "image-text-to-text", "generated_from_trainer", "dataset:imagefolder", "base_model:alexbeta80/DDTdonut-TeresaNoFESTO", "base_model:finetune:alexbeta80/DDTdonut-TeresaNoFESTO", "license:mit", "endpoints_compatible", "region:us" ]	image-text-to-text	"2024-03-18T13:42:57Z"	--- license: mit base_model: alexbeta80/DDTdonut-TeresaNoFESTO tags: - generated_from_trainer datasets: - imagefolder model-index: - name: DDTdonut-TeresaConFESTO-aggiunto38 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # DDTdonut-TeresaConFESTO-aggiunto38 This model is a fine-tuned version of [alexbeta80/DDTdonut-TeresaNoFESTO](https://huggingface.co/alexbeta80/DDTdonut-TeresaNoFESTO) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0873 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.9142 \| 1.0 \| 19 \| 0.2204 \| \| 0.562 \| 2.0 \| 38 \| 0.1151 \| \| 0.4506 \| 3.0 \| 57 \| 0.0873 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
abhiag/SpotifyMain	abhiag	"2023-05-30T18:50:12Z"	0	0	null	[ "region:us" ]	null	"2023-05-30T18:45:31Z"	# Spotify-Recommendation-System Please visit the following link to access the demo version: [Spotify-Recommendation-System](https://longliveruby-spotify-recommendation-system.hf.space/) https://user-images.githubusercontent.com/107134115/201241072-06681109-72ad-4416-b5f0-35322646dc1e.mp4 ## Description The goal of this project is to create a recommendation system that would allow users to discover music based on a given playlist or song that they already enjoy. This project begins with data collection and a self-growing dataset to ensure that the model will work well in the future and continues through model deployment. ## Data For this project, I'm using the Million Playlist Dataset, which, as its name implies, consists of one million playlists. contains a number of songs, and some metadata is included as well, such as the name of the playlist, duration, number of songs, number of artists, etc. It is created by sampling playlists from the billions of playlists that Spotify users have created over the years. Playlists that meet the following criteria were selected at random: - Created by a user that resides in the United States and is at least 13 years old - Was a public playlist at the time the MPD was generated - Contains at least 5 tracks - Contains no more than 250 tracks - Contains at least 3 unique artists - Contains at least 2 unique albums - Has no local tracks (local tracks are non-Spotify tracks that a user has on their local device - Has at least one follower (not including the creator - Was created after January 1, 2010 and before December 1, 2017 - Does not have an offensive title - Does not have an adult-oriented title if the playlist was created by a user under 18 years of age Check out the dataset [here](https://www.aicrowd.com/challenges/spotify-million-playlist-dataset-challenge) ## Data extraction The first step will be to obtain keys to use. We'll need a [Spotify for developers](https://developer.spotify.com/) account for this. This is equivalent to a Spotify account and does not necessitate Spotify Premium. Go to the dashboard and select "create an app" from there. We now have access to the public and private keys required to use the API. Now that we have an app, we can get a client ID and a client secret for this app. Both of these will be required to authenticate with the Spotify web API for our application, and can be thought of as a kind of username and password for the application. It is best practice not to share either of these, but especially don’t share the client secret key. To prevent this, we can keep it in a separate file, which, if you’re using Git for version control, should be Gitignored. Spotify credentials should be stored the in the a `Spotify.yaml` file with the first line as the credential id and the second line as the secret key: ```python Client_id : ********************** client_secret : ******************** ``` To access this credentials, please use the following code: ```python stream= open("Spotify/Spotify.yaml") spotify_details = yaml.safe_load(stream) auth_manager = SpotifyClientCredentials(client_id=spotify_details['Client_id'], client_secret=spotify_details['client_secret']) sp = spotipy.client.Spotify(auth_manager=auth_manager) ``` ## Code ### Reading1M_feature_extraction.ipynb - This notebook reads the main.json files containing the playlists in order to train the model and generate recommendations. - The loop_slices() function will go through as many slices as desired to extract the unique track URIs from the playlists for the content-based recommendation system. - Using the Spotify API for Feature Extraction (Audio Features, Track Release Date, Track Popularity, Artist Popularity, Artist Genres) and Saving Results to a CSV Files and Errors to a Log File ```python f = open('data/audio_features.csv','a') e=0 for i in tqdm(range(0,len(t_uri),100)): try: track_feature = sp.audio_features(t_uri[i:i+100]) track_df = pd.DataFrame(track_feature) csv_data = track_df.to_csv(header=False,index=False) f.write(csv_data) except Exception as error: e+=1 r = open("audio_features_log.txt", "a") r.write(datetime.datetime.now().strftime("%d.%b %Y %H:%M:%S")+": "+str(error)+'\n') r.close() time.sleep(3) continue r = open("audio_features_log.txt", "a") r.write(datetime.datetime.now().strftime("%d.%b %Y %H:%M:%S")+" _________________________ "+"Total Number Of Errors : "+str(e)+" _________________________ "+'\n') r.close() f.close() ``` ### Preprocessing.ipynb - This notebook reads the extracted features and merges them into one dataframe. - Handling missing extraction features and dropping duplicated and irrelevant columns - Create five point buckets for track and artist popularity and 50 point buckets for the track release date. ```python df['Track_release_date'] = df['Track_release_date'].apply(lambda x: int(x/50)) ``` If I'm listening to music from the 1950s, I'd like the model to recommend music from the same era. ### Modeling.ipynb - Repeating the extraction features and preprocessing steps for the user's playlist (input) - If a track from the user's playlist is missing from the dataset, it will be added automatically. - TfidfVectorizer was used for the Artist Genres (TF-IDF automatically assigns weights to metadata based on how frequently they appear). <img width="1017" alt="tfidf_4" src="https://user-images.githubusercontent.com/107134115/201203710-c1a48e8b-1365-4cc3-bba4-58a1102bafde.png"> - I was first using OneHotEncoder for Track_release_date, Track_pop, Artist_pop but I found no difference in the final result other than high memory usage. - Converting a user playlist to a single vector - Cosine similarity is used to compare playlist vectors to song vectors to generate recommendations. ![image](https://user-images.githubusercontent.com/107134115/201203569-6bcd14fd-6704-4ad7-9577-44095bd65f74.png) - I decided to go with three models. Model 1 which gives the genera more weight than the audio features Model 2 which gives equal weight to all features (as a result, playlist languages and genres are ignored) Spotify Model**, which is available through the Spotify API ### Deployment Please visit the following link to access the app's final version: https://huggingface.co/spaces/Longliveruby/Spotify-Recommendation-System The website can be accessed and tested out there. Due to the limitations of file sizes and RAM limits, I decided to go with [huggingface](https://huggingface.co/) because the free version is not severely limited. You can test the app on localhost by cloning the repository data, cd into the folder and run the following commands: ```python cd Streamlit streamlit run main.py ``` Installing dependencies: ```python pip install -r requirements.txt ``` ### Reference - https://medium.com/analytics-vidhya/music-recommender-system-part-2-ff4c3f54cba3 - https://github.com/madhavthaker/spotify-recommendation-system - https://spotipy.readthedocs.io/en/master/
LarryAIDraw/nitocris__fate__v1	LarryAIDraw	"2023-05-22T20:51:10Z"	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	"2023-05-22T20:46:53Z"	--- license: creativeml-openrail-m --- https://civitai.com/models/72952/nitocris-fate-grand-order
rohandsouza/starcoder2-lora	rohandsouza	"2025-03-03T09:40:41Z"	0	0	peft	[ "peft", "safetensors", "generated_from_trainer", "code", "text-generation", "base_model:bigcode/starcoder2-15b", "base_model:adapter:bigcode/starcoder2-15b", "license:bigcode-openrail-m", "region:us" ]	text-generation	"2025-03-03T09:31:07Z"	--- library_name: peft license: bigcode-openrail-m base_model: bigcode/starcoder2-15b tags: - generated_from_trainer - code model-index: - name: starcoder2-lora results: [] pipeline_tag: text-generation --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # starcoder2-lora This model is a fine-tuned version of [bigcode/starcoder2-15b](https://huggingface.co/bigcode/starcoder2-15b) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - training_steps: 1000 ### Framework versions - PEFT 0.14.0 - Transformers 4.47.1 - Pytorch 2.5.1+cu121 - Datasets 3.3.2 - Tokenizers 0.21.0
mradermacher/Qwen-2.5-base-agentic-7b-GGUF	mradermacher	"2025-03-14T03:30:44Z"	0	0	transformers	[ "transformers", "gguf", "merge", "mergekit", "lazymergekit", "en", "base_model:Jebadiah/Qwen-2.5-base-agentic-7b", "base_model:quantized:Jebadiah/Qwen-2.5-base-agentic-7b", "endpoints_compatible", "region:us", "conversational" ]	null	"2025-03-14T02:57:03Z"	--- base_model: Jebadiah/Qwen-2.5-base-agentic-7b language: - en library_name: transformers quantized_by: mradermacher tags: - merge - mergekit - lazymergekit --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/Jebadiah/Qwen-2.5-base-agentic-7b <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-base-agentic-7b-GGUF/resolve/main/Qwen-2.5-base-agentic-7b.Q2_K.gguf) \| Q2_K \| 3.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-base-agentic-7b-GGUF/resolve/main/Qwen-2.5-base-agentic-7b.Q3_K_S.gguf) \| Q3_K_S \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-base-agentic-7b-GGUF/resolve/main/Qwen-2.5-base-agentic-7b.Q3_K_M.gguf) \| Q3_K_M \| 3.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-base-agentic-7b-GGUF/resolve/main/Qwen-2.5-base-agentic-7b.Q3_K_L.gguf) \| Q3_K_L \| 4.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-base-agentic-7b-GGUF/resolve/main/Qwen-2.5-base-agentic-7b.IQ4_XS.gguf) \| IQ4_XS \| 4.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-base-agentic-7b-GGUF/resolve/main/Qwen-2.5-base-agentic-7b.Q4_K_S.gguf) \| Q4_K_S \| 4.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-base-agentic-7b-GGUF/resolve/main/Qwen-2.5-base-agentic-7b.Q4_K_M.gguf) \| Q4_K_M \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-base-agentic-7b-GGUF/resolve/main/Qwen-2.5-base-agentic-7b.Q5_K_S.gguf) \| Q5_K_S \| 5.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-base-agentic-7b-GGUF/resolve/main/Qwen-2.5-base-agentic-7b.Q5_K_M.gguf) \| Q5_K_M \| 5.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-base-agentic-7b-GGUF/resolve/main/Qwen-2.5-base-agentic-7b.Q6_K.gguf) \| Q6_K \| 6.4 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-base-agentic-7b-GGUF/resolve/main/Qwen-2.5-base-agentic-7b.Q8_0.gguf) \| Q8_0 \| 8.2 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-base-agentic-7b-GGUF/resolve/main/Qwen-2.5-base-agentic-7b.f16.gguf) \| f16 \| 15.3 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
mradermacher/AetherUncensored-GGUF	mradermacher	"2025-01-12T07:05:53Z"	874	1	transformers	[ "transformers", "gguf", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:Daemontatox/AetherUncensored", "base_model:quantized:Daemontatox/AetherUncensored", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	"2025-01-10T13:02:51Z"	--- base_model: Daemontatox/AetherUncensored language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - text-generation-inference - transformers - unsloth - llama - trl --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/Daemontatox/AetherUncensored <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/AetherUncensored-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/AetherUncensored-GGUF/resolve/main/AetherUncensored.Q2_K.gguf) \| Q2_K \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/AetherUncensored-GGUF/resolve/main/AetherUncensored.Q3_K_S.gguf) \| Q3_K_S \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/AetherUncensored-GGUF/resolve/main/AetherUncensored.Q3_K_M.gguf) \| Q3_K_M \| 4.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/AetherUncensored-GGUF/resolve/main/AetherUncensored.Q3_K_L.gguf) \| Q3_K_L \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/AetherUncensored-GGUF/resolve/main/AetherUncensored.IQ4_XS.gguf) \| IQ4_XS \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/AetherUncensored-GGUF/resolve/main/AetherUncensored.Q4_K_S.gguf) \| Q4_K_S \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/AetherUncensored-GGUF/resolve/main/AetherUncensored.Q4_K_M.gguf) \| Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/AetherUncensored-GGUF/resolve/main/AetherUncensored.Q5_K_S.gguf) \| Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/AetherUncensored-GGUF/resolve/main/AetherUncensored.Q5_K_M.gguf) \| Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/AetherUncensored-GGUF/resolve/main/AetherUncensored.Q6_K.gguf) \| Q6_K \| 6.7 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/AetherUncensored-GGUF/resolve/main/AetherUncensored.Q8_0.gguf) \| Q8_0 \| 8.6 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/AetherUncensored-GGUF/resolve/main/AetherUncensored.f16.gguf) \| f16 \| 16.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
Jehadoumer/ChainAware-HadithIsnadParser-withPrefix-AraBART	Jehadoumer	"2025-02-11T18:29:48Z"	0	0	transformers	[ "transformers", "safetensors", "mbart", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	"2025-02-11T18:29:22Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
meyflex/Mixtral_SIG_v2	meyflex	"2024-03-27T14:58:05Z"	0	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "base_model:adapter:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "region:us" ]	null	"2024-03-27T14:56:20Z"	--- license: apache-2.0 library_name: peft tags: - trl - sft - generated_from_trainer datasets: - generator base_model: mistralai/Mistral-7B-Instruct-v0.2 model-index: - name: Mixtral_SIG_v2 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Mixtral_SIG_v2 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 0.6608 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2.5e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 0.03 - training_steps: 300 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 2.618 \| 0.34 \| 10 \| 2.1689 \| \| 1.5656 \| 0.69 \| 20 \| 1.6442 \| \| 1.2846 \| 1.03 \| 30 \| 1.4577 \| \| 1.144 \| 1.38 \| 40 \| 1.3486 \| \| 1.0455 \| 1.72 \| 50 \| 1.2648 \| \| 1.0073 \| 2.07 \| 60 \| 1.1995 \| \| 0.951 \| 2.41 \| 70 \| 1.1439 \| \| 0.9218 \| 2.76 \| 80 \| 1.0959 \| \| 0.8527 \| 3.1 \| 90 \| 1.0501 \| \| 0.8351 \| 3.45 \| 100 \| 0.9564 \| \| 0.7632 \| 3.79 \| 110 \| 0.9155 \| \| 0.697 \| 4.14 \| 120 \| 0.8449 \| \| 0.6341 \| 4.48 \| 130 \| 0.7953 \| \| 0.6212 \| 4.83 \| 140 \| 0.7716 \| \| 0.5881 \| 5.17 \| 150 \| 0.7591 \| \| 0.5804 \| 5.52 \| 160 \| 0.7433 \| \| 0.5694 \| 5.86 \| 170 \| 0.7309 \| \| 0.5537 \| 6.21 \| 180 \| 0.7210 \| \| 0.5466 \| 6.55 \| 190 \| 0.7129 \| \| 0.5272 \| 6.9 \| 200 \| 0.7023 \| \| 0.5106 \| 7.24 \| 210 \| 0.6936 \| \| 0.5225 \| 7.59 \| 220 \| 0.6842 \| \| 0.5062 \| 7.93 \| 230 \| 0.6783 \| \| 0.5003 \| 8.28 \| 240 \| 0.6759 \| \| 0.4931 \| 8.62 \| 250 \| 0.6712 \| \| 0.4828 \| 8.97 \| 260 \| 0.6664 \| \| 0.4642 \| 9.31 \| 270 \| 0.6641 \| \| 0.5037 \| 9.66 \| 280 \| 0.6616 \| \| 0.4674 \| 10.0 \| 290 \| 0.6607 \| \| 0.462 \| 10.34 \| 300 \| 0.6608 \| ### Framework versions - PEFT 0.10.0 - Transformers 4.37.2 - Pytorch 2.2.1 - Datasets 2.18.0 - Tokenizers 0.15.1
alex-levashov/segformer-b0-scene-parse-150	alex-levashov	"2023-11-03T12:33:23Z"	20	0	transformers	[ "transformers", "pytorch", "tensorboard", "safetensors", "segformer", "generated_from_trainer", "dataset:scene_parse_150", "base_model:nvidia/mit-b0", "base_model:finetune:nvidia/mit-b0", "license:other", "endpoints_compatible", "region:us" ]	null	"2023-03-31T10:24:18Z"	--- license: other base_model: nvidia/mit-b0 tags: - generated_from_trainer datasets: - scene_parse_150 model-index: - name: segformer-b0-scene-parse-150 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # segformer-b0-scene-parse-150 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the scene_parse_150 dataset. It achieves the following results on the evaluation set: - Loss: 2.7158 - Mean Iou: 0.0575 - Mean Accuracy: 0.0995 - Overall Accuracy: 0.4648 - Per Category Iou: [0.44672496974409803, 0.5246878610396156, 0.2073942489175086, 0.4461580147251187, 0.6709173669159216, 0.35982779947389176, 0.0005154694530654325, 0.009501153711522114, 0.23323905377607992, 0.0, 0.023848147241266732, 0.0, 0.06428503562945369, 0.0, 0.0, 0.00526018196460086, 0.0, 0.0, 0.0004003660489590483, 0.2826172203237914, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan] - Per Category Accuracy: [0.8701105877534303, 0.7649097707689807, 0.20824275665250883, 0.6818336289049002, 0.9654490232009587, 0.49512427161374717, 0.006057546693589096, 0.01288659793814433, 0.4959889393146437, nan, 0.034012615588327307, nan, 0.06484693975349345, 0.0, 0.0, 0.00827783320300914, nan, 0.0, 0.0004003660489590483, 0.4684163288044319, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan] ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 6e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Mean Iou \| Mean Accuracy \| Overall Accuracy \| Per Category Iou \| Per Category Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:-------------:\|:----------------:\|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:\|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:\| \| 2.8861 \| 10.0 \| 200 \| 3.4518 \| 0.0460 \| 0.0871 \| 0.4387 \| [0.3969301711292726, 0.407009124541566, 0.1858691819464034, 0.3487187527048191, 0.6198477877978043, 0.43618812656641603, 0.0, 0.1088497725164539, 0.05231273336889431, 0.0, 0.0, 0.0, 0.01404489007098984, 0.0, 0.0, 0.0001569283883454517, 0.0, 0.0, 0.0, 0.14669763591205962, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan] \| [0.9001446344460373, 0.6596260770606406, 0.18804276334124834, 0.609796983742136, 0.9662352814360626, 0.6622963491497206, 0.0, 0.191012324625998, 0.053624014810070224, nan, 0.0, nan, 0.014069658226149629, 0.0, 0.0, 0.0001617817564106021, nan, 0.0, 0.0, 0.19742502553310018, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan] \| \| 2.0228 \| 20.0 \| 400 \| 3.0714 \| 0.0521 \| 0.0902 \| 0.4319 \| [0.3908819659806409, 0.34176425750121264, 0.27734684694336714, 0.3467711453980972, 0.6652598893529553, 0.3993713022078525, 0.0, 0.11508504324411957, 0.16300110838512025, 0.0, 0.037551428372190325, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.18148929755803436, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan] \| [0.7808233497167042, 0.4810925052836937, 0.2885856660312364, 0.6733491542655118, 0.9645296083292647, 0.7610893090736116, 0.0, 0.15819510115494922, 0.2044742659407441, nan, 0.04701380148273178, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.24220853579276408, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan] \| \| 2.0541 \| 30.0 \| 600 \| 2.8125 \| 0.0606 \| 0.1022 \| 0.4683 \| [0.4354912810082317, 0.5136657316079992, 0.2571735614101172, 0.46600687018210146, 0.6816991679609, 0.46349720485077905, 0.003975688393168351, 0.015114196148678908, 0.14418364714985812, 0.0, 0.021026667032093622, nan, 0.012695499216091163, 0.0, 0.0, 0.0007345439706182412, 0.0, 0.0, 0.0, 0.31855511784736595, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan] \| [0.833117874940269, 0.922861323362055, 0.25877618362819527, 0.6713901002087563, 0.9657660628118877, 0.7062076346771317, 0.046062594649167087, 0.019620572048678397, 0.3056529788081643, nan, 0.02790853334691413, nan, 0.012727865207307022, 0.0, 0.0, 0.0009706905384636126, nan, 0.0, 0.0, 0.4429760762588592, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan] \| \| 1.9657 \| 40.0 \| 800 \| 2.7501 \| 0.0563 \| 0.0985 \| 0.4660 \| [0.4502025953819058, 0.5305299792942421, 0.20067731011127238, 0.47464834479446677, 0.6634585667585132, 0.3259851182020951, 0.0, 0.014531871786918676, 0.2514721268503095, 0.0, 0.03485342019543974, nan, 0.01199095889361376, 0.0, 0.0, 0.009941192943153179, 0.0, 0.0, 0.002573634543894767, 0.23698272648191873, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan] \| [0.8888362686872824, 0.7831246951715168, 0.20808668606401123, 0.6802372568673983, 0.9664445275792758, 0.40083541443691284, 0.0, 0.02133555538330362, 0.5200553034267815, nan, 0.054492939199266635, nan, 0.011999463282792463, 0.0, 0.0, 0.01340092215601154, nan, 0.0, 0.0025737817433081674, 0.47216118349788, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan] \| \| 1.608 \| 50.0 \| 1000 \| 2.7158 \| 0.0575 \| 0.0995 \| 0.4648 \| [0.44672496974409803, 0.5246878610396156, 0.2073942489175086, 0.4461580147251187, 0.6709173669159216, 0.35982779947389176, 0.0005154694530654325, 0.009501153711522114, 0.23323905377607992, 0.0, 0.023848147241266732, 0.0, 0.06428503562945369, 0.0, 0.0, 0.00526018196460086, 0.0, 0.0, 0.0004003660489590483, 0.2826172203237914, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan] \| [0.8701105877534303, 0.7649097707689807, 0.20824275665250883, 0.6818336289049002, 0.9654490232009587, 0.49512427161374717, 0.006057546693589096, 0.01288659793814433, 0.4959889393146437, nan, 0.034012615588327307, nan, 0.06484693975349345, 0.0, 0.0, 0.00827783320300914, nan, 0.0, 0.0004003660489590483, 0.4684163288044319, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan] \| ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1
llmflow/krx_Qwen2_1.5B_Instruct	llmflow	"2024-10-24T02:14:07Z"	6	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "krx", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	"2024-10-24T02:01:26Z"	--- base_model: unsloth/qwen2-7b-instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen2 - trl - sft - krx license: apache-2.0 language: - en --- # Uploaded model - Developed by: LDC-ai - License: apache-2.0 - Finetuned from model : unsloth/qwen2-7b-instruct-bnb-4bit This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
kostiantynk1205/a3347739-4156-47a9-b3f5-63beba7eda42	kostiantynk1205	"2025-01-24T10:25:42Z"	6	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:jingyeom/seal3.1.6n_7b", "base_model:adapter:jingyeom/seal3.1.6n_7b", "region:us" ]	null	"2025-01-24T10:23:54Z"	--- library_name: peft base_model: jingyeom/seal3.1.6n_7b tags: - axolotl - generated_from_trainer model-index: - name: a3347739-4156-47a9-b3f5-63beba7eda42 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: jingyeom/seal3.1.6n_7b bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 9a09f1acef25a62c_train_data.json ds_type: json format: custom path: /workspace/input_data/9a09f1acef25a62c_train_data.json type: field_input: arguments field_instruction: instruction field_output: output format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 4 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: kostiantynk1205/a3347739-4156-47a9-b3f5-63beba7eda42 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 10 micro_batch_size: 2 mlflow_experiment_name: /tmp/9a09f1acef25a62c_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 4 sequence_len: 512 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: eac52d0c-9782-4014-a17f-cfdef1d621e3 wandb_project: Birthday-SN56-6-Gradients-On-Demand wandb_run: your_name wandb_runid: eac52d0c-9782-4014-a17f-cfdef1d621e3 warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # a3347739-4156-47a9-b3f5-63beba7eda42 This model is a fine-tuned version of [jingyeom/seal3.1.6n_7b](https://huggingface.co/jingyeom/seal3.1.6n_7b) on the None dataset. It achieves the following results on the evaluation set: - Loss: nan ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.0 \| 0.0008 \| 1 \| nan \| \| 2.1563 \| 0.0024 \| 3 \| nan \| \| 0.0 \| 0.0049 \| 6 \| nan \| \| 0.0 \| 0.0073 \| 9 \| nan \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
gouthamsk/mistral-embedded-c-v0.3	gouthamsk	"2024-04-08T09:35:34Z"	11	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-04-08T09:32:01Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
IbtiHt/Agrobot-llma-ft	IbtiHt	"2024-06-21T19:40:35Z"	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	"2024-04-28T10:50:08Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
mradermacher/T-III-12B-i1-GGUF	mradermacher	"2024-08-24T18:35:14Z"	20	1	transformers	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:Frowning/T-III-12B", "base_model:quantized:Frowning/T-III-12B", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	"2024-08-24T16:43:20Z"	--- base_model: Frowning/T-III-12B language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/Frowning/T-III-12B <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/T-III-12B-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-IQ1_S.gguf) \| i1-IQ1_S \| 3.1 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-IQ1_M.gguf) \| i1-IQ1_M \| 3.3 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 3.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 4.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-IQ2_S.gguf) \| i1-IQ2_S \| 4.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-IQ2_M.gguf) \| i1-IQ2_M \| 4.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-Q2_K.gguf) \| i1-Q2_K \| 4.9 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 5.0 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 5.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 5.6 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-IQ3_S.gguf) \| i1-IQ3_S \| 5.7 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-IQ3_M.gguf) \| i1-IQ3_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 6.2 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 6.7 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 6.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-Q4_0.gguf) \| i1-Q4_0 \| 7.2 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 7.2 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 7.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 8.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 8.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/T-III-12B-i1-GGUF/resolve/main/T-III-12B.i1-Q6_K.gguf) \| i1-Q6_K \| 10.2 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
SumanthRH/OpenRLHF-smol-sft-mixture	SumanthRH	"2024-10-19T00:14:24Z"	167	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-10-19T00:06:06Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
easwar03/t5-small-finetuned-xsum	easwar03	"2024-11-01T13:37:23Z"	114	0	transformers	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "dataset:xsum", "base_model:google-t5/t5-small", "base_model:finetune:google-t5/t5-small", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	"2024-11-01T13:30:55Z"	--- library_name: transformers license: apache-2.0 base_model: t5-small tags: - generated_from_trainer datasets: - xsum model-index: - name: t5-small-finetuned-xsum results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # t5-small-finetuned-xsum This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the xsum dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\|:------:\|:-------:\|:---------:\|:-------:\| \| No log \| 1.0 \| 19 \| 3.4517 \| 17.4709 \| 2.6232 \| 13.6143 \| 13.891 \| 18.89 \| ### Framework versions - Transformers 4.44.2 - Pytorch 2.5.0+cu121 - Datasets 3.1.0 - Tokenizers 0.19.1
Livingwithmachines/mr_resnest50d_4s2x40d_timm_pretrain_railspace_and_building	Livingwithmachines	"2024-09-10T08:23:22Z"	16	0	timm	[ "timm", "pytorch", "vision", "mapreader", "maps", "National Library of Scotland", "historical", "lam", "humanities", "heritage", "image-classification", "en", "dataset:Livingwithmachines/MapReader_Data_SIGSPATIAL_2022", "arxiv:2111.15592", "license:apache-2.0", "region:us" ]	image-classification	"2023-06-28T12:09:13Z"	--- '[object Object]': null language: - en library_name: timm pipeline_tag: image-classification tags: - vision - mapreader - maps - National Library of Scotland - historical - lam - humanities - heritage license: apache-2.0 datasets: - Livingwithmachines/MapReader_Data_SIGSPATIAL_2022 --- # Model Card for mr_resnest50d_4s2x40d_timm_pretrain_railspace_and_building A ResNeSt (ResNet based architecture with Split Attention) image classification model. Trained on ImageNet-1k by paper authors and fine-tuned on gold standard annotations and outputs from early experiments using MapReader (found [here](https://huggingface.co/datasets/Livingwithmachines/MapReader_Data_SIGSPATIAL_2022)). ## Model Details ### Model Description - Model type: Image classification /feature backbone - Finetuned from model: https://huggingface.co/timm/resnest50d_4s2x40d.in1k ### Classes and labels - 0: no - 1: railspace - 2: building - 3: railspace & building ## Uses This fine-tuned version of the model is an output of the MapReader pipeline. It was used to classify 'patch' images (cells/regions) of scanned nineteenth-century series maps of Britain provided by the National Library of Scotland (learn more [here](https://maps.nls.uk/os/)). We classified patches to indicate the presence of buildings and railway infrastructure. See [our paper](https://dl.acm.org/doi/10.1145/3557919.3565812) for more details about labels. ## How to Get Started with the Model in MapReader Please go to [the MapReader documentation](https://mapreader.readthedocs.io/en/latest/User-guide/Classify.html) for instructions on how to use this model in MapReader. ## Training, Evaluation and Testing Details ### Training, Evaluation and Testing Data This model was fine-tuned on [manually-annotated data](https://huggingface.co/datasets/Livingwithmachines/MapReader_Data_SIGSPATIAL_2022). ### Training, Evaluation and Testing Procedure Details can be found [here](https://dl.acm.org/doi/10.1145/3557919.3565812). Open access version of the article available [here](https://arxiv.org/abs/2111.15592). ### Results Data outputs can be found [here](https://huggingface.co/datasets/Livingwithmachines/MapReader_Data_SIGSPATIAL_2022). Further details can be found [here](https://dl.acm.org/doi/10.1145/3557919.3565812). ## More Information This model was fine-tuned using MapReader. The code for MapReader can be found [here](https://github.com/Living-with-machines/MapReader) and the documentation can be found [here](https://mapreader.readthedocs.io/en/latest/). ## Model Card Authors - Katie McDonough ([email protected]) - Rosie Wood ([email protected]) ## Model Card Contact Katie McDonough ([email protected]) ## Funding Statement This work was supported by Living with Machines (AHRC grant AH/S01179X/1) and The Alan Turing Institute (EPSRC grant EP/N510129/1). Living with Machines, funded by the UK Research and Innovation (UKRI) Strategic Priority Fund, is a multidisciplinary collaboration delivered by the Arts and Humanities Research Council (AHRC), with The Alan Turing Institute, the British Library and Cambridge, King's College London, East Anglia, Exeter, and Queen Mary University of London.
elmurod1202/bertbek-news-big-cased	elmurod1202	"2023-06-20T10:58:46Z"	205	4	transformers	[ "transformers", "pytorch", "safetensors", "bert", "fill-mask", "uz", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	"2023-06-14T14:29:00Z"	--- license: mit language: - uz --- # BERTbek-news-big-cased A pre-trained BERT model for Uzbek (12layers, cased). Trained on big News corpus (Daryo)
bamec66557/MISCHIEVOUS-12B-Mix_Neo	bamec66557	"2024-12-20T02:33:20Z"	15	1	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "conversational", "dataset:open-llm-leaderboard/bamec66557__MISCHIEVOUS-12B-Mix_Neo-details", "base_model:bamec66557/MISCHIEVOUS-12B-Mix_0.4v", "base_model:merge:bamec66557/MISCHIEVOUS-12B-Mix_0.4v", "base_model:bamec66557/MISCHIEVOUS-12B-Mix_0.5v", "base_model:merge:bamec66557/MISCHIEVOUS-12B-Mix_0.5v", "license:apache-2.0", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-12-19T20:41:22Z"	--- license: apache-2.0 library_name: transformers tags: - mergekit - merge base_model: - bamec66557/MISCHIEVOUS-12B-Mix_0.4v - bamec66557/MISCHIEVOUS-12B-Mix_0.5v model-index: - name: MISCHIEVOUS-12B-Mix_Neo results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 62.5 name: strict accuracy source: url: >- https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_Neo name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 30.36 name: normalized accuracy source: url: >- https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_Neo name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 11.63 name: exact match source: url: >- https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_Neo name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 8.84 name: acc_norm source: url: >- https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_Neo name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 11.64 name: acc_norm source: url: >- https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_Neo name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 29.84 name: accuracy source: url: >- https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_Neo name: Open LLM Leaderboard datasets: - open-llm-leaderboard/bamec66557__MISCHIEVOUS-12B-Mix_Neo-details --- # merge This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the SLERP merge method. ### Models Merged The following models were included in the merge: * [bamec66557/MISCHIEVOUS-12B-Mix_0.4v](https://huggingface.co/bamec66557/MISCHIEVOUS-12B-Mix_0.4v) * [bamec66557/MISCHIEVOUS-12B-Mix_0.5v](https://huggingface.co/bamec66557/MISCHIEVOUS-12B-Mix_0.5v) ### Configuration The following YAML configuration was used to produce this model: ```yaml description: Merging MISCHIEVOUS-12B-Mix models with sliced slerp # Metadata and Rationale model_description: \| This configuration merges two versions of the MISCHIEVOUS-12B-Mix model: 0.4v and 0.3v. 0.3v was further fine-tuned on a specific dataset (ADD DATASET NAME HERE if known). The sliced slerp approach allows for layer-specific control over the merging process. base_model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v dtype: bfloat16 merge_method: slerp tokenizer_source: union # Slices Configuration (Layer-Specific Merging) slices: - sources: - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v layer_range: [0, 10] - model: bamec66557/MISCHIEVOUS-12B-Mix_0.5v layer_range: [0, 10] parameters: t: - name: self_attn value: [0.8, 0.85, 0.9, 0.95, 1.0] - name: mlp value: [0.9, 0.95, 1.0, 1.05, 1.1] - name: layer_norm value: [0.6, 0.65, 0.7, 0.75, 0.8] - name: embed_tokens value: [1.0] - sources: - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v layer_range: [10, 20] - model: bamec66557/MISCHIEVOUS-12B-Mix_0.5v layer_range: [10, 20] parameters: t: - name: self_attn value: [0.7, 0.75, 0.8, 0.85, 0.9] - name: mlp value: [1.0, 0.95, 0.9, 0.85, 0.8] - name: layer_norm value: [0.5, 0.55, 0.6, 0.65, 0.7] - name: embed_tokens value: [1.0] - sources: - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v layer_range: [20, 30] - model: bamec66557/MISCHIEVOUS-12B-Mix_0.5v layer_range: [20, 30] parameters: t: - name: self_attn value: [0.6, 0.65, 0.7, 0.75, 0.8] - name: mlp value: [0.8, 0.75, 0.7, 0.65, 0.6] - name: layer_norm value: [0.4, 0.45, 0.5, 0.55, 0.6] - name: embed_tokens value: [1.0] - sources: - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v layer_range: [30, 40] - model: bamec66557/MISCHIEVOUS-12B-Mix_0.5v layer_range: [30, 40] parameters: t: - name: self_attn value: [0.9, 1.0, 1.1, 1.2, 1.3] - name: mlp value: [0.7, 0.65, 0.6, 0.55, 0.5] - name: layer_norm value: [0.7, 0.75, 0.8, 0.85, 0.9] - name: embed_tokens value: [1.0] # Regularization (Prevent Overfitting During Merging) regularization: - method: weight_clipping clip_range: [-0.2, 0.2] - method: random_noise scale: 0.015 - method: l2_norm scale: 0.01 # Postprocessing (Enhance Merged Model Quality) postprocessing: - operation: random_noise scale: 0.0025 - operation: non_linear_scaling parameters: function: tanh - operation: sharpening intensity: 0.3 - operation: gaussian_smoothing sigma: 1.5 - operation: smoothing parameters: adaptive: true range: [0.8, 1.2] kernel_size: 5 - operation: normalize - operation: dynamic_scaling scale_range: [0.75, 1.25] # Evaluation (Crucial for Assessing Merge Quality) evaluation: metrics: - perplexity - accuracy # If applicable (e.g., classification tasks) - bleu # For translation tasks - rouge # For summarization tasks datasets: - wikitext # General language understanding - lambada # Long-range dependency modeling - (ADD RELEVANT TASK-SPECIFIC DATASETS HERE) prompts: # Example prompts – REPLACE WITH YOUR OWN - "The quick brown fox jumps over the lazy dog." - "Translate 'Thank you' to Spanish:" - "Write a short summary of the French Revolution." # Logging and Output logging: output_dir: ./merged_models log_level: INFO # Optional: Ties Merging (Advanced Technique) # ties: # enabled: true # method: greedy # Or "optimal", "random" # layers: [0, 10, 20, 30] # Example layers for ties merging ``` # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/bamec66557__MISCHIEVOUS-12B-Mix_Neo-details) \| Metric \|Value\| \|-------------------\|----:\| \|Avg. \|25.80\| \|IFEval (0-Shot) \|62.50\| \|BBH (3-Shot) \|30.36\| \|MATH Lvl 5 (4-Shot)\|11.63\| \|GPQA (0-shot) \| 8.84\| \|MuSR (0-shot) \|11.64\| \|MMLU-PRO (5-shot) \|29.84\|
tsavage68/MedQA_L3_1000steps_1e5rate_SFT	tsavage68	"2024-05-18T19:58:17Z"	8	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "trl", "sft", "generated_from_trainer", "conversational", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "base_model:finetune:meta-llama/Meta-Llama-3-8B-Instruct", "license:llama3", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-05-18T19:54:38Z"	--- license: llama3 base_model: meta-llama/Meta-Llama-3-8B-Instruct tags: - trl - sft - generated_from_trainer model-index: - name: MedQA_L3_1000steps_1e5rate_SFT results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # MedQA_L3_1000steps_1e5rate_SFT This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3681 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 2 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 100 - training_steps: 1000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.4577 \| 0.0489 \| 50 \| 0.5024 \| \| 0.4969 \| 0.0977 \| 100 \| 0.4876 \| \| 0.4689 \| 0.1466 \| 150 \| 0.4380 \| \| 0.4891 \| 0.1954 \| 200 \| 0.4313 \| \| 0.424 \| 0.2443 \| 250 \| 0.4275 \| \| 0.4408 \| 0.2931 \| 300 \| 0.4208 \| \| 0.4124 \| 0.3420 \| 350 \| 0.4160 \| \| 0.4012 \| 0.3908 \| 400 \| 0.4113 \| \| 0.4305 \| 0.4397 \| 450 \| 0.4285 \| \| 0.4031 \| 0.4885 \| 500 \| 0.3974 \| \| 0.3863 \| 0.5374 \| 550 \| 0.3916 \| \| 0.3981 \| 0.5862 \| 600 \| 0.3861 \| \| 0.3705 \| 0.6351 \| 650 \| 0.3810 \| \| 0.3591 \| 0.6839 \| 700 \| 0.3760 \| \| 0.3642 \| 0.7328 \| 750 \| 0.3722 \| \| 0.3712 \| 0.7816 \| 800 \| 0.3699 \| \| 0.3893 \| 0.8305 \| 850 \| 0.3686 \| \| 0.3512 \| 0.8793 \| 900 \| 0.3682 \| \| 0.3546 \| 0.9282 \| 950 \| 0.3681 \| \| 0.3736 \| 0.9770 \| 1000 \| 0.3681 \| ### Framework versions - Transformers 4.41.0 - Pytorch 2.0.0+cu117 - Datasets 2.19.1 - Tokenizers 0.19.1
nat-hunt/2e7863e4-5614-4227-ad2e-761543858daf	nat-hunt	"2025-01-17T15:34:10Z"	11	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:upstage/SOLAR-10.7B-Instruct-v1.0", "base_model:adapter:upstage/SOLAR-10.7B-Instruct-v1.0", "license:cc-by-nc-4.0", "region:us" ]	null	"2025-01-17T15:20:55Z"	--- library_name: peft license: cc-by-nc-4.0 base_model: upstage/SOLAR-10.7B-Instruct-v1.0 tags: - axolotl - generated_from_trainer model-index: - name: 2e7863e4-5614-4227-ad2e-761543858daf results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: upstage/SOLAR-10.7B-Instruct-v1.0 bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 8c0a3b008ff7d88c_train_data.json ds_type: json format: custom path: /workspace/input_data/8c0a3b008ff7d88c_train_data.json type: field_instruction: prompt field_output: reference_response format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 4 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: nat-hunt/2e7863e4-5614-4227-ad2e-761543858daf hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 10 micro_batch_size: 2 mlflow_experiment_name: /tmp/8c0a3b008ff7d88c_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 4 sequence_len: 512 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: d61742d2-7873-491b-9a75-3c6a2fc849c2 wandb_project: Birthday-SN56-4-Gradients-On-Demand wandb_run: your_name wandb_runid: d61742d2-7873-491b-9a75-3c6a2fc849c2 warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # 2e7863e4-5614-4227-ad2e-761543858daf This model is a fine-tuned version of [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0) on the None dataset. It achieves the following results on the evaluation set: - Loss: nan ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.1491 \| 0.0002 \| 1 \| nan \| \| 0.0 \| 0.0005 \| 3 \| nan \| \| 0.0 \| 0.0010 \| 6 \| nan \| \| 0.0 \| 0.0015 \| 9 \| nan \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
EMBO/SourceData_GENEPROD-ROLES_v_1-0-0_BioLinkBERT_base	EMBO	"2024-01-03T10:53:45Z"	173	0	transformers	[ "transformers", "pytorch", "bert", "token-classification", "generated_from_trainer", "dataset:source_data", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	"2024-01-03T10:42:56Z"	--- license: apache-2.0 tags: - generated_from_trainer datasets: - source_data metrics: - precision - recall - f1 model-index: - name: SourceData_GENEPROD-ROLES_v_1-0-0_BioLinkBERT_base results: - task: name: Token Classification type: token-classification dataset: name: source_data type: source_data args: ROLES_GP metrics: - name: Precision type: precision value: 0.9221463136920012 - name: Recall type: recall value: 0.9271166229430002 - name: F1 type: f1 value: 0.9246247889065956 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # SourceData_GENEPROD-ROLES_v_1-0-0_BioLinkBERT_base This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-base](https://huggingface.co/michiyasunaga/BioLinkBERT-base) on the source_data dataset. It achieves the following results on the evaluation set: - Loss: 0.0137 - Accuracy Score: 0.9948 - Precision: 0.9221 - Recall: 0.9271 - F1: 0.9246 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 256 - seed: 42 - optimizer: Adafactor - lr_scheduler_type: linear - num_epochs: 1.0 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy Score \| Precision \| Recall \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------------:\|:---------:\|:------:\|:------:\| \| 0.0153 \| 1.0 \| 432 \| 0.0137 \| 0.9948 \| 0.9221 \| 0.9271 \| 0.9246 \| ### Framework versions - Transformers 4.20.1 - Pytorch 1.11.0a0+bfe5ad2 - Datasets 2.10.1 - Tokenizers 0.12.1
MikeRoz/ArliAI_Llama-3.1-70B-ArliAI-RPMax-v1.1-3.5bpw-h6-exl2	MikeRoz	"2024-10-01T05:42:51Z"	5	1	null	[ "safetensors", "llama", "license:llama3", "exl2", "region:us" ]	null	"2024-10-01T03:46:05Z"	--- license: llama3 --- # Llama-3.1-70B-ArliAI-RPMax-v1.1 ===================================== ## RPMax Series Overview \| [2B](https://huggingface.co/ArliAI/Gemma-2-2B-ArliAI-RPMax-v1.1) \| [3.8B](https://huggingface.co/ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1) \| [8B](https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1) \| [9B](https://huggingface.co/ArliAI/Gemma-2-9B-ArliAI-RPMax-v1.1) \| [12B](https://huggingface.co/ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1) \| [20B](https://huggingface.co/ArliAI/InternLM2_5-20B-ArliAI-RPMax-v1.1) \| [22B](https://huggingface.co/ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1) \| [70B](https://huggingface.co/ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.1) \| RPMax is a series of models that are trained on a diverse set of curated creative writing and RP datasets with a focus on variety and deduplication. This model is designed to be highly creative and non-repetitive by making sure no two entries in the dataset have repeated characters or situations, which makes sure the model does not latch on to a certain personality and be capable of understanding and acting appropriately to any characters or situations. Early tests by users mentioned that these models does not feel like any other RP models, having a different style and generally doesn't feel in-bred. You can access the model at https://arliai.com and ask questions at https://www.reddit.com/r/ArliAI/ We also have a models ranking page at https://www.arliai.com/models-ranking Ask questions in our new Discord Server! https://discord.gg/aDVx6FZN ## Model Description Llama-3.1-70B-ArliAI-RPMax-v1.1 is a variant of the Meta-Llama-3.1-70B-Instruct model. This version is an early test on 70B that is only run with a short sequence length for training, we are planning to run another training with higher sequence length. Let us know what you think of the model! The 8B and 12B versions of RPMax had great feedback from users, so we expect this 70B version to one of the best RP models. ### Training Details * Sequence Length: 4096 * Training Duration: Approximately 5 days on 2x3090Ti * Epochs: 1 epoch training for minimized repetition sickness * LORA: 64-rank 128-alpha, resulting in ~2% trainable weights * Learning Rate: 0.00001 * Gradient accumulation: Very low 32 for better learning. ## Quantization The model is available in quantized formats: We recommend using full weights or GPTQ. GGUF provided by https://huggingface.co/mradermacher/Llama-3.1-70B-ArliAI-RPMax-v1.1-GGUF * FP16: https://huggingface.co/ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.1 * GPTQ_Q4: https://huggingface.co/ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.1-GPTQ_Q4 * GPTQ_Q8: https://huggingface.co/ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.1-GPTQ_Q8 * GGUF: https://huggingface.co/ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.1-GGUF ## Suggested Prompt Format Llama 3 Instruct Format Example: ``` <\|begin_of_text\|><\|start_header_id\|>system<\|end_header_id\|> You are [character]. You have a personality of [personality description]. [Describe scenario]<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> {{ user_message_1 }}<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|> {{ model_answer_1 }}<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> {{ user_message_2 }}<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|> ```
mmmino/doctor	mmmino	"2023-12-02T08:56:36Z"	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:squarelike/llama2-ko-medical-7b", "base_model:adapter:squarelike/llama2-ko-medical-7b", "region:us" ]	null	"2023-12-02T08:56:09Z"	--- library_name: peft base_model: squarelike/llama2-ko-medical-7b --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.6.3.dev0
stuartmesham/deberta-v3-large_lemon-spell_5k_1_p3	stuartmesham	"2022-10-24T16:36:24Z"	6	0	transformers	[ "transformers", "pytorch", "deberta-v2", "token-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	"2022-10-24T16:35:01Z"	--- tags: - generated_from_trainer metrics: - accuracy model-index: - name: deberta-v3-large_lemon-spell_5k_1_p3 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # deberta-v3-large_lemon-spell_5k_1_p3 This model is a fine-tuned version of [model_saves/deberta-v3-large_lemon-spell_5k_1_p2](https://huggingface.co/model_saves/deberta-v3-large_lemon-spell_5k_1_p2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4106 - Accuracy: 0.9421 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - num_epochs: 15.0 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 268 \| 0.4106 \| 0.9421 \| \| No log \| 2.0 \| 536 \| 0.4260 \| 0.9418 \| \| No log \| 3.0 \| 804 \| 0.4570 \| 0.9414 \| \| 0.2933 \| 4.0 \| 1072 \| 0.4891 \| 0.9402 \| ### Framework versions - Transformers 4.21.0.dev0 - Pytorch 1.11.0+cu113 - Datasets 2.3.2 - Tokenizers 0.12.1
Gabcsor/Reinforce-PixelCopter_v2	Gabcsor	"2023-03-07T14:52:47Z"	0	0	null	[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	"2023-03-07T14:52:44Z"	--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-PixelCopter_v2 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 7.10 +/- 10.17 name: mean_reward verified: false --- # Reinforce Agent playing Pixelcopter-PLE-v0 This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
mrferr3t/40f2fb54-d7e6-4812-be11-e63df45f5a83	mrferr3t	"2025-01-30T08:07:04Z"	8	0	peft	[ "peft", "safetensors", "qwen2", "axolotl", "generated_from_trainer", "base_model:Qwen/Qwen2.5-0.5B", "base_model:adapter:Qwen/Qwen2.5-0.5B", "license:apache-2.0", "region:us" ]	null	"2025-01-30T08:00:55Z"	--- library_name: peft license: apache-2.0 base_model: Qwen/Qwen2.5-0.5B tags: - axolotl - generated_from_trainer model-index: - name: 40f2fb54-d7e6-4812-be11-e63df45f5a83 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: Qwen/Qwen2.5-0.5B bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - d29377c015063976_train_data.json ds_type: json format: custom path: /workspace/input_data/d29377c015063976_train_data.json type: field_input: queries_old field_instruction: long_query field_output: product_text format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_steps: 30 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: mrferr3t/40f2fb54-d7e6-4812-be11-e63df45f5a83 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0005 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 100 micro_batch_size: 2 mlflow_experiment_name: /tmp/d29377c015063976_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false save_steps: 300 saves_per_epoch: 0 sequence_len: 512 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 34b92764-f84f-4ee8-a37c-781383fee0a5 wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: 34b92764-f84f-4ee8-a37c-781383fee0a5 warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # 40f2fb54-d7e6-4812-be11-e63df45f5a83 This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.8079 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 3.5149 \| 0.0004 \| 1 \| 3.6245 \| \| 2.7282 \| 0.0125 \| 30 \| 2.8827 \| \| 2.8515 \| 0.0250 \| 60 \| 2.8310 \| \| 3.1856 \| 0.0376 \| 90 \| 2.8079 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.3.1+cu121 - Datasets 3.0.1 - Tokenizers 0.20.1
prxy5607/f7293db8-0de2-4e19-a611-d5a58c0e425b	prxy5607	"2025-01-20T07:21:50Z"	7	0	peft	[ "peft", "safetensors", "opt", "axolotl", "generated_from_trainer", "base_model:facebook/opt-1.3b", "base_model:adapter:facebook/opt-1.3b", "license:other", "region:us" ]	null	"2025-01-20T07:11:15Z"	--- library_name: peft license: other base_model: facebook/opt-1.3b tags: - axolotl - generated_from_trainer model-index: - name: f7293db8-0de2-4e19-a611-d5a58c0e425b results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: facebook/opt-1.3b bf16: true chat_template: llama3 data_processes: 16 dataset_prepared_path: null datasets: - data_files: - 757b0458c641616e_train_data.json ds_type: json format: custom path: /workspace/input_data/757b0458c641616e_train_data.json type: field_input: language field_instruction: url field_output: text format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null device_map: auto do_eval: true early_stopping_patience: 5 eval_batch_size: 4 eval_max_new_tokens: 128 eval_steps: 50 eval_table_size: null evals_per_epoch: null flash_attention: true fp16: false fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: true group_by_length: true hub_model_id: prxy5607/f7293db8-0de2-4e19-a611-d5a58c0e425b hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0001 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 128 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 64 lora_target_linear: true lr_scheduler: cosine max_grad_norm: 1.0 max_memory: 0: 75GB max_steps: 200 micro_batch_size: 8 mlflow_experiment_name: /tmp/757b0458c641616e_train_data.json model_type: AutoModelForCausalLM num_epochs: 3 optim_args: adam_beta1: 0.9 adam_beta2: 0.95 adam_epsilon: 1e-5 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false save_steps: 50 saves_per_epoch: null sequence_len: 1024 strict: false tf32: true tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: d5ba2543-9a01-4db3-bc01-98e33dde829a wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: d5ba2543-9a01-4db3-bc01-98e33dde829a warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # f7293db8-0de2-4e19-a611-d5a58c0e425b This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.4665 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 8 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 9.7126 \| 0.0034 \| 1 \| 2.5636 \| \| 10.757 \| 0.1718 \| 50 \| 2.5148 \| \| 11.0539 \| 0.3436 \| 100 \| 2.4840 \| \| 10.5692 \| 0.5155 \| 150 \| 2.4706 \| \| 11.2552 \| 0.6873 \| 200 \| 2.4665 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
SidXXD/pgd_2-dds_sds-dds_False-for_train	SidXXD	"2025-02-13T11:38:13Z"	0	0	diffusers	[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "custom-diffusion", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]	text-to-image	"2025-02-13T11:34:29Z"	--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 instance_prompt: photo of a sks cat tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - custom-diffusion inference: true --- # Custom Diffusion - SidXXD/pgd_2-dds_sds-dds_False-for_train These are Custom Diffusion adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on photo of a sks cat using [Custom Diffusion](https://www.cs.cmu.edu/~custom-diffusion). You can find some example images in the following. For more details on the training, please follow [this link](https://github.com/huggingface/diffusers/blob/main/examples/custom_diffusion).
jncraton/bge-small-en-ct2-int8	jncraton	"2023-08-20T11:47:29Z"	13	0	transformers	[ "transformers", "mteb", "sentence transformers", "sentence-similarity", "en", "license:mit", "model-index", "endpoints_compatible", "region:us" ]	sentence-similarity	"2023-08-20T11:37:33Z"	--- tags: - mteb - sentence transformers model-index: - name: bge-small-en results: - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (en) config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 74.34328358208955 - type: ap value: 37.59947775195661 - type: f1 value: 68.548415491933 - task: type: Classification dataset: type: mteb/amazon_polarity name: MTEB AmazonPolarityClassification config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 93.04527499999999 - type: ap value: 89.60696356772135 - type: f1 value: 93.03361469382438 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (en) config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 46.08 - type: f1 value: 45.66249835363254 - task: type: Retrieval dataset: type: arguana name: MTEB ArguAna config: default split: test revision: None metrics: - type: map_at_1 value: 35.205999999999996 - type: map_at_10 value: 50.782000000000004 - type: map_at_100 value: 51.547 - type: map_at_1000 value: 51.554 - type: map_at_3 value: 46.515 - type: map_at_5 value: 49.296 - type: mrr_at_1 value: 35.632999999999996 - type: mrr_at_10 value: 50.958999999999996 - type: mrr_at_100 value: 51.724000000000004 - type: mrr_at_1000 value: 51.731 - type: mrr_at_3 value: 46.669 - type: mrr_at_5 value: 49.439 - type: ndcg_at_1 value: 35.205999999999996 - type: ndcg_at_10 value: 58.835 - type: ndcg_at_100 value: 62.095 - type: ndcg_at_1000 value: 62.255 - type: ndcg_at_3 value: 50.255 - type: ndcg_at_5 value: 55.296 - type: precision_at_1 value: 35.205999999999996 - type: precision_at_10 value: 8.421 - type: precision_at_100 value: 0.984 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 20.365 - type: precision_at_5 value: 14.680000000000001 - type: recall_at_1 value: 35.205999999999996 - type: recall_at_10 value: 84.211 - type: recall_at_100 value: 98.43499999999999 - type: recall_at_1000 value: 99.644 - type: recall_at_3 value: 61.095 - type: recall_at_5 value: 73.4 - task: type: Clustering dataset: type: mteb/arxiv-clustering-p2p name: MTEB ArxivClusteringP2P config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 47.52644476278646 - task: type: Clustering dataset: type: mteb/arxiv-clustering-s2s name: MTEB ArxivClusteringS2S config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 39.973045724188964 - task: type: Reranking dataset: type: mteb/askubuntudupquestions-reranking name: MTEB AskUbuntuDupQuestions config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 62.28285314871488 - type: mrr value: 74.52743701358659 - task: type: STS dataset: type: mteb/biosses-sts name: MTEB BIOSSES config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 80.09041909160327 - type: cos_sim_spearman value: 79.96266537706944 - type: euclidean_pearson value: 79.50774978162241 - type: euclidean_spearman value: 79.9144715078551 - type: manhattan_pearson value: 79.2062139879302 - type: manhattan_spearman value: 79.35000081468212 - task: type: Classification dataset: type: mteb/banking77 name: MTEB Banking77Classification config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 85.31493506493506 - type: f1 value: 85.2704557977762 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-p2p name: MTEB BiorxivClusteringP2P config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 39.6837242810816 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-s2s name: MTEB BiorxivClusteringS2S config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 35.38881249555897 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackAndroidRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 27.884999999999998 - type: map_at_10 value: 39.574 - type: map_at_100 value: 40.993 - type: map_at_1000 value: 41.129 - type: map_at_3 value: 36.089 - type: map_at_5 value: 38.191 - type: mrr_at_1 value: 34.477999999999994 - type: mrr_at_10 value: 45.411 - type: mrr_at_100 value: 46.089999999999996 - type: mrr_at_1000 value: 46.147 - type: mrr_at_3 value: 42.346000000000004 - type: mrr_at_5 value: 44.292 - type: ndcg_at_1 value: 34.477999999999994 - type: ndcg_at_10 value: 46.123999999999995 - type: ndcg_at_100 value: 51.349999999999994 - type: ndcg_at_1000 value: 53.578 - type: ndcg_at_3 value: 40.824 - type: ndcg_at_5 value: 43.571 - type: precision_at_1 value: 34.477999999999994 - type: precision_at_10 value: 8.841000000000001 - type: precision_at_100 value: 1.4460000000000002 - type: precision_at_1000 value: 0.192 - type: precision_at_3 value: 19.742 - type: precision_at_5 value: 14.421000000000001 - type: recall_at_1 value: 27.884999999999998 - type: recall_at_10 value: 59.087 - type: recall_at_100 value: 80.609 - type: recall_at_1000 value: 95.054 - type: recall_at_3 value: 44.082 - type: recall_at_5 value: 51.593999999999994 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackEnglishRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.639 - type: map_at_10 value: 40.047 - type: map_at_100 value: 41.302 - type: map_at_1000 value: 41.425 - type: map_at_3 value: 37.406 - type: map_at_5 value: 38.934000000000005 - type: mrr_at_1 value: 37.707 - type: mrr_at_10 value: 46.082 - type: mrr_at_100 value: 46.745 - type: mrr_at_1000 value: 46.786 - type: mrr_at_3 value: 43.980999999999995 - type: mrr_at_5 value: 45.287 - type: ndcg_at_1 value: 37.707 - type: ndcg_at_10 value: 45.525 - type: ndcg_at_100 value: 49.976 - type: ndcg_at_1000 value: 51.94499999999999 - type: ndcg_at_3 value: 41.704 - type: ndcg_at_5 value: 43.596000000000004 - type: precision_at_1 value: 37.707 - type: precision_at_10 value: 8.465 - type: precision_at_100 value: 1.375 - type: precision_at_1000 value: 0.183 - type: precision_at_3 value: 19.979 - type: precision_at_5 value: 14.115 - type: recall_at_1 value: 30.639 - type: recall_at_10 value: 54.775 - type: recall_at_100 value: 73.678 - type: recall_at_1000 value: 86.142 - type: recall_at_3 value: 43.230000000000004 - type: recall_at_5 value: 48.622 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGamingRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 38.038 - type: map_at_10 value: 49.922 - type: map_at_100 value: 51.032 - type: map_at_1000 value: 51.085 - type: map_at_3 value: 46.664 - type: map_at_5 value: 48.588 - type: mrr_at_1 value: 43.95 - type: mrr_at_10 value: 53.566 - type: mrr_at_100 value: 54.318999999999996 - type: mrr_at_1000 value: 54.348 - type: mrr_at_3 value: 51.066 - type: mrr_at_5 value: 52.649 - type: ndcg_at_1 value: 43.95 - type: ndcg_at_10 value: 55.676 - type: ndcg_at_100 value: 60.126000000000005 - type: ndcg_at_1000 value: 61.208 - type: ndcg_at_3 value: 50.20400000000001 - type: ndcg_at_5 value: 53.038 - type: precision_at_1 value: 43.95 - type: precision_at_10 value: 8.953 - type: precision_at_100 value: 1.2109999999999999 - type: precision_at_1000 value: 0.135 - type: precision_at_3 value: 22.256999999999998 - type: precision_at_5 value: 15.524 - type: recall_at_1 value: 38.038 - type: recall_at_10 value: 69.15 - type: recall_at_100 value: 88.31599999999999 - type: recall_at_1000 value: 95.993 - type: recall_at_3 value: 54.663 - type: recall_at_5 value: 61.373 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGisRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.872 - type: map_at_10 value: 32.912 - type: map_at_100 value: 33.972 - type: map_at_1000 value: 34.046 - type: map_at_3 value: 30.361 - type: map_at_5 value: 31.704 - type: mrr_at_1 value: 26.779999999999998 - type: mrr_at_10 value: 34.812 - type: mrr_at_100 value: 35.754999999999995 - type: mrr_at_1000 value: 35.809000000000005 - type: mrr_at_3 value: 32.335 - type: mrr_at_5 value: 33.64 - type: ndcg_at_1 value: 26.779999999999998 - type: ndcg_at_10 value: 37.623 - type: ndcg_at_100 value: 42.924 - type: ndcg_at_1000 value: 44.856 - type: ndcg_at_3 value: 32.574 - type: ndcg_at_5 value: 34.842 - type: precision_at_1 value: 26.779999999999998 - type: precision_at_10 value: 5.729 - type: precision_at_100 value: 0.886 - type: precision_at_1000 value: 0.109 - type: precision_at_3 value: 13.559 - type: precision_at_5 value: 9.469 - type: recall_at_1 value: 24.872 - type: recall_at_10 value: 50.400999999999996 - type: recall_at_100 value: 74.954 - type: recall_at_1000 value: 89.56 - type: recall_at_3 value: 36.726 - type: recall_at_5 value: 42.138999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackMathematicaRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.803 - type: map_at_10 value: 24.348 - type: map_at_100 value: 25.56 - type: map_at_1000 value: 25.668000000000003 - type: map_at_3 value: 21.811 - type: map_at_5 value: 23.287 - type: mrr_at_1 value: 20.771 - type: mrr_at_10 value: 28.961 - type: mrr_at_100 value: 29.979 - type: mrr_at_1000 value: 30.046 - type: mrr_at_3 value: 26.555 - type: mrr_at_5 value: 28.060000000000002 - type: ndcg_at_1 value: 20.771 - type: ndcg_at_10 value: 29.335 - type: ndcg_at_100 value: 35.188 - type: ndcg_at_1000 value: 37.812 - type: ndcg_at_3 value: 24.83 - type: ndcg_at_5 value: 27.119 - type: precision_at_1 value: 20.771 - type: precision_at_10 value: 5.4350000000000005 - type: precision_at_100 value: 0.9480000000000001 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 11.982 - type: precision_at_5 value: 8.831 - type: recall_at_1 value: 16.803 - type: recall_at_10 value: 40.039 - type: recall_at_100 value: 65.83200000000001 - type: recall_at_1000 value: 84.478 - type: recall_at_3 value: 27.682000000000002 - type: recall_at_5 value: 33.535 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackPhysicsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 28.345 - type: map_at_10 value: 37.757000000000005 - type: map_at_100 value: 39.141 - type: map_at_1000 value: 39.262 - type: map_at_3 value: 35.183 - type: map_at_5 value: 36.592 - type: mrr_at_1 value: 34.649 - type: mrr_at_10 value: 43.586999999999996 - type: mrr_at_100 value: 44.481 - type: mrr_at_1000 value: 44.542 - type: mrr_at_3 value: 41.29 - type: mrr_at_5 value: 42.642 - type: ndcg_at_1 value: 34.649 - type: ndcg_at_10 value: 43.161 - type: ndcg_at_100 value: 48.734 - type: ndcg_at_1000 value: 51.046 - type: ndcg_at_3 value: 39.118 - type: ndcg_at_5 value: 41.022 - type: precision_at_1 value: 34.649 - type: precision_at_10 value: 7.603 - type: precision_at_100 value: 1.209 - type: precision_at_1000 value: 0.157 - type: precision_at_3 value: 18.319 - type: precision_at_5 value: 12.839 - type: recall_at_1 value: 28.345 - type: recall_at_10 value: 53.367 - type: recall_at_100 value: 76.453 - type: recall_at_1000 value: 91.82000000000001 - type: recall_at_3 value: 41.636 - type: recall_at_5 value: 46.760000000000005 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackProgrammersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 22.419 - type: map_at_10 value: 31.716 - type: map_at_100 value: 33.152 - type: map_at_1000 value: 33.267 - type: map_at_3 value: 28.74 - type: map_at_5 value: 30.48 - type: mrr_at_1 value: 28.310999999999996 - type: mrr_at_10 value: 37.039 - type: mrr_at_100 value: 38.09 - type: mrr_at_1000 value: 38.145 - type: mrr_at_3 value: 34.437 - type: mrr_at_5 value: 36.024 - type: ndcg_at_1 value: 28.310999999999996 - type: ndcg_at_10 value: 37.41 - type: ndcg_at_100 value: 43.647999999999996 - type: ndcg_at_1000 value: 46.007 - type: ndcg_at_3 value: 32.509 - type: ndcg_at_5 value: 34.943999999999996 - type: precision_at_1 value: 28.310999999999996 - type: precision_at_10 value: 6.963 - type: precision_at_100 value: 1.1860000000000002 - type: precision_at_1000 value: 0.154 - type: precision_at_3 value: 15.867999999999999 - type: precision_at_5 value: 11.507000000000001 - type: recall_at_1 value: 22.419 - type: recall_at_10 value: 49.28 - type: recall_at_100 value: 75.802 - type: recall_at_1000 value: 92.032 - type: recall_at_3 value: 35.399 - type: recall_at_5 value: 42.027 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.669249999999998 - type: map_at_10 value: 33.332583333333325 - type: map_at_100 value: 34.557833333333335 - type: map_at_1000 value: 34.67141666666666 - type: map_at_3 value: 30.663166666666662 - type: map_at_5 value: 32.14883333333333 - type: mrr_at_1 value: 29.193833333333334 - type: mrr_at_10 value: 37.47625 - type: mrr_at_100 value: 38.3545 - type: mrr_at_1000 value: 38.413166666666676 - type: mrr_at_3 value: 35.06741666666667 - type: mrr_at_5 value: 36.450666666666656 - type: ndcg_at_1 value: 29.193833333333334 - type: ndcg_at_10 value: 38.505416666666676 - type: ndcg_at_100 value: 43.81125 - type: ndcg_at_1000 value: 46.09558333333333 - type: ndcg_at_3 value: 33.90916666666667 - type: ndcg_at_5 value: 36.07666666666666 - type: precision_at_1 value: 29.193833333333334 - type: precision_at_10 value: 6.7251666666666665 - type: precision_at_100 value: 1.1058333333333332 - type: precision_at_1000 value: 0.14833333333333332 - type: precision_at_3 value: 15.554166666666665 - type: precision_at_5 value: 11.079250000000002 - type: recall_at_1 value: 24.669249999999998 - type: recall_at_10 value: 49.75583333333332 - type: recall_at_100 value: 73.06908333333332 - type: recall_at_1000 value: 88.91316666666667 - type: recall_at_3 value: 36.913250000000005 - type: recall_at_5 value: 42.48641666666666 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackStatsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.044999999999998 - type: map_at_10 value: 30.349999999999998 - type: map_at_100 value: 31.273 - type: map_at_1000 value: 31.362000000000002 - type: map_at_3 value: 28.508 - type: map_at_5 value: 29.369 - type: mrr_at_1 value: 26.994 - type: mrr_at_10 value: 33.12 - type: mrr_at_100 value: 33.904 - type: mrr_at_1000 value: 33.967000000000006 - type: mrr_at_3 value: 31.365 - type: mrr_at_5 value: 32.124 - type: ndcg_at_1 value: 26.994 - type: ndcg_at_10 value: 34.214 - type: ndcg_at_100 value: 38.681 - type: ndcg_at_1000 value: 40.926 - type: ndcg_at_3 value: 30.725 - type: ndcg_at_5 value: 31.967000000000002 - type: precision_at_1 value: 26.994 - type: precision_at_10 value: 5.215 - type: precision_at_100 value: 0.807 - type: precision_at_1000 value: 0.108 - type: precision_at_3 value: 12.986 - type: precision_at_5 value: 8.712 - type: recall_at_1 value: 24.044999999999998 - type: recall_at_10 value: 43.456 - type: recall_at_100 value: 63.675000000000004 - type: recall_at_1000 value: 80.05499999999999 - type: recall_at_3 value: 33.561 - type: recall_at_5 value: 36.767 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackTexRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 15.672 - type: map_at_10 value: 22.641 - type: map_at_100 value: 23.75 - type: map_at_1000 value: 23.877000000000002 - type: map_at_3 value: 20.219 - type: map_at_5 value: 21.648 - type: mrr_at_1 value: 18.823 - type: mrr_at_10 value: 26.101999999999997 - type: mrr_at_100 value: 27.038 - type: mrr_at_1000 value: 27.118 - type: mrr_at_3 value: 23.669 - type: mrr_at_5 value: 25.173000000000002 - type: ndcg_at_1 value: 18.823 - type: ndcg_at_10 value: 27.176000000000002 - type: ndcg_at_100 value: 32.42 - type: ndcg_at_1000 value: 35.413 - type: ndcg_at_3 value: 22.756999999999998 - type: ndcg_at_5 value: 25.032 - type: precision_at_1 value: 18.823 - type: precision_at_10 value: 5.034000000000001 - type: precision_at_100 value: 0.895 - type: precision_at_1000 value: 0.132 - type: precision_at_3 value: 10.771 - type: precision_at_5 value: 8.1 - type: recall_at_1 value: 15.672 - type: recall_at_10 value: 37.296 - type: recall_at_100 value: 60.863 - type: recall_at_1000 value: 82.234 - type: recall_at_3 value: 25.330000000000002 - type: recall_at_5 value: 30.964000000000002 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackUnixRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.633 - type: map_at_10 value: 32.858 - type: map_at_100 value: 34.038000000000004 - type: map_at_1000 value: 34.141 - type: map_at_3 value: 30.209000000000003 - type: map_at_5 value: 31.567 - type: mrr_at_1 value: 28.358 - type: mrr_at_10 value: 36.433 - type: mrr_at_100 value: 37.352000000000004 - type: mrr_at_1000 value: 37.41 - type: mrr_at_3 value: 34.033 - type: mrr_at_5 value: 35.246 - type: ndcg_at_1 value: 28.358 - type: ndcg_at_10 value: 37.973 - type: ndcg_at_100 value: 43.411 - type: ndcg_at_1000 value: 45.747 - type: ndcg_at_3 value: 32.934999999999995 - type: ndcg_at_5 value: 35.013 - type: precision_at_1 value: 28.358 - type: precision_at_10 value: 6.418 - type: precision_at_100 value: 1.02 - type: precision_at_1000 value: 0.133 - type: precision_at_3 value: 14.677000000000001 - type: precision_at_5 value: 10.335999999999999 - type: recall_at_1 value: 24.633 - type: recall_at_10 value: 50.048 - type: recall_at_100 value: 73.821 - type: recall_at_1000 value: 90.046 - type: recall_at_3 value: 36.284 - type: recall_at_5 value: 41.370000000000005 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWebmastersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 23.133 - type: map_at_10 value: 31.491999999999997 - type: map_at_100 value: 33.062000000000005 - type: map_at_1000 value: 33.256 - type: map_at_3 value: 28.886 - type: map_at_5 value: 30.262 - type: mrr_at_1 value: 28.063 - type: mrr_at_10 value: 36.144 - type: mrr_at_100 value: 37.14 - type: mrr_at_1000 value: 37.191 - type: mrr_at_3 value: 33.762 - type: mrr_at_5 value: 34.997 - type: ndcg_at_1 value: 28.063 - type: ndcg_at_10 value: 36.951 - type: ndcg_at_100 value: 43.287 - type: ndcg_at_1000 value: 45.777 - type: ndcg_at_3 value: 32.786 - type: ndcg_at_5 value: 34.65 - type: precision_at_1 value: 28.063 - type: precision_at_10 value: 7.055 - type: precision_at_100 value: 1.476 - type: precision_at_1000 value: 0.22899999999999998 - type: precision_at_3 value: 15.481 - type: precision_at_5 value: 11.186 - type: recall_at_1 value: 23.133 - type: recall_at_10 value: 47.285 - type: recall_at_100 value: 76.176 - type: recall_at_1000 value: 92.176 - type: recall_at_3 value: 35.223 - type: recall_at_5 value: 40.142 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWordpressRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 19.547 - type: map_at_10 value: 26.374 - type: map_at_100 value: 27.419 - type: map_at_1000 value: 27.539 - type: map_at_3 value: 23.882 - type: map_at_5 value: 25.163999999999998 - type: mrr_at_1 value: 21.442 - type: mrr_at_10 value: 28.458 - type: mrr_at_100 value: 29.360999999999997 - type: mrr_at_1000 value: 29.448999999999998 - type: mrr_at_3 value: 25.97 - type: mrr_at_5 value: 27.273999999999997 - type: ndcg_at_1 value: 21.442 - type: ndcg_at_10 value: 30.897000000000002 - type: ndcg_at_100 value: 35.99 - type: ndcg_at_1000 value: 38.832 - type: ndcg_at_3 value: 25.944 - type: ndcg_at_5 value: 28.126 - type: precision_at_1 value: 21.442 - type: precision_at_10 value: 4.9910000000000005 - type: precision_at_100 value: 0.8109999999999999 - type: precision_at_1000 value: 0.11800000000000001 - type: precision_at_3 value: 11.029 - type: precision_at_5 value: 7.911 - type: recall_at_1 value: 19.547 - type: recall_at_10 value: 42.886 - type: recall_at_100 value: 66.64999999999999 - type: recall_at_1000 value: 87.368 - type: recall_at_3 value: 29.143 - type: recall_at_5 value: 34.544000000000004 - task: type: Retrieval dataset: type: climate-fever name: MTEB ClimateFEVER config: default split: test revision: None metrics: - type: map_at_1 value: 15.572 - type: map_at_10 value: 25.312 - type: map_at_100 value: 27.062 - type: map_at_1000 value: 27.253 - type: map_at_3 value: 21.601 - type: map_at_5 value: 23.473 - type: mrr_at_1 value: 34.984 - type: mrr_at_10 value: 46.406 - type: mrr_at_100 value: 47.179 - type: mrr_at_1000 value: 47.21 - type: mrr_at_3 value: 43.485 - type: mrr_at_5 value: 45.322 - type: ndcg_at_1 value: 34.984 - type: ndcg_at_10 value: 34.344 - type: ndcg_at_100 value: 41.015 - type: ndcg_at_1000 value: 44.366 - type: ndcg_at_3 value: 29.119 - type: ndcg_at_5 value: 30.825999999999997 - type: precision_at_1 value: 34.984 - type: precision_at_10 value: 10.358 - type: precision_at_100 value: 1.762 - type: precision_at_1000 value: 0.23900000000000002 - type: precision_at_3 value: 21.368000000000002 - type: precision_at_5 value: 15.948 - type: recall_at_1 value: 15.572 - type: recall_at_10 value: 39.367999999999995 - type: recall_at_100 value: 62.183 - type: recall_at_1000 value: 80.92200000000001 - type: recall_at_3 value: 26.131999999999998 - type: recall_at_5 value: 31.635999999999996 - task: type: Retrieval dataset: type: dbpedia-entity name: MTEB DBPedia config: default split: test revision: None metrics: - type: map_at_1 value: 8.848 - type: map_at_10 value: 19.25 - type: map_at_100 value: 27.193 - type: map_at_1000 value: 28.721999999999998 - type: map_at_3 value: 13.968 - type: map_at_5 value: 16.283 - type: mrr_at_1 value: 68.75 - type: mrr_at_10 value: 76.25 - type: mrr_at_100 value: 76.534 - type: mrr_at_1000 value: 76.53999999999999 - type: mrr_at_3 value: 74.667 - type: mrr_at_5 value: 75.86699999999999 - type: ndcg_at_1 value: 56.00000000000001 - type: ndcg_at_10 value: 41.426 - type: ndcg_at_100 value: 45.660000000000004 - type: ndcg_at_1000 value: 53.02 - type: ndcg_at_3 value: 46.581 - type: ndcg_at_5 value: 43.836999999999996 - type: precision_at_1 value: 68.75 - type: precision_at_10 value: 32.800000000000004 - type: precision_at_100 value: 10.440000000000001 - type: precision_at_1000 value: 1.9980000000000002 - type: precision_at_3 value: 49.667 - type: precision_at_5 value: 42.25 - type: recall_at_1 value: 8.848 - type: recall_at_10 value: 24.467 - type: recall_at_100 value: 51.344 - type: recall_at_1000 value: 75.235 - type: recall_at_3 value: 15.329 - type: recall_at_5 value: 18.892999999999997 - task: type: Classification dataset: type: mteb/emotion name: MTEB EmotionClassification config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 48.95 - type: f1 value: 43.44563593360779 - task: type: Retrieval dataset: type: fever name: MTEB FEVER config: default split: test revision: None metrics: - type: map_at_1 value: 78.036 - type: map_at_10 value: 85.639 - type: map_at_100 value: 85.815 - type: map_at_1000 value: 85.829 - type: map_at_3 value: 84.795 - type: map_at_5 value: 85.336 - type: mrr_at_1 value: 84.353 - type: mrr_at_10 value: 90.582 - type: mrr_at_100 value: 90.617 - type: mrr_at_1000 value: 90.617 - type: mrr_at_3 value: 90.132 - type: mrr_at_5 value: 90.447 - type: ndcg_at_1 value: 84.353 - type: ndcg_at_10 value: 89.003 - type: ndcg_at_100 value: 89.60000000000001 - type: ndcg_at_1000 value: 89.836 - type: ndcg_at_3 value: 87.81400000000001 - type: ndcg_at_5 value: 88.478 - type: precision_at_1 value: 84.353 - type: precision_at_10 value: 10.482 - type: precision_at_100 value: 1.099 - type: precision_at_1000 value: 0.11399999999999999 - type: precision_at_3 value: 33.257999999999996 - type: precision_at_5 value: 20.465 - type: recall_at_1 value: 78.036 - type: recall_at_10 value: 94.517 - type: recall_at_100 value: 96.828 - type: recall_at_1000 value: 98.261 - type: recall_at_3 value: 91.12 - type: recall_at_5 value: 92.946 - task: type: Retrieval dataset: type: fiqa name: MTEB FiQA2018 config: default split: test revision: None metrics: - type: map_at_1 value: 20.191 - type: map_at_10 value: 32.369 - type: map_at_100 value: 34.123999999999995 - type: map_at_1000 value: 34.317 - type: map_at_3 value: 28.71 - type: map_at_5 value: 30.607 - type: mrr_at_1 value: 40.894999999999996 - type: mrr_at_10 value: 48.842 - type: mrr_at_100 value: 49.599 - type: mrr_at_1000 value: 49.647000000000006 - type: mrr_at_3 value: 46.785 - type: mrr_at_5 value: 47.672 - type: ndcg_at_1 value: 40.894999999999996 - type: ndcg_at_10 value: 39.872 - type: ndcg_at_100 value: 46.126 - type: ndcg_at_1000 value: 49.476 - type: ndcg_at_3 value: 37.153000000000006 - type: ndcg_at_5 value: 37.433 - type: precision_at_1 value: 40.894999999999996 - type: precision_at_10 value: 10.818 - type: precision_at_100 value: 1.73 - type: precision_at_1000 value: 0.231 - type: precision_at_3 value: 25.051000000000002 - type: precision_at_5 value: 17.531 - type: recall_at_1 value: 20.191 - type: recall_at_10 value: 45.768 - type: recall_at_100 value: 68.82000000000001 - type: recall_at_1000 value: 89.133 - type: recall_at_3 value: 33.296 - type: recall_at_5 value: 38.022 - task: type: Retrieval dataset: type: hotpotqa name: MTEB HotpotQA config: default split: test revision: None metrics: - type: map_at_1 value: 39.257 - type: map_at_10 value: 61.467000000000006 - type: map_at_100 value: 62.364 - type: map_at_1000 value: 62.424 - type: map_at_3 value: 58.228 - type: map_at_5 value: 60.283 - type: mrr_at_1 value: 78.515 - type: mrr_at_10 value: 84.191 - type: mrr_at_100 value: 84.378 - type: mrr_at_1000 value: 84.385 - type: mrr_at_3 value: 83.284 - type: mrr_at_5 value: 83.856 - type: ndcg_at_1 value: 78.515 - type: ndcg_at_10 value: 69.78999999999999 - type: ndcg_at_100 value: 72.886 - type: ndcg_at_1000 value: 74.015 - type: ndcg_at_3 value: 65.23 - type: ndcg_at_5 value: 67.80199999999999 - type: precision_at_1 value: 78.515 - type: precision_at_10 value: 14.519000000000002 - type: precision_at_100 value: 1.694 - type: precision_at_1000 value: 0.184 - type: precision_at_3 value: 41.702 - type: precision_at_5 value: 27.046999999999997 - type: recall_at_1 value: 39.257 - type: recall_at_10 value: 72.59299999999999 - type: recall_at_100 value: 84.679 - type: recall_at_1000 value: 92.12 - type: recall_at_3 value: 62.552 - type: recall_at_5 value: 67.616 - task: type: Classification dataset: type: mteb/imdb name: MTEB ImdbClassification config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 91.5152 - type: ap value: 87.64584669595709 - type: f1 value: 91.50605576428437 - task: type: Retrieval dataset: type: msmarco name: MTEB MSMARCO config: default split: dev revision: None metrics: - type: map_at_1 value: 21.926000000000002 - type: map_at_10 value: 34.049 - type: map_at_100 value: 35.213 - type: map_at_1000 value: 35.265 - type: map_at_3 value: 30.309 - type: map_at_5 value: 32.407000000000004 - type: mrr_at_1 value: 22.55 - type: mrr_at_10 value: 34.657 - type: mrr_at_100 value: 35.760999999999996 - type: mrr_at_1000 value: 35.807 - type: mrr_at_3 value: 30.989 - type: mrr_at_5 value: 33.039 - type: ndcg_at_1 value: 22.55 - type: ndcg_at_10 value: 40.842 - type: ndcg_at_100 value: 46.436 - type: ndcg_at_1000 value: 47.721999999999994 - type: ndcg_at_3 value: 33.209 - type: ndcg_at_5 value: 36.943 - type: precision_at_1 value: 22.55 - type: precision_at_10 value: 6.447 - type: precision_at_100 value: 0.9249999999999999 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 14.136000000000001 - type: precision_at_5 value: 10.381 - type: recall_at_1 value: 21.926000000000002 - type: recall_at_10 value: 61.724999999999994 - type: recall_at_100 value: 87.604 - type: recall_at_1000 value: 97.421 - type: recall_at_3 value: 40.944 - type: recall_at_5 value: 49.915 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (en) config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 93.54765161878704 - type: f1 value: 93.3298945415573 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (en) config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 75.71591427268582 - type: f1 value: 59.32113870474471 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (en) config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 75.83053127101547 - type: f1 value: 73.60757944876475 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (en) config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 78.72562205783457 - type: f1 value: 78.63761662505502 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-p2p name: MTEB MedrxivClusteringP2P config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 33.37935633767996 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-s2s name: MTEB MedrxivClusteringS2S config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 31.55270546130387 - task: type: Reranking dataset: type: mteb/mind_small name: MTEB MindSmallReranking config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 30.462692753143834 - type: mrr value: 31.497569753511563 - task: type: Retrieval dataset: type: nfcorpus name: MTEB NFCorpus config: default split: test revision: None metrics: - type: map_at_1 value: 5.646 - type: map_at_10 value: 12.498 - type: map_at_100 value: 15.486 - type: map_at_1000 value: 16.805999999999997 - type: map_at_3 value: 9.325 - type: map_at_5 value: 10.751 - type: mrr_at_1 value: 43.034 - type: mrr_at_10 value: 52.662 - type: mrr_at_100 value: 53.189 - type: mrr_at_1000 value: 53.25 - type: mrr_at_3 value: 50.929 - type: mrr_at_5 value: 51.92 - type: ndcg_at_1 value: 41.796 - type: ndcg_at_10 value: 33.477000000000004 - type: ndcg_at_100 value: 29.996000000000002 - type: ndcg_at_1000 value: 38.864 - type: ndcg_at_3 value: 38.940000000000005 - type: ndcg_at_5 value: 36.689 - type: precision_at_1 value: 43.034 - type: precision_at_10 value: 24.799 - type: precision_at_100 value: 7.432999999999999 - type: precision_at_1000 value: 1.9929999999999999 - type: precision_at_3 value: 36.842000000000006 - type: precision_at_5 value: 32.135999999999996 - type: recall_at_1 value: 5.646 - type: recall_at_10 value: 15.963 - type: recall_at_100 value: 29.492 - type: recall_at_1000 value: 61.711000000000006 - type: recall_at_3 value: 10.585 - type: recall_at_5 value: 12.753999999999998 - task: type: Retrieval dataset: type: nq name: MTEB NQ config: default split: test revision: None metrics: - type: map_at_1 value: 27.602 - type: map_at_10 value: 41.545 - type: map_at_100 value: 42.644999999999996 - type: map_at_1000 value: 42.685 - type: map_at_3 value: 37.261 - type: map_at_5 value: 39.706 - type: mrr_at_1 value: 31.141000000000002 - type: mrr_at_10 value: 44.139 - type: mrr_at_100 value: 44.997 - type: mrr_at_1000 value: 45.025999999999996 - type: mrr_at_3 value: 40.503 - type: mrr_at_5 value: 42.64 - type: ndcg_at_1 value: 31.141000000000002 - type: ndcg_at_10 value: 48.995 - type: ndcg_at_100 value: 53.788000000000004 - type: ndcg_at_1000 value: 54.730000000000004 - type: ndcg_at_3 value: 40.844 - type: ndcg_at_5 value: 44.955 - type: precision_at_1 value: 31.141000000000002 - type: precision_at_10 value: 8.233 - type: precision_at_100 value: 1.093 - type: precision_at_1000 value: 0.11800000000000001 - type: precision_at_3 value: 18.579 - type: precision_at_5 value: 13.533999999999999 - type: recall_at_1 value: 27.602 - type: recall_at_10 value: 69.216 - type: recall_at_100 value: 90.252 - type: recall_at_1000 value: 97.27 - type: recall_at_3 value: 47.987 - type: recall_at_5 value: 57.438 - task: type: Retrieval dataset: type: quora name: MTEB QuoraRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 70.949 - type: map_at_10 value: 84.89999999999999 - type: map_at_100 value: 85.531 - type: map_at_1000 value: 85.548 - type: map_at_3 value: 82.027 - type: map_at_5 value: 83.853 - type: mrr_at_1 value: 81.69999999999999 - type: mrr_at_10 value: 87.813 - type: mrr_at_100 value: 87.917 - type: mrr_at_1000 value: 87.91799999999999 - type: mrr_at_3 value: 86.938 - type: mrr_at_5 value: 87.53999999999999 - type: ndcg_at_1 value: 81.75 - type: ndcg_at_10 value: 88.55499999999999 - type: ndcg_at_100 value: 89.765 - type: ndcg_at_1000 value: 89.871 - type: ndcg_at_3 value: 85.905 - type: ndcg_at_5 value: 87.41 - type: precision_at_1 value: 81.75 - type: precision_at_10 value: 13.403 - type: precision_at_100 value: 1.528 - type: precision_at_1000 value: 0.157 - type: precision_at_3 value: 37.597 - type: precision_at_5 value: 24.69 - type: recall_at_1 value: 70.949 - type: recall_at_10 value: 95.423 - type: recall_at_100 value: 99.509 - type: recall_at_1000 value: 99.982 - type: recall_at_3 value: 87.717 - type: recall_at_5 value: 92.032 - task: type: Clustering dataset: type: mteb/reddit-clustering name: MTEB RedditClustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 51.76962893449579 - task: type: Clustering dataset: type: mteb/reddit-clustering-p2p name: MTEB RedditClusteringP2P config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 62.32897690686379 - task: type: Retrieval dataset: type: scidocs name: MTEB SCIDOCS config: default split: test revision: None metrics: - type: map_at_1 value: 4.478 - type: map_at_10 value: 11.994 - type: map_at_100 value: 13.977 - type: map_at_1000 value: 14.295 - type: map_at_3 value: 8.408999999999999 - type: map_at_5 value: 10.024 - type: mrr_at_1 value: 22.1 - type: mrr_at_10 value: 33.526 - type: mrr_at_100 value: 34.577000000000005 - type: mrr_at_1000 value: 34.632000000000005 - type: mrr_at_3 value: 30.217 - type: mrr_at_5 value: 31.962000000000003 - type: ndcg_at_1 value: 22.1 - type: ndcg_at_10 value: 20.191 - type: ndcg_at_100 value: 27.954 - type: ndcg_at_1000 value: 33.491 - type: ndcg_at_3 value: 18.787000000000003 - type: ndcg_at_5 value: 16.378999999999998 - type: precision_at_1 value: 22.1 - type: precision_at_10 value: 10.69 - type: precision_at_100 value: 2.1919999999999997 - type: precision_at_1000 value: 0.35200000000000004 - type: precision_at_3 value: 17.732999999999997 - type: precision_at_5 value: 14.499999999999998 - type: recall_at_1 value: 4.478 - type: recall_at_10 value: 21.657 - type: recall_at_100 value: 44.54 - type: recall_at_1000 value: 71.542 - type: recall_at_3 value: 10.778 - type: recall_at_5 value: 14.687 - task: type: STS dataset: type: mteb/sickr-sts name: MTEB SICK-R config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 82.82325259156718 - type: cos_sim_spearman value: 79.2463589100662 - type: euclidean_pearson value: 80.48318380496771 - type: euclidean_spearman value: 79.34451935199979 - type: manhattan_pearson value: 80.39041824178759 - type: manhattan_spearman value: 79.23002892700211 - task: type: STS dataset: type: mteb/sts12-sts name: MTEB STS12 config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 85.74130231431258 - type: cos_sim_spearman value: 78.36856568042397 - type: euclidean_pearson value: 82.48301631890303 - type: euclidean_spearman value: 78.28376980722732 - type: manhattan_pearson value: 82.43552075450525 - type: manhattan_spearman value: 78.22702443947126 - task: type: STS dataset: type: mteb/sts13-sts name: MTEB STS13 config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 79.96138619461459 - type: cos_sim_spearman value: 81.85436343502379 - type: euclidean_pearson value: 81.82895226665367 - type: euclidean_spearman value: 82.22707349602916 - type: manhattan_pearson value: 81.66303369445873 - type: manhattan_spearman value: 82.05030197179455 - task: type: STS dataset: type: mteb/sts14-sts name: MTEB STS14 config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 80.05481244198648 - type: cos_sim_spearman value: 80.85052504637808 - type: euclidean_pearson value: 80.86728419744497 - type: euclidean_spearman value: 81.033786401512 - type: manhattan_pearson value: 80.90107531061103 - type: manhattan_spearman value: 81.11374116827795 - task: type: STS dataset: type: mteb/sts15-sts name: MTEB STS15 config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 84.615220756399 - type: cos_sim_spearman value: 86.46858500002092 - type: euclidean_pearson value: 86.08307800247586 - type: euclidean_spearman value: 86.72691443870013 - type: manhattan_pearson value: 85.96155594487269 - type: manhattan_spearman value: 86.605909505275 - task: type: STS dataset: type: mteb/sts16-sts name: MTEB STS16 config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 82.14363913634436 - type: cos_sim_spearman value: 84.48430226487102 - type: euclidean_pearson value: 83.75303424801902 - type: euclidean_spearman value: 84.56762380734538 - type: manhattan_pearson value: 83.6135447165928 - type: manhattan_spearman value: 84.39898212616731 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-en) config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 85.09909252554525 - type: cos_sim_spearman value: 85.70951402743276 - type: euclidean_pearson value: 87.1991936239908 - type: euclidean_spearman value: 86.07745840612071 - type: manhattan_pearson value: 87.25039137549952 - type: manhattan_spearman value: 85.99938746659761 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (en) config: en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 63.529332093413615 - type: cos_sim_spearman value: 65.38177340147439 - type: euclidean_pearson value: 66.35278011412136 - type: euclidean_spearman value: 65.47147267032997 - type: manhattan_pearson value: 66.71804682408693 - type: manhattan_spearman value: 65.67406521423597 - task: type: STS dataset: type: mteb/stsbenchmark-sts name: MTEB STSBenchmark config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 82.45802942885662 - type: cos_sim_spearman value: 84.8853341842566 - type: euclidean_pearson value: 84.60915021096707 - type: euclidean_spearman value: 85.11181242913666 - type: manhattan_pearson value: 84.38600521210364 - type: manhattan_spearman value: 84.89045417981723 - task: type: Reranking dataset: type: mteb/scidocs-reranking name: MTEB SciDocsRR config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 85.92793380635129 - type: mrr value: 95.85834191226348 - task: type: Retrieval dataset: type: scifact name: MTEB SciFact config: default split: test revision: None metrics: - type: map_at_1 value: 55.74400000000001 - type: map_at_10 value: 65.455 - type: map_at_100 value: 66.106 - type: map_at_1000 value: 66.129 - type: map_at_3 value: 62.719 - type: map_at_5 value: 64.441 - type: mrr_at_1 value: 58.667 - type: mrr_at_10 value: 66.776 - type: mrr_at_100 value: 67.363 - type: mrr_at_1000 value: 67.384 - type: mrr_at_3 value: 64.889 - type: mrr_at_5 value: 66.122 - type: ndcg_at_1 value: 58.667 - type: ndcg_at_10 value: 69.904 - type: ndcg_at_100 value: 72.807 - type: ndcg_at_1000 value: 73.423 - type: ndcg_at_3 value: 65.405 - type: ndcg_at_5 value: 67.86999999999999 - type: precision_at_1 value: 58.667 - type: precision_at_10 value: 9.3 - type: precision_at_100 value: 1.08 - type: precision_at_1000 value: 0.11299999999999999 - type: precision_at_3 value: 25.444 - type: precision_at_5 value: 17 - type: recall_at_1 value: 55.74400000000001 - type: recall_at_10 value: 82.122 - type: recall_at_100 value: 95.167 - type: recall_at_1000 value: 100 - type: recall_at_3 value: 70.14399999999999 - type: recall_at_5 value: 76.417 - task: type: PairClassification dataset: type: mteb/sprintduplicatequestions-pairclassification name: MTEB SprintDuplicateQuestions config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.86534653465347 - type: cos_sim_ap value: 96.54142419791388 - type: cos_sim_f1 value: 93.07535641547861 - type: cos_sim_precision value: 94.81327800829875 - type: cos_sim_recall value: 91.4 - type: dot_accuracy value: 99.86435643564356 - type: dot_ap value: 96.53682260449868 - type: dot_f1 value: 92.98515104966718 - type: dot_precision value: 95.27806925498426 - type: dot_recall value: 90.8 - type: euclidean_accuracy value: 99.86336633663366 - type: euclidean_ap value: 96.5228676185697 - type: euclidean_f1 value: 92.9735234215886 - type: euclidean_precision value: 94.70954356846472 - type: euclidean_recall value: 91.3 - type: manhattan_accuracy value: 99.85841584158416 - type: manhattan_ap value: 96.50392760934032 - type: manhattan_f1 value: 92.84642321160581 - type: manhattan_precision value: 92.8928928928929 - type: manhattan_recall value: 92.80000000000001 - type: max_accuracy value: 99.86534653465347 - type: max_ap value: 96.54142419791388 - type: max_f1 value: 93.07535641547861 - task: type: Clustering dataset: type: mteb/stackexchange-clustering name: MTEB StackExchangeClustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 61.08285408766616 - task: type: Clustering dataset: type: mteb/stackexchange-clustering-p2p name: MTEB StackExchangeClusteringP2P config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 35.640675309010604 - task: type: Reranking dataset: type: mteb/stackoverflowdupquestions-reranking name: MTEB StackOverflowDupQuestions config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 53.20333913710715 - type: mrr value: 54.088813555725324 - task: type: Summarization dataset: type: mteb/summeval name: MTEB SummEval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 30.79465221925075 - type: cos_sim_spearman value: 30.530816059163634 - type: dot_pearson value: 31.364837244718043 - type: dot_spearman value: 30.79726823684003 - task: type: Retrieval dataset: type: trec-covid name: MTEB TRECCOVID config: default split: test revision: None metrics: - type: map_at_1 value: 0.22599999999999998 - type: map_at_10 value: 1.735 - type: map_at_100 value: 8.978 - type: map_at_1000 value: 20.851 - type: map_at_3 value: 0.613 - type: map_at_5 value: 0.964 - type: mrr_at_1 value: 88 - type: mrr_at_10 value: 92.867 - type: mrr_at_100 value: 92.867 - type: mrr_at_1000 value: 92.867 - type: mrr_at_3 value: 92.667 - type: mrr_at_5 value: 92.667 - type: ndcg_at_1 value: 82 - type: ndcg_at_10 value: 73.164 - type: ndcg_at_100 value: 51.878 - type: ndcg_at_1000 value: 44.864 - type: ndcg_at_3 value: 79.184 - type: ndcg_at_5 value: 76.39 - type: precision_at_1 value: 88 - type: precision_at_10 value: 76.2 - type: precision_at_100 value: 52.459999999999994 - type: precision_at_1000 value: 19.692 - type: precision_at_3 value: 82.667 - type: precision_at_5 value: 80 - type: recall_at_1 value: 0.22599999999999998 - type: recall_at_10 value: 1.942 - type: recall_at_100 value: 12.342 - type: recall_at_1000 value: 41.42 - type: recall_at_3 value: 0.637 - type: recall_at_5 value: 1.034 - task: type: Retrieval dataset: type: webis-touche2020 name: MTEB Touche2020 config: default split: test revision: None metrics: - type: map_at_1 value: 3.567 - type: map_at_10 value: 13.116 - type: map_at_100 value: 19.39 - type: map_at_1000 value: 20.988 - type: map_at_3 value: 7.109 - type: map_at_5 value: 9.950000000000001 - type: mrr_at_1 value: 42.857 - type: mrr_at_10 value: 57.404999999999994 - type: mrr_at_100 value: 58.021 - type: mrr_at_1000 value: 58.021 - type: mrr_at_3 value: 54.762 - type: mrr_at_5 value: 56.19 - type: ndcg_at_1 value: 38.775999999999996 - type: ndcg_at_10 value: 30.359 - type: ndcg_at_100 value: 41.284 - type: ndcg_at_1000 value: 52.30200000000001 - type: ndcg_at_3 value: 36.744 - type: ndcg_at_5 value: 34.326 - type: precision_at_1 value: 42.857 - type: precision_at_10 value: 26.122 - type: precision_at_100 value: 8.082 - type: precision_at_1000 value: 1.559 - type: precision_at_3 value: 40.136 - type: precision_at_5 value: 35.510000000000005 - type: recall_at_1 value: 3.567 - type: recall_at_10 value: 19.045 - type: recall_at_100 value: 49.979 - type: recall_at_1000 value: 84.206 - type: recall_at_3 value: 8.52 - type: recall_at_5 value: 13.103000000000002 - task: type: Classification dataset: type: mteb/toxic_conversations_50k name: MTEB ToxicConversationsClassification config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 68.8394 - type: ap value: 13.454399712443099 - type: f1 value: 53.04963076364322 - task: type: Classification dataset: type: mteb/tweet_sentiment_extraction name: MTEB TweetSentimentExtractionClassification config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 60.546123372948514 - type: f1 value: 60.86952793277713 - task: type: Clustering dataset: type: mteb/twentynewsgroups-clustering name: MTEB TwentyNewsgroupsClustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 49.10042955060234 - task: type: PairClassification dataset: type: mteb/twittersemeval2015-pairclassification name: MTEB TwitterSemEval2015 config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 85.03308100375514 - type: cos_sim_ap value: 71.08284605869684 - type: cos_sim_f1 value: 65.42539436255494 - type: cos_sim_precision value: 64.14807302231237 - type: cos_sim_recall value: 66.75461741424802 - type: dot_accuracy value: 84.68736961316088 - type: dot_ap value: 69.20524036530992 - type: dot_f1 value: 63.54893953365829 - type: dot_precision value: 63.45698500394633 - type: dot_recall value: 63.641160949868066 - type: euclidean_accuracy value: 85.07480479227513 - type: euclidean_ap value: 71.14592761009864 - type: euclidean_f1 value: 65.43814432989691 - type: euclidean_precision value: 63.95465994962216 - type: euclidean_recall value: 66.99208443271768 - type: manhattan_accuracy value: 85.06288370984085 - type: manhattan_ap value: 71.07289742593868 - type: manhattan_f1 value: 65.37585421412301 - type: manhattan_precision value: 62.816147859922175 - type: manhattan_recall value: 68.15303430079156 - type: max_accuracy value: 85.07480479227513 - type: max_ap value: 71.14592761009864 - type: max_f1 value: 65.43814432989691 - task: type: PairClassification dataset: type: mteb/twitterurlcorpus-pairclassification name: MTEB TwitterURLCorpus config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 87.79058485659952 - type: cos_sim_ap value: 83.7183187008759 - type: cos_sim_f1 value: 75.86921142180798 - type: cos_sim_precision value: 73.00683371298405 - type: cos_sim_recall value: 78.96519864490298 - type: dot_accuracy value: 87.0085768618776 - type: dot_ap value: 81.87467488474279 - type: dot_f1 value: 74.04188363990559 - type: dot_precision value: 72.10507114191901 - type: dot_recall value: 76.08561749307053 - type: euclidean_accuracy value: 87.8332751193387 - type: euclidean_ap value: 83.83585648120315 - type: euclidean_f1 value: 76.02582177042369 - type: euclidean_precision value: 73.36388371759989 - type: euclidean_recall value: 78.88820449645827 - type: manhattan_accuracy value: 87.87208444910156 - type: manhattan_ap value: 83.8101950642973 - type: manhattan_f1 value: 75.90454195535027 - type: manhattan_precision value: 72.44419564761039 - type: manhattan_recall value: 79.71204188481676 - type: max_accuracy value: 87.87208444910156 - type: max_ap value: 83.83585648120315 - type: max_f1 value: 76.02582177042369 license: mit language: - en pipeline_tag: sentence-similarity --- <h1 align="center">FlagEmbedding</h1> <h4 align="center"> <p> <a href=#model-list>Model List</a> \| <a href=#usage>Usage</a> \| <a href="#evaluation">Evaluation</a> \| <a href="#train">Train</a> \| <a href="#contact">Contact</a> \| <a href="#license">License</a> <p> </h4> More details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding). [English](README.md) \| [中文](https://github.com/FlagOpen/FlagEmbedding/blob/master/README_zh.md) FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector database for LLMs. *********** 🌟Updates🌟 ********* - 08/09/2023: BGE Models are integrated into Langchain, you can use it like [this](#using-langchain); C-MTEB leaderboard is [avaliable](https://huggingface.co/spaces/mteb/leaderboard). - 08/05/2023: Release base-scale and small-scale models, best performance among the models of the same size 🤗** - 08/02/2023: Release `bge-large-`(short for BAAI General Embedding) Models, rank 1st on MTEB and C-MTEB benchmark!* - 08/01/2023: We release the [Chinese Massive Text Embedding Benchmark](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB) (C-MTEB), consisting of 31 test dataset. ## Model List `bge` is short for `BAAI general embedding`. \| Model \| Language \| Description \| query instruction for retrieval\* \| \|:-------------------------------\|:--------:\| :--------:\| :--------:\| \| [BAAI/bge-large-en](https://huggingface.co/BAAI/bge-large-en) \| English \| rank 1st in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard \| `Represent this sentence for searching relevant passages: ` \| \| [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) \| English \| rank 2nd in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard \| `Represent this sentence for searching relevant passages: ` \| \| [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) \| English \| a small-scale model but with competitive performance \| `Represent this sentence for searching relevant passages: ` \| \| [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) \| Chinese \| rank 1st in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark \| `为这个句子生成表示以用于检索相关文章：` \| \| [BAAI/bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct) \| Chinese \| This model is trained without instruction, and rank 2nd in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark \| \| \| [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) \| Chinese \| a base-scale model but has similar ability with `bge-large-zh` \| `为这个句子生成表示以用于检索相关文章：` \| \| [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) \| Chinese \| a small-scale model but with competitive performance \| `为这个句子生成表示以用于检索相关文章：` \| \: If you need to search the long* relevant passages to a short query (s2p retrieval task), you need to add the instruction to the query; in other cases, no instruction is needed, just use the original query directly. In all cases, no instruction need to be added to passages. ## Usage Here are some examples to use `bge` models with [FlagEmbedding](#using-flagembedding), [Sentence-Transformers](#using-sentence-transformers), [Langchain](#using-langchain), or [Huggingface Transformers](#using-huggingface-transformers). #### Using FlagEmbedding ``` pip install -U FlagEmbedding ``` If it doesn't work for you, you can see [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md) for more methods to install FlagEmbedding. ```python from FlagEmbedding import FlagModel sentences = ["样例数据-1", "样例数据-2"] model = FlagModel('BAAI/bge-large-zh', query_instruction_for_retrieval="为这个句子生成表示以用于检索相关文章：") embeddings_1 = model.encode(sentences) embeddings_2 = model.encode(sentences) similarity = embeddings_1 @ embeddings_2.T print(similarity) # for s2p(short query to long passage) retrieval task, please use encode_queries() which will automatically add the instruction to each query # corpus in retrieval task can still use encode() or encode_corpus(), since they don't need instruction queries = ['query_1', 'query_2'] passages = ["样例文档-1", "样例文档-2"] q_embeddings = model.encode_queries(queries) p_embeddings = model.encode(passages) scores = q_embeddings @ p_embeddings.T ``` The value of argument `query_instruction_for_retrieval` see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list). FlagModel will use all available GPUs when encoding, please set `os.environ["CUDA_VISIBLE_DEVICES"]` to choose GPU. #### Using Sentence-Transformers Using this model also is easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` ```python from sentence_transformers import SentenceTransformer sentences = ["样例数据-1", "样例数据-2"] model = SentenceTransformer('BAAI/bge-large-zh') embeddings_1 = model.encode(sentences, normalize_embeddings=True) embeddings_2 = model.encode(sentences, normalize_embeddings=True) similarity = embeddings_1 @ embeddings_2.T print(similarity) ``` For s2p(short query to long passage) retrieval task, each short query should start with an instruction (instructions see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list)). But the instruction is not needed for passages. ```python from sentence_transformers import SentenceTransformer queries = ['query_1', 'query_2'] passages = ["样例文档-1", "样例文档-2"] instruction = "为这个句子生成表示以用于检索相关文章：" model = SentenceTransformer('BAAI/bge-large-zh') q_embeddings = model.encode([instruction+q for q in queries], normalize_embeddings=True) p_embeddings = model.encode(passages, normalize_embeddings=True) scores = q_embeddings @ p_embeddings.T ``` #### Using Langchain You can use `bge` in langchain like this: ```python from langchain.embeddings import HuggingFaceBgeEmbeddings model_name = "BAAI/bge-small-en" model_kwargs = {'device': 'cuda'} encode_kwargs = {'normalize_embeddings': True} # set True to compute cosine similarity model_norm = HuggingFaceBgeEmbeddings( model_name=model_name, model_kwargs=model_kwargs, encode_kwargs=encode_kwargs ) ``` #### Using HuggingFace Transformers With transformers package, you can use the model like this: First, you pass your input through the transformer model, then you select the last hidden state of first token (i.e., [CLS]) as the sentence embedding. ```python from transformers import AutoTokenizer, AutoModel import torch # Sentences we want sentence embeddings for sentences = ["样例数据-1", "样例数据-2"] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-large-zh') model = AutoModel.from_pretrained('BAAI/bge-large-zh') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # for s2p(short query to long passage) retrieval task, add an instruction to query (not add instruction for passages) # encoded_input = tokenizer([instruction + q for q in queries], padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(encoded_input) # Perform pooling. In this case, cls pooling. sentence_embeddings = model_output[0][:, 0] # normalize embeddings sentence_embeddings = torch.nn.functional.normalize(sentence_embeddings, p=2, dim=1) print("Sentence embeddings:", sentence_embeddings) ``` ## Evaluation `baai-general-embedding` models achieve state-of-the-art performance on both MTEB and C-MTEB leaderboard! More details and evaluation tools see our [scripts](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md). - MTEB: \| Model Name \| Dimension \| Sequence Length \| Average (56) \| Retrieval (15) \|Clustering (11) \| Pair Classification (3) \| Reranking (4) \| STS (10) \| Summarization (1) \| Classification (12) \| \|:----:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\| \| [bge-large-en](https://huggingface.co/BAAI/bge-large-en) \| 1024 \| 512 \| 63.98 \| 53.9 \| 46.98 \| 85.8 \| 59.48 \| 81.56 \| 32.06 \| 76.21 \| \| [bge-base-en](https://huggingface.co/BAAI/bge-base-en) \| 768 \| 512 \| 63.36 \| 53.0 \| 46.32 \| 85.86 \| 58.7 \| 81.84 \| 29.27 \| 75.27 \| \| [gte-large](https://huggingface.co/thenlper/gte-large) \| 1024 \| 512 \| 63.13 \| 52.22 \| 46.84 \| 85.00 \| 59.13 \| 83.35 \| 31.66 \| 73.33 \| \| [gte-base](https://huggingface.co/thenlper/gte-base) \| 768 \| 512 \| 62.39 \| 51.14 \| 46.2 \| 84.57 \| 58.61 \| 82.3 \| 31.17 \| 73.01 \| \| [e5-large-v2](https://huggingface.co/intfloat/e5-large-v2) \| 1024\| 512 \| 62.25 \| 50.56 \| 44.49 \| 86.03 \| 56.61 \| 82.05 \| 30.19 \| 75.24 \| \| [bge-small-en](https://huggingface.co/BAAI/bge-small-en) \| 384 \| 512 \| 62.11 \| 51.82 \| 44.31 \| 83.78 \| 57.97 \| 80.72 \| 30.53 \| 74.37 \| \| [instructor-xl](https://huggingface.co/hkunlp/instructor-xl) \| 768 \| 512 \| 61.79 \| 49.26 \| 44.74 \| 86.62 \| 57.29 \| 83.06 \| 32.32 \| 61.79 \| \| [e5-base-v2](https://huggingface.co/intfloat/e5-base-v2) \| 768 \| 512 \| 61.5 \| 50.29 \| 43.80 \| 85.73 \| 55.91 \| 81.05 \| 30.28 \| 73.84 \| \| [gte-small](https://huggingface.co/thenlper/gte-small) \| 384 \| 512 \| 61.36 \| 49.46 \| 44.89 \| 83.54 \| 57.7 \| 82.07 \| 30.42 \| 72.31 \| \| [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) \| 1536 \| 8192 \| 60.99 \| 49.25 \| 45.9 \| 84.89 \| 56.32 \| 80.97 \| 30.8 \| 70.93 \| \| [e5-small-v2](https://huggingface.co/intfloat/e5-base-v2) \| 384 \| 512 \| 59.93 \| 49.04 \| 39.92 \| 84.67 \| 54.32 \| 80.39 \| 31.16 \| 72.94 \| \| [sentence-t5-xxl](https://huggingface.co/sentence-transformers/sentence-t5-xxl) \| 768 \| 512 \| 59.51 \| 42.24 \| 43.72 \| 85.06 \| 56.42 \| 82.63 \| 30.08 \| 73.42 \| \| [all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) \| 768 \| 514 \| 57.78 \| 43.81 \| 43.69 \| 83.04 \| 59.36 \| 80.28 \| 27.49 \| 65.07 \| \| [sgpt-bloom-7b1-msmarco](https://huggingface.co/bigscience/sgpt-bloom-7b1-msmarco) \| 4096 \| 2048 \| 57.59 \| 48.22 \| 38.93 \| 81.9 \| 55.65 \| 77.74 \| 33.6 \| 66.19 \| \| [all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) \| 384 \| 512 \| 56.53 \| 42.69 \| 41.81 \| 82.41 \| 58.44 \| 79.8 \| 27.9 \| 63.21 \| \| [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) \| 384 \| 512 \| 56.26 \| 41.95 \| 42.35 \| 82.37 \| 58.04 \| 78.9 \| 30.81 \| 63.05 \| \| [contriever-base-msmarco](https://huggingface.co/nthakur/contriever-base-msmarco) \| 768 \| 512 \| 56.00 \| 41.88 \| 41.1 \| 82.54 \| 53.14 \| 76.51 \| 30.36 \| 66.68 \| \| [sentence-t5-base](https://huggingface.co/sentence-transformers/sentence-t5-base) \| 768 \| 512 \| 55.27 \| 33.63 \| 40.21 \| 85.18 \| 53.09 \| 81.14 \| 31.39 \| 69.81 \| - C-MTEB: We create a benchmark C-MTEB for chinese text embedding which consists of 31 datasets from 6 tasks. Please refer to [C_MTEB](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md) for a detailed introduction. \| Model \| Embedding dimension \| Avg \| Retrieval \| STS \| PairClassification \| Classification \| Reranking \| Clustering \| \|:-------------------------------\|:--------:\|:--------:\|:--------:\|:--------:\|:--------:\|:--------:\|:--------:\|:--------:\| \| [bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) \| 1024 \| 64.20 \| 71.53 \| 53.23 \| 78.94 \| 72.26 \| 65.11 \| 48.39 \| \| [bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct) \| 1024 \| 63.53 \| 70.55 \| 50.98 \| 76.77 \| 72.49 \| 64.91 \| 50.01 \| \| [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) \| 768 \| 62.96 \| 69.53 \| 52.05 \| 77.5 \| 70.98 \| 64.91 \| 47.63 \| \| [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) \| 512 \| 58.27 \| 63.07 \| 46.87 \| 70.35 \| 67.78 \| 61.48 \| 45.09 \| \| [m3e-base](https://huggingface.co/moka-ai/m3e-base) \| 768 \| 57.10 \|56.91 \| 48.15 \| 63.99 \| 70.28 \| 59.34 \| 47.68 \| \| [m3e-large](https://huggingface.co/moka-ai/m3e-large) \| 1024 \| 57.05 \|54.75 \| 48.64 \| 64.3 \| 71.22 \| 59.66 \| 48.88 \| \| [text-embedding-ada-002(OpenAI)](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings) \| 1536 \| 53.02 \| 52.0 \| 40.61 \| 69.56 \| 67.38 \| 54.28 \| 45.68 \| \| [luotuo](https://huggingface.co/silk-road/luotuo-bert-medium) \| 1024 \| 49.37 \| 44.4 \| 39.41 \| 66.62 \| 65.29 \| 49.25 \| 44.39 \| \| [text2vec](https://huggingface.co/shibing624/text2vec-base-chinese) \| 768 \| 47.63 \| 38.79 \| 41.71 \| 67.41 \| 65.18 \| 49.45 \| 37.66 \| \| [text2vec-large](https://huggingface.co/GanymedeNil/text2vec-large-chinese) \| 1024 \| 47.36 \| 41.94 \| 41.98 \| 70.86 \| 63.42 \| 49.16 \| 30.02 \| ## Train This section will introduce the way we used to train the general embedding. The training scripts are in [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md), and we provide some examples to do [pre-train](https://github.com/FlagOpen/FlagEmbedding/blob/master/examples/pretrain/README.md) and [fine-tune](https://github.com/FlagOpen/FlagEmbedding/blob/master/examples/finetune/README.md). 1. RetroMAE Pre-train We pre-train the model following the method [retromae](https://github.com/staoxiao/RetroMAE), which shows promising improvement in retrieval task ([paper](https://aclanthology.org/2022.emnlp-main.35.pdf)). The pre-training was conducted on 24 A100(40G) GPUs with a batch size of 720. In retromae, the mask ratio of encoder and decoder are 0.3, 0.5 respectively. We used the AdamW optimizer and the learning rate is 2e-5. Pre-training data: - English: - [Pile](https://pile.eleuther.ai/) - [wikipedia](https://huggingface.co/datasets/wikipedia) - [msmarco](https://huggingface.co/datasets/Tevatron/msmarco-passage-corpus) - Chinese: - [wudao](https://github.com/BAAI-WuDao/Data) 2. Finetune We fine-tune the model using a contrastive objective. The format of input data is a triple`(query, positive, negative)`. Besides the negative in the triple, we also adopt in-batch negatives strategy. We employ the cross-device negatives sharing method to share negatives among different GPUs, which can dramatically increase the number of negatives. We trained our model on 48 A100(40G) GPUs with a large batch size of 32,768 (so there are 65,535 negatives for each query in a batch). We used the AdamW optimizer and the learning rate is 1e-5. The temperature for contrastive loss is 0.01. Besides, we add instruction to the query for s2p(short query to long passage) retrieval task in the training (add nothing to passages). For English, the instruction is `Represent this sentence for searching relevant passages: `; For Chinese, the instruction is `为这个句子生成表示以用于检索相关文章：`. In the evaluation, the instruction should be added for queries in retrieval task, not be added for other tasks. Noted that the instruction is not needed for passages. The finetune script is accessible in this repository: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md). You can easily finetune your model with it. Training data: - For English, we collect 230M text pairs from [wikipedia](https://huggingface.co/datasets/wikipedia), [cc-net](https://github.com/facebookresearch/cc_net), and so on. - For chinese, we collect 120M text pairs from [wudao](https://github.com/BAAI-WuDao/Data), [simclue](https://github.com/CLUEbenchmark/SimCLUE) and so on. The data collection is to be released in the future.** We will continually update the embedding models and training codes, hoping to promote the development of the embedding model community. ## License FlagEmbedding is licensed under [MIT License](https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE). The released models can be used for commercial purposes free of charge.
Helsinki-NLP/opus-mt-tvl-fr	Helsinki-NLP	"2023-08-16T12:07:47Z"	120	0	transformers	[ "transformers", "pytorch", "tf", "marian", "text2text-generation", "translation", "tvl", "fr", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	translation	"2022-03-02T23:29:04Z"	--- tags: - translation license: apache-2.0 --- ### opus-mt-tvl-fr * source languages: tvl * target languages: fr * OPUS readme: [tvl-fr](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/tvl-fr/README.md) * dataset: opus * model: transformer-align * pre-processing: normalization + SentencePiece * download original weights: [opus-2020-01-16.zip](https://object.pouta.csc.fi/OPUS-MT-models/tvl-fr/opus-2020-01-16.zip) * test set translations: [opus-2020-01-16.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/tvl-fr/opus-2020-01-16.test.txt) * test set scores: [opus-2020-01-16.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/tvl-fr/opus-2020-01-16.eval.txt) ## Benchmarks \| testset \| BLEU \| chr-F \| \|-----------------------\|-------\|-------\| \| JW300.tvl.fr \| 24.0 \| 0.410 \|
phpthinh/pho1e-5	phpthinh	"2024-08-20T14:36:11Z"	188	0	transformers	[ "transformers", "safetensors", "vit", "image-feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	image-feature-extraction	"2024-08-20T14:27:26Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
PrunaAI/google-codegemma-7b-HQQ-4bit-smashed	PrunaAI	"2024-08-02T15:57:16Z"	1	0	transformers	[ "transformers", "gemma", "text-generation", "pruna-ai", "base_model:google/codegemma-7b", "base_model:finetune:google/codegemma-7b", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	"2024-04-29T16:06:46Z"	--- thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg" base_model: google/codegemma-7b metrics: - memory_disk - memory_inference - inference_latency - inference_throughput - inference_CO2_emissions - inference_energy_consumption tags: - pruna-ai --- <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <a href="https://www.pruna.ai/" target="_blank" rel="noopener noreferrer"> <img src="https://i.imgur.com/eDAlcgk.png" alt="PrunaAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </a> </div> <!-- header end --> [![Twitter](https://img.shields.io/twitter/follow/PrunaAI?style=social)](https://twitter.com/PrunaAI) [![GitHub](https://img.shields.io/github/followers/PrunaAI?label=Follow%20%40PrunaAI&style=social)](https://github.com/PrunaAI) [![LinkedIn](https://img.shields.io/badge/LinkedIn-Connect-blue)](https://www.linkedin.com/company/93832878/admin/feed/posts/?feedType=following) [![Discord](https://img.shields.io/badge/Discord-Join%20Us-blue?style=social&logo=discord)](https://discord.gg/rskEr4BZJx) # Simply make AI models cheaper, smaller, faster, and greener! - Give a thumbs up if you like this model! - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact). - Request access to easily compress your own AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai). - Read the documentations to know more [here](https://pruna-ai-pruna.readthedocs-hosted.com/en/latest/) - Join Pruna AI community on Discord [here](https://discord.gg/rskEr4BZJx) to share feedback/suggestions or get help. ## Results ![image info](./plots.png) Frequently Asked Questions - *How does the compression work?* The model is compressed with hqq. - *How does the model quality change?* The quality of the model output might vary compared to the base model. - *How is the model efficiency evaluated?* These results were obtained on HARDWARE_NAME with configuration described in `model/smash_config.json` and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you. - *What is the model format?* We use safetensors. - *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data. - *What is the naming convention for Pruna Huggingface models?* We take the original model name and append "turbo", "tiny", or "green" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model. - *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai). - *What are "first" metrics?* Results mentioning "first" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads. - *What are "Sync" and "Async" metrics?* "Sync" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. "Async" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases. ## Setup You can run the smashed model with these steps: 0. Check requirements from the original repo google/codegemma-7b installed. In particular, check python, cuda, and transformers versions. 1. Make sure that you have installed quantization related packages. ```bash pip install hqq ``` 2. Load & run the model. ```python from transformers import AutoModelForCausalLM, AutoTokenizer from hqq.engine.hf import HQQModelForCausalLM from hqq.models.hf.base import AutoHQQHFModel try: model = HQQModelForCausalLM.from_quantized("PrunaAI/google-codegemma-7b-HQQ-4bit-smashed", device_map='auto') except: model = AutoHQQHFModel.from_quantized("PrunaAI/google-codegemma-7b-HQQ-4bit-smashed") tokenizer = AutoTokenizer.from_pretrained("google/codegemma-7b") input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"] outputs = model.generate(input_ids, max_new_tokens=216) tokenizer.decode(outputs[0]) ``` ## Configurations The configuration info are in `smash_config.json`. ## Credits & License The license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-7b before using this model which provided the base model. The license of the `pruna-engine` is [here](https://pypi.org/project/pruna-engine/) on Pypi. ## Want to compress other models? - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact). - Request access to easily compress your own AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
HanaHelaly/Llama_Model	HanaHelaly	"2024-06-11T20:05:47Z"	3	1	transformers	[ "transformers", "safetensors", "llama", "license:apache-2.0", "text-generation-inference", "endpoints_compatible", "region:us" ]	null	"2024-06-11T20:03:26Z"	--- title: "ASK ME!" emoji: "🚀" colorFrom: "blue" colorTo: "green" sdk: streamlit sdk_version: "1.10.0" app_file: app.py pinned: false license: apache-2.0 ---
Elkelouizajo/bert_mnli_1000	Elkelouizajo	"2024-07-16T12:11:06Z"	108	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:google-bert/bert-large-cased", "base_model:finetune:google-bert/bert-large-cased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	"2024-07-16T11:19:09Z"	--- license: apache-2.0 base_model: google-bert/bert-large-cased tags: - generated_from_trainer model-index: - name: results_1K results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # results_1K This model is a fine-tuned version of [google-bert/bert-large-cased](https://huggingface.co/google-bert/bert-large-cased) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5.0 ### Training results ### Framework versions - Transformers 4.39.0.dev0 - Pytorch 2.1.2.post103 - Datasets 2.19.1.dev0 - Tokenizers 0.15.2
mabobe-biyong/m2m100_418M-fr-ful-rel-ft	mabobe-biyong	"2024-01-24T21:31:41Z"	118	0	transformers	[ "transformers", "pytorch", "m2m_100", "text2text-generation", "Cameroonian culture", "fr", "license:afl-3.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	"2024-01-21T12:34:27Z"	--- license: afl-3.0 language: - fr library_name: transformers tags: - Cameroonian culture ---
nettur/my-movies-xzg	nettur	"2023-11-05T17:30:50Z"	0	0	null	[ "NxtWave-GenAI-Webinar", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "region:us" ]	text-to-image	"2023-11-05T17:30:00Z"	--- license: creativeml-openrail-m tags: - NxtWave-GenAI-Webinar - text-to-image - stable-diffusion --- ### My-Movies-XZG Dreambooth model trained by nettur following the "Build your own Gen AI model" session by NxtWave. Project Submission Code: MITS-34 Sample pictures of this concept: ![0](https://huggingface.co/nettur/my-movies-xzg/resolve/main/sample_images/xzg.png)
RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf	RichardErkhov	"2024-09-16T11:32:47Z"	80	0	null	[ "gguf", "arxiv:2405.04324", "endpoints_compatible", "region:us" ]	null	"2024-09-15T21:56:13Z"	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) granite-34b-code-base-8k - GGUF - Model creator: https://huggingface.co/ibm-granite/ - Original model: https://huggingface.co/ibm-granite/granite-34b-code-base-8k/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [granite-34b-code-base-8k.Q2_K.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q2_K.gguf) \| Q2_K \| 12.21GB \| \| [granite-34b-code-base-8k.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.IQ3_XS.gguf) \| IQ3_XS \| 13.36GB \| \| [granite-34b-code-base-8k.IQ3_S.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.IQ3_S.gguf) \| IQ3_S \| 13.79GB \| \| [granite-34b-code-base-8k.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q3_K_S.gguf) \| Q3_K_S \| 13.79GB \| \| [granite-34b-code-base-8k.IQ3_M.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.IQ3_M.gguf) \| IQ3_M \| 14.84GB \| \| [granite-34b-code-base-8k.Q3_K.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q3_K.gguf) \| Q3_K \| 16.36GB \| \| [granite-34b-code-base-8k.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q3_K_M.gguf) \| Q3_K_M \| 16.36GB \| \| [granite-34b-code-base-8k.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q3_K_L.gguf) \| Q3_K_L \| 18.21GB \| \| [granite-34b-code-base-8k.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.IQ4_XS.gguf) \| IQ4_XS \| 17.19GB \| \| [granite-34b-code-base-8k.Q4_0.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q4_0.gguf) \| Q4_0 \| 17.92GB \| \| [granite-34b-code-base-8k.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.IQ4_NL.gguf) \| IQ4_NL \| 18.11GB \| \| [granite-34b-code-base-8k.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q4_K_S.gguf) \| Q4_K_S \| 18.11GB \| \| [granite-34b-code-base-8k.Q4_K.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q4_K.gguf) \| Q4_K \| 19.92GB \| \| [granite-34b-code-base-8k.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q4_K_M.gguf) \| Q4_K_M \| 19.92GB \| \| [granite-34b-code-base-8k.Q4_1.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q4_1.gguf) \| Q4_1 \| 19.86GB \| \| [granite-34b-code-base-8k.Q5_0.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q5_0.gguf) \| Q5_0 \| 21.8GB \| \| [granite-34b-code-base-8k.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q5_K_S.gguf) \| Q5_K_S \| 21.8GB \| \| [granite-34b-code-base-8k.Q5_K.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q5_K.gguf) \| Q5_K \| 23.05GB \| \| [granite-34b-code-base-8k.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q5_K_M.gguf) \| Q5_K_M \| 23.05GB \| \| [granite-34b-code-base-8k.Q5_1.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q5_1.gguf) \| Q5_1 \| 23.74GB \| \| [granite-34b-code-base-8k.Q6_K.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q6_K.gguf) \| Q6_K \| 25.93GB \| \| [granite-34b-code-base-8k.Q8_0.gguf](https://huggingface.co/RichardErkhov/ibm-granite_-_granite-34b-code-base-8k-gguf/blob/main/granite-34b-code-base-8k.Q8_0.gguf) \| Q8_0 \| 33.52GB \| Original model description: --- pipeline_tag: text-generation inference: true license: apache-2.0 datasets: - codeparrot/github-code-clean - bigcode/starcoderdata # - Stackexchange # - CommonCrawl - open-web-math/open-web-math - math-ai/StackMathQA # - Arxiv # - Wikipedia # - conceptofmind/FLAN_2022 # Original link is broken, we used IBM's filtered version \| Phase 2 metrics: - code_eval library_name: transformers tags: - code - granite model-index: - name: granite-34b-code-base-8k results: - task: type: text-generation dataset: type: mbpp name: MBPP metrics: - name: pass@1 type: pass@1 value: 47.2 veriefied: false - task: type: text-generation dataset: type: evalplus/mbppplus name: MBPP+ metrics: - name: pass@1 type: pass@1 value: 53.1 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalSynthesis(Python) metrics: - name: pass@1 type: pass@1 value: 48.2 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalSynthesis(JavaScript) metrics: - name: pass@1 type: pass@1 value: 54.9 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalSynthesis(Java) metrics: - name: pass@1 type: pass@1 value: 61.6 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalSynthesis(Go) metrics: - name: pass@1 type: pass@1 value: 40.2 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalSynthesis(C++) metrics: - name: pass@1 type: pass@1 value: 50.0 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalSynthesis(Rust) metrics: - name: pass@1 type: pass@1 value: 39.6 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalExplain(Python) metrics: - name: pass@1 type: pass@1 value: 42.7 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalExplain(JavaScript) metrics: - name: pass@1 type: pass@1 value: 26.2 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalExplain(Java) metrics: - name: pass@1 type: pass@1 value: 47.0 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalExplain(Go) metrics: - name: pass@1 type: pass@1 value: 26.8 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalExplain(C++) metrics: - name: pass@1 type: pass@1 value: 36.6 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalExplain(Rust) metrics: - name: pass@1 type: pass@1 value: 25.0 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalFix(Python) metrics: - name: pass@1 type: pass@1 value: 20.1 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalFix(JavaScript) metrics: - name: pass@1 type: pass@1 value: 30.5 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalFix(Java) metrics: - name: pass@1 type: pass@1 value: 40.9 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalFix(Go) metrics: - name: pass@1 type: pass@1 value: 34.1 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalFix(C++) metrics: - name: pass@1 type: pass@1 value: 39.0 veriefied: false - task: type: text-generation dataset: type: bigcode/humanevalpack name: HumanEvalFix(Rust) metrics: - name: pass@1 type: pass@1 value: 12.2 veriefied: false --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png) # Granite-34B-Code-Base-8K ## Model Summary Granite-34B-Code-Base-8K is a decoder-only code model designed for code generative tasks (e.g., code generation, code explanation, code fixing, etc.). It is trained using depth upscaling from Granite-20B-Code-Base model with a two-phase training strategy. In phase 1, our model is trained on 3 trillion tokens (1.4 trillion tokens after depth up scaling). In phase 2, our model is trained on 500 billion tokens with a carefully designed mixture of high-quality data from code and natural language domains to improve the models’ ability to reason and follow instructions. - Developers: IBM Research - GitHub Repository: [ibm-granite/granite-code-models](https://github.com/ibm-granite/granite-code-models) - Paper: [Granite Code Models: A Family of Open Foundation Models for Code Intelligence](https://arxiv.org/abs/2405.04324) - Release Date: May 6th, 2024 - License: [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0). ## Usage ### Intended use Prominent enterprise use cases of LLMs in software engineering productivity include code generation, code explanation, code fixing, generating unit tests, generating documentation, addressing technical debt issues, vulnerability detection, code translation, and more. All Granite Code Base models, including the 34B parameter model, are able to handle these tasks as they were trained on a large amount of code data from 116 programming languages. ### Generation This is a simple example of how to use Granite-34B-Code-Base-8K model. ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer device = "cuda" # or "cpu" model_path = "ibm-granite/granite-34b-code-base-8k" tokenizer = AutoTokenizer.from_pretrained(model_path) # drop device_map if running on CPU model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device) model.eval() # change input text as desired input_text = "def generate():" # tokenize the text input_tokens = tokenizer(input_text, return_tensors="pt") # transfer tokenized inputs to the device for i in input_tokens: input_tokens[i] = input_tokens[i].to(device) # generate output tokens output = model.generate(input_tokens) # decode output tokens into text output = tokenizer.batch_decode(output) # loop over the batch to print, in this example the batch size is 1 for i in output: print(i) ``` ## Training Data - Data Collection and Filtering: Pretraining code data is sourced from a combination of publicly available datasets (e.g., [GitHub Code Clean](https://huggingface.co/datasets/codeparrot/github-code-clean), [Starcoder data](https://huggingface.co/datasets/bigcode/starcoderdata)), and additional public code repositories and issues from GitHub. We filter raw data to retain a list of 116 programming languages. After language filtering, we also filter out low-quality code. - Exact and Fuzzy Deduplication: We adopt an aggressive deduplication strategy that includes both exact and fuzzy deduplication to remove documents having (near) identical code content. - HAP, PII, Malware Filtering: We apply a HAP content filter that reduces models' likelihood of generating hateful, abusive, or profane language. We also make sure to redact Personally Identifiable Information (PII) by replacing PII content (e.g., names, email addresses, keys, passwords) with corresponding tokens (e.g., ⟨NAME⟩, ⟨EMAIL⟩, ⟨KEY⟩, ⟨PASSWORD⟩). Moreover, we scan all datasets using [ClamAV](https://www.clamav.net/) to identify and remove instances of malware in the source code. - Natural Language Datasets: In addition to collecting code data for model training, we curate several publicly available high-quality natural language datasets to improve models' proficiency in language understanding and mathematical reasoning. Unlike the code data, we do not deduplicate these datasets. ## Infrastructure We train the Granite Code models using two of IBM's super computing clusters, namely Vela and Blue Vela, both outfitted with NVIDIA A100 and H100 GPUs respectively. These clusters provide a scalable and efficient infrastructure for training our models over thousands of GPUs. ## Ethical Considerations and Limitations The use of Large Language Models involves risks and ethical considerations people must be aware of. Regarding code generation, caution is urged against complete reliance on specific code models for crucial decisions or impactful information as the generated code is not guaranteed to work as intended. Granite-34B-Code-Base-8K model is not the exception in this regard. Even though this model is suited for multiple code-related tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying source code verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use Granite-34B-Code-Base-8K** model with ethical intentions and in a responsible way.
Miguelfgf/miguelfgf-thumbnails	Miguelfgf	"2025-01-08T19:23:19Z"	14	0	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	"2025-01-08T19:01:45Z"	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: TOK --- # Miguelfgf Thumbnails <Gallery /> Trained on Replicate using: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `TOK` to trigger the image generation. ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('Miguelfgf/miguelfgf-thumbnails', weight_name='lora.safetensors') image = pipeline('your prompt').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
Bijibapakmu/larissalora	Bijibapakmu	"2023-05-13T09:50:32Z"	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	"2023-05-13T09:46:45Z"	--- license: creativeml-openrail-m ---
itlwas/DeepSeek-V2-Lite-Q4_K_M-GGUF	itlwas	"2024-12-28T23:13:16Z"	35	0	null	[ "gguf", "llama-cpp", "gguf-my-repo", "base_model:deepseek-ai/DeepSeek-V2-Lite", "base_model:quantized:deepseek-ai/DeepSeek-V2-Lite", "license:other", "endpoints_compatible", "region:us", "conversational" ]	null	"2024-12-28T23:12:33Z"	--- license: other license_name: deepseek license_link: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL tags: - llama-cpp - gguf-my-repo base_model: deepseek-ai/DeepSeek-V2-Lite --- # AIronMind/DeepSeek-V2-Lite-Q4_K_M-GGUF This model was converted to GGUF format from [`deepseek-ai/DeepSeek-V2-Lite`](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo AIronMind/DeepSeek-V2-Lite-Q4_K_M-GGUF --hf-file deepseek-v2-lite-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo AIronMind/DeepSeek-V2-Lite-Q4_K_M-GGUF --hf-file deepseek-v2-lite-q4_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo AIronMind/DeepSeek-V2-Lite-Q4_K_M-GGUF --hf-file deepseek-v2-lite-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo AIronMind/DeepSeek-V2-Lite-Q4_K_M-GGUF --hf-file deepseek-v2-lite-q4_k_m.gguf -c 2048 ```
theodullin/conditional-detr-resnet-50_finetuned_blood_cell_10epochs	theodullin	"2023-10-16T14:40:34Z"	27	0	transformers	[ "transformers", "pytorch", "conditional_detr", "object-detection", "generated_from_trainer", "dataset:blood-cell-object-detection", "base_model:microsoft/conditional-detr-resnet-50", "base_model:finetune:microsoft/conditional-detr-resnet-50", "license:apache-2.0", "endpoints_compatible", "region:us" ]	object-detection	"2023-10-16T14:31:19Z"	--- license: apache-2.0 base_model: microsoft/conditional-detr-resnet-50 tags: - generated_from_trainer datasets: - blood-cell-object-detection model-index: - name: conditional-detr-resnet-50_finetuned_blood_cell_10epochs results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # conditional-detr-resnet-50_finetuned_blood_cell_10epochs This model is a fine-tuned version of [microsoft/conditional-detr-resnet-50](https://huggingface.co/microsoft/conditional-detr-resnet-50) on the blood-cell-object-detection dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results ### Framework versions - Transformers 4.34.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.1
RichardErkhov/ContextualAI_-_archangel_csft_pythia1-4b-awq	RichardErkhov	"2024-12-30T10:42:48Z"	5	0	null	[ "safetensors", "gpt_neox", "4-bit", "awq", "region:us" ]	null	"2024-12-30T10:42:14Z"	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) archangel_csft_pythia1-4b - AWQ - Model creator: https://huggingface.co/ContextualAI/ - Original model: https://huggingface.co/ContextualAI/archangel_csft_pythia1-4b/ Original model description: --- license: apache-2.0 datasets: - stanfordnlp/SHP - Anthropic/hh-rlhf - OpenAssistant/oasst1 language: - en metrics: - accuracy tags: - human feedback - rlhf - preferences - alignment - HALO - halos - dpo - rl --- ![halos](https://gist.github.com/assets/29318529/fe2d8391-dbd1-4b7e-9dc4-7cb97e55bc06) This repo contains the model checkpoints for: - model family <b>pythia1-4b</b> - optimized with the loss <b>CSFT</b> - aligned using the SHP, Anthropic HH and Open Assistant datasets. To prompt Archangel models, ensure that the format is consistent with that of TuluV2. For example, a prompt should be formatted as follows, where `<\|user\|>` corresponds to the human's role and `<\|assistant\|>` corresponds to the LLM's role. The human should speak first: ``` <\|user\|> Hi! I'm looking for a cake recipe. <\|assistant\|> What kind of cake? <\|user\|> Chocolate cake. <\|assistant\|> ``` Note that a beginning-of-sequence (BOS) token is automatically added by all Archangel models during tokenization and does not have to be added by you. No end-of-sequence (EOS) token is added to the prompt. For models trained with our conditional SFT model, the tokenizers have additional tokens `<\|good\|>` and `<\|bad\|>` included in the embeddings. To generate with these control tokens in the context, postpend either to the prompt. Please refer to our [code repository](https://github.com/ContextualAI/HALOs) or [blog](https://contextual.ai/better-cheaper-faster-llm-alignment-with-kto/) which contains intructions for training your own HALOs and links to our model cards. If you find this repo or the technical paper useful in your research, please feel free to cite [our work](https://github.com/ContextualAI/HALOs/blob/main/assets/report.pdf): ``` @techreport{ethayarajh2023halos, author = {Ethayarajh, Kawin and Xu, Winnie, and Jurafsky, Dan and Kiela, Douwe}, title = {Human-Centered Loss Functions (HALOs)}, institution = {Contextual AI}, note = {https://github.com/ContextualAI/HALOs/blob/main/assets/report.pdf}, year = {2023}, } ```
t-tsuma/core-outline-gemma	t-tsuma	"2024-03-06T01:20:38Z"	5	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-03-05T17:27:03Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Tnuw/xlm-roberta-base-finetuned-panx-de	Tnuw	"2024-02-28T10:57:56Z"	129	0	transformers	[ "transformers", "pytorch", "tensorboard", "xlm-roberta", "token-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	"2024-02-28T10:47:54Z"	--- license: mit tags: - generated_from_trainer metrics: - f1 model-index: - name: xlm-roberta-base-finetuned-panx-de results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # xlm-roberta-base-finetuned-panx-de This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1350 - F1: 0.8626 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 24 - eval_batch_size: 24 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| 0.2585 \| 1.0 \| 525 \| 0.1580 \| 0.8255 \| \| 0.1282 \| 2.0 \| 1050 \| 0.1381 \| 0.8447 \| \| 0.0805 \| 3.0 \| 1575 \| 0.1350 \| 0.8626 \| ### Framework versions - Transformers 4.30.0 - Pytorch 2.1.0+cu121 - Datasets 2.17.1 - Tokenizers 0.13.3
datlaaaaaaa/318f3be8-2ff7-4793-a144-bd0a58d9ce7b	datlaaaaaaa	"2025-01-26T14:40:00Z"	8	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:Vikhrmodels/Vikhr-7B-instruct_0.4", "base_model:adapter:Vikhrmodels/Vikhr-7B-instruct_0.4", "8-bit", "bitsandbytes", "region:us" ]	null	"2025-01-26T14:01:09Z"	--- library_name: peft base_model: Vikhrmodels/Vikhr-7B-instruct_0.4 tags: - axolotl - generated_from_trainer model-index: - name: 318f3be8-2ff7-4793-a144-bd0a58d9ce7b results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: Vikhrmodels/Vikhr-7B-instruct_0.4 bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - d0da19b659235425_train_data.json ds_type: json format: custom path: /workspace/input_data/d0da19b659235425_train_data.json type: field_input: text field_instruction: question field_output: attempt format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: true gradient_clipping: 1.0 group_by_length: false hub_model_id: datlaaaaaaa/318f3be8-2ff7-4793-a144-bd0a58d9ce7b hub_repo: null hub_strategy: end hub_token: null learning_rate: 5.0e-05 load_in_4bit: true load_in_8bit: true local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 200 micro_batch_size: 2 mlflow_experiment_name: /tmp/d0da19b659235425_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: a8fc1de9-3b72-443e-98a0-68609717c93d wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: a8fc1de9-3b72-443e-98a0-68609717c93d warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # 318f3be8-2ff7-4793-a144-bd0a58d9ce7b This model is a fine-tuned version of [Vikhrmodels/Vikhr-7B-instruct_0.4](https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_0.4) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.7586 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 5 - training_steps: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.8113 \| 0.3498 \| 200 \| 0.7586 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
Akshint47/grpo-lora-model	Akshint47	"2025-03-17T12:28:10Z"	0	0	null	[ "license:apache-2.0", "region:us" ]	null	"2025-03-17T12:28:10Z"	--- license: apache-2.0 ---
chatpig/t5-v1_1-xl-encoder-gguf	chatpig	"2025-02-24T09:00:30Z"	486	1	null	[ "gguf", "t5", "gguf-node", "base_model:google/t5-v1_1-xl", "base_model:quantized:google/t5-v1_1-xl", "license:apache-2.0", "region:us" ]	null	"2025-02-12T07:43:07Z"	--- license: apache-2.0 base_model: - google/t5-v1_1-xl tags: - t5 - gguf-node --- # t5-v1_1-xl-encoder-gguf - t5xl text encoder for image/image-text-to-image generation - compatible with both [comfyui-gguf](https://github.com/city96/ComfyUI-GGUF) and [gguf-node](https://github.com/calcuis/gguf) - example model supported: [aura](https://huggingface.co/calcuis/aura)
nihaal-mansoor/Llama3-mental-health-llm-finetuned-v3-high-accuracy	nihaal-mansoor	"2024-06-07T14:27:43Z"	9	1	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	"2024-06-07T13:31:21Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
toiquangle1234/comment_classification	toiquangle1234	"2024-05-23T11:42:58Z"	116	1	transformers	[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:vinai/phobert-base-v2", "base_model:finetune:vinai/phobert-base-v2", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	"2024-05-17T15:46:28Z"	--- base_model: vinai/phobert-base-v2 tags: - generated_from_trainer metrics: - accuracy model-index: - name: comment_classification results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # comment_classification This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4387 - Accuracy: 0.9228 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\| \| 0.2831 \| 1.0 \| 18435 \| 0.2946 \| 0.9082 \| \| 0.2315 \| 2.0 \| 36870 \| 0.3132 \| 0.9182 \| \| 0.1888 \| 3.0 \| 55305 \| 0.3513 \| 0.9235 \| \| 0.1483 \| 4.0 \| 73740 \| 0.3971 \| 0.9209 \| \| 0.0997 \| 5.0 \| 92175 \| 0.4387 \| 0.9228 \| ### Framework versions - Transformers 4.41.1 - Pytorch 2.3.0+cu121 - Tokenizers 0.19.1
gmongaras/Wizard_7B_Reddit_Political_2019	gmongaras	"2023-09-11T18:39:08Z"	6	0	transformers	[ "transformers", "pytorch", "llama", "text-generation", "license:openrail", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2023-09-10T15:07:03Z"	--- license: openrail --- Model from: https://huggingface.co/TheBloke/wizardLM-7B-HF/tree/main Trained on: https://huggingface.co/datasets/gmongaras/reddit_political_2019 For about 6000 steps with a batch sise of 8, 2 accumulation steps, and using LoRA adapters on all layers.
google/bert_uncased_L-10_H-256_A-4	google	"2021-05-19T17:23:44Z"	924	0	transformers	[ "transformers", "pytorch", "jax", "bert", "arxiv:1908.08962", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	"2022-03-02T23:29:05Z"	--- thumbnail: https://huggingface.co/front/thumbnails/google.png license: apache-2.0 --- BERT Miniatures === This is the set of 24 BERT models referenced in [Well-Read Students Learn Better: On the Importance of Pre-training Compact Models](https://arxiv.org/abs/1908.08962) (English only, uncased, trained with WordPiece masking). We have shown that the standard BERT recipe (including model architecture and training objective) is effective on a wide range of model sizes, beyond BERT-Base and BERT-Large. The smaller BERT models are intended for environments with restricted computational resources. They can be fine-tuned in the same manner as the original BERT models. However, they are most effective in the context of knowledge distillation, where the fine-tuning labels are produced by a larger and more accurate teacher. Our goal is to enable research in institutions with fewer computational resources and encourage the community to seek directions of innovation alternative to increasing model capacity. You can download the 24 BERT miniatures either from the [official BERT Github page](https://github.com/google-research/bert/), or via HuggingFace from the links below: \| \|H=128\|H=256\|H=512\|H=768\| \|---\|:---:\|:---:\|:---:\|:---:\| \| L=2 \|[2/128 (BERT-Tiny)][2_128]\|[2/256][2_256]\|[2/512][2_512]\|[2/768][2_768]\| \| L=4 \|[4/128][4_128]\|[4/256 (BERT-Mini)][4_256]\|[4/512 (BERT-Small)][4_512]\|[4/768][4_768]\| \| L=6 \|[6/128][6_128]\|[6/256][6_256]\|[6/512][6_512]\|[6/768][6_768]\| \| L=8 \|[8/128][8_128]\|[8/256][8_256]\|[8/512 (BERT-Medium)][8_512]\|[8/768][8_768]\| \| L=10 \|[10/128][10_128]\|[10/256][10_256]\|[10/512][10_512]\|[10/768][10_768]\| \| L=12 \|[12/128][12_128]\|[12/256][12_256]\|[12/512][12_512]\|[12/768 (BERT-Base)][12_768]\| Note that the BERT-Base model in this release is included for completeness only; it was re-trained under the same regime as the original model. Here are the corresponding GLUE scores on the test set: \|Model\|Score\|CoLA\|SST-2\|MRPC\|STS-B\|QQP\|MNLI-m\|MNLI-mm\|QNLI(v2)\|RTE\|WNLI\|AX\| \|---\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\|:---:\| \|BERT-Tiny\|64.2\|0.0\|83.2\|81.1/71.1\|74.3/73.6\|62.2/83.4\|70.2\|70.3\|81.5\|57.2\|62.3\|21.0\| \|BERT-Mini\|65.8\|0.0\|85.9\|81.1/71.8\|75.4/73.3\|66.4/86.2\|74.8\|74.3\|84.1\|57.9\|62.3\|26.1\| \|BERT-Small\|71.2\|27.8\|89.7\|83.4/76.2\|78.8/77.0\|68.1/87.0\|77.6\|77.0\|86.4\|61.8\|62.3\|28.6\| \|BERT-Medium\|73.5\|38.0\|89.6\|86.6/81.6\|80.4/78.4\|69.6/87.9\|80.0\|79.1\|87.7\|62.2\|62.3\|30.5\| For each task, we selected the best fine-tuning hyperparameters from the lists below, and trained for 4 epochs: - batch sizes: 8, 16, 32, 64, 128 - learning rates: 3e-4, 1e-4, 5e-5, 3e-5 If you use these models, please cite the following paper: ``` @article{turc2019, title={Well-Read Students Learn Better: On the Importance of Pre-training Compact Models}, author={Turc, Iulia and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina}, journal={arXiv preprint arXiv:1908.08962v2 }, year={2019} } ``` [2_128]: https://huggingface.co/google/bert_uncased_L-2_H-128_A-2 [2_256]: https://huggingface.co/google/bert_uncased_L-2_H-256_A-4 [2_512]: https://huggingface.co/google/bert_uncased_L-2_H-512_A-8 [2_768]: https://huggingface.co/google/bert_uncased_L-2_H-768_A-12 [4_128]: https://huggingface.co/google/bert_uncased_L-4_H-128_A-2 [4_256]: https://huggingface.co/google/bert_uncased_L-4_H-256_A-4 [4_512]: https://huggingface.co/google/bert_uncased_L-4_H-512_A-8 [4_768]: https://huggingface.co/google/bert_uncased_L-4_H-768_A-12 [6_128]: https://huggingface.co/google/bert_uncased_L-6_H-128_A-2 [6_256]: https://huggingface.co/google/bert_uncased_L-6_H-256_A-4 [6_512]: https://huggingface.co/google/bert_uncased_L-6_H-512_A-8 [6_768]: https://huggingface.co/google/bert_uncased_L-6_H-768_A-12 [8_128]: https://huggingface.co/google/bert_uncased_L-8_H-128_A-2 [8_256]: https://huggingface.co/google/bert_uncased_L-8_H-256_A-4 [8_512]: https://huggingface.co/google/bert_uncased_L-8_H-512_A-8 [8_768]: https://huggingface.co/google/bert_uncased_L-8_H-768_A-12 [10_128]: https://huggingface.co/google/bert_uncased_L-10_H-128_A-2 [10_256]: https://huggingface.co/google/bert_uncased_L-10_H-256_A-4 [10_512]: https://huggingface.co/google/bert_uncased_L-10_H-512_A-8 [10_768]: https://huggingface.co/google/bert_uncased_L-10_H-768_A-12 [12_128]: https://huggingface.co/google/bert_uncased_L-12_H-128_A-2 [12_256]: https://huggingface.co/google/bert_uncased_L-12_H-256_A-4 [12_512]: https://huggingface.co/google/bert_uncased_L-12_H-512_A-8 [12_768]: https://huggingface.co/google/bert_uncased_L-12_H-768_A-12
Xu-Ouyang/pythia-2.8b-deduped-int2-step36000-GPTQ-wikitext2-uva	Xu-Ouyang	"2024-09-16T07:22:09Z"	61	0	transformers	[ "transformers", "safetensors", "gpt_neox", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "2-bit", "gptq", "region:us" ]	text-generation	"2024-09-16T07:21:41Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
dmdoy/Emotion_Recognition_From_Speech	dmdoy	"2024-03-19T17:21:43Z"	0	2	null	[ "music", "code", "audio-classification", "en", "arxiv:1912.10458", "arxiv:1909.05645", "arxiv:1701.08071", "license:gpl-3.0", "region:us" ]	audio-classification	"2024-03-19T15:41:25Z"	--- license: gpl-3.0 language: - en metrics: - accuracy pipeline_tag: audio-classification tags: - music - code --- # Emotion Recognition From Speech (V1.0) <p align="justify">The understanding of emotions from voice by a human brain are normal instincts of human beings, but automating the process of emotion recognition from speech without referring any language or linguistic information remains an uphill grind. In the research work presented based on the input speech, I am trying to predict one of the six types of emotions (sad, neutral, happy, fear, angry, disgust). The diagram given below explain how emotion recognition from speech works. The audio features are extracted from input speech, then those features are passed to the emotion recognition model which predicts one of the six emotions for the given input speech.</p> ![Working Of Emotion Recgnition From Speech](https://user-images.githubusercontent.com/13017779/127468882-130282fb-9424-4366-a656-00c040232940.png) # Motivation <p align="justify">Most of the smart devices or voice assistants or robots present in the world are not smart enough to understand the emotions. They are just like command and follow devices they have no emotional intelligence. When people are talking to each other based on the voice they understand situation and react to it, for instance if someone is angry then other person will try to clam him by conveying in soft tone, these kind of harmonic changes are not possible with smart devices or voice assistants as they lack emtional intelligence. So adding emotions and making devices understand emotions will take them one step further to human like intelligence.</p> # Application <p align="justify">There are tonnes of applicates based on one can imagine. Few applications based on my thinking are human computer interaction using voice, home automation, anger/stress management by decoding emotions from voice, emotion recognition can help in detecting fear and cops can used this system to check if dialer is feared by some one or its just a normal call to register a complain, Marketing companies can use emotions to sell products based on user mood, autonomous vehicles can detect user emotion and adjust the speed of vehicles, It can help in solving psychological or depression problems. These are few applications according to me but there can be many more as voice based systems are increasing, even voice bsed chatting is common on social media platforms like clubhouse, discord, twitch, and others.</p> # Libraries and coding language used for the project ![languages](https://img.shields.io/github/languages/count/devanshmody/Research_Methodology_COMP-5112) <a href="http://ffmpeg.org/"><img src="https://img.shields.io/badge/ffmpeg-green?style=flat&logo=ffmpeg&labelColor=green"></a> <a href="https://pandas.pydata.org/"><img src="https://img.shields.io/badge/pandas-darkblue?style=flat&logo=pandas&labelColor=darkblue"></a> <a href="https://numpy.org/"><img src="https://img.shields.io/badge/numpy-skyblue?style=flat&logo=numpy&labelColor=skyblue"></a> <a href="https://www.tensorflow.org/"><img src="https://img.shields.io/badge/tensorflow-orange?style=flat&logo=tensorflow&labelColor=orange"></a> <a href="https://docs.python.org/3/library/os.html"><img src="https://img.shields.io/badge/os-lightyellow?style=flat&logo=os&labelColor=lightyellow"></a> <a href="https://docs.python.org/3/library/time.html"><img src="https://img.shields.io/badge/time-lightgreen?style=flat&logo=time&labelColor=lightgreen"></a> <a href="https://librosa.org/"><img src="https://img.shields.io/badge/librosa-pink?style=flat&logo=librosa&labelColor=pink"></a> <a href="https://docs.python.org/3/library/warnings.html"><img src="https://img.shields.io/badge/warnings-lightred?style=flat&logo=warings&labelColor=lightred"></a> <a href="https://docs.python.org/3/library/base64.html"><img src="https://img.shields.io/badge/base64-lightgrey?style=flat&logo=base64&labelColor=lightgrey"></a> <a href="https://pypi.org/project/google-colab/"><img src="https://img.shields.io/badge/google-colab-lightorange?style=flat&logo=google-colab&labelColor=lightorange"></a> <a href="https://docs.python.org/3/library/glob.html"><img src="https://img.shields.io/badge/glob-lightgrey?style=flat&logo=glob&labelColor=lightgrey"></a> <a href="https://docs.python.org/3/library/re.html"><img src="https://img.shields.io/badge/regex-darkgreen?style=flat&logo=regex&labelColor=darkgreen"></a> <a href="https://scikit-learn.org/stable/"><img src="https://img.shields.io/badge/scikit-learn-darkorange?style=flat&logo=scikit-learn&labelColor=darkorange"></a> <a href="https://keras.io/"><img src="https://img.shields.io/badge/keras-darkred?style=flat&logo=keras&labelColor=darkred"></a> <a href="https://www.scipy.org/"><img src="https://img.shields.io/badge/scipy-violet?style=flat&logo=scipy&labelColor=violet"></a> <a href="https://docs.python.org/3/library/io.html"><img src="https://img.shields.io/badge/io-grey?style=flat&logo=io&labelColor=grey"></a> <a href="https://ipython.org/"><img src="https://img.shields.io/badge/ipython-purple?style=flat&logo=ipython&labelColor=purple"></a> <a href="https://matplotlib.org/"><img src="https://img.shields.io/badge/matplotlib-brown?style=flat&logo=matplotlib&labelColor=brown"></a> <a href="https://www.python.org/doc/"><img src="https://img.shields.io/badge/python3-yellow?style=flat&logo=python3&labelColor=yellow"></a> ![programming style](https://img.shields.io/badge/programming%20style-functional-brightgreen) ![programming language](https://img.shields.io/badge/programming%20language-python-red) # Dataset description <p align="justify">I have used four datasets and all four datasets are freely available to downloaded from kaggle website. So I have downloaded the data, extracted and stored in my google drive.</p> 1) Ryerson Audio Visual Database of Emotional Speech and Song (Ravdess) dataset description:<br> Dataset link to download: "https://www.kaggle.com/uwrfkaggler/ravdess-emotional-speech-audio" <br> Dataset stored on google drive at path: "/content/drive/MyDrive/Audiofiles/audio_speech_actors_01-24/"<br> Dataset contains sub folders and file names as example in numbers format 03-01-01-01-01-01-01.wav.<br> Actor (01 to 24. Odd numbered actors are male, even numbered actors are female).<br> So based on the number there is a identifier for each number and its meaning are as follows: * Modality (01 = full-AV, 02 = video-only, 03 = audio-only). * Vocal channel (01 = speech, 02 = song). * Emotion (01 = neutral, 02 = calm, 03 = happy, 04 = sad, 05 = angry, 06 = fearful, 07 = disgust, 08 = surprised). * Emotional intensity (01 = normal, 02 = strong). NOTE: There is no strong intensity for the 'neutral' emotion. * Statement (01 = "Kids are talking by the door", 02 = "Dogs are sitting by the door"). * Repetition (01 = 1st repetition, 02 = 2nd repetition). * Therefore file 03-01-01-01-01-01-01.wav can be deduced as 03=audio-only, 01=speech, 01=neutral, 01=normal, 01=statement kids and 01=1st repetition. 2) Crowd sourced Emotional Mutimodal Actors Dataset (CREMA-D) dataset description:<br> Dataset link to download: "https://www.kaggle.com/ejlok1/cremad" <br> Dataset stored on google drive at path: "/content/drive/MyDrive/Audiofiles/AudioWAV/"<br> The format of files is 1001_DFA_ANG_XX.wav, where ANG stands for angry emotion.<br> Similarly different emotion mappings are as follows:<br> {'SAD':'sad','ANG':'angry','DIS':'disgust','FEA':'fear','HAP':'happy','NEU':'neutral'} 3) Toronto emotional speech set (Tess) dataset description:<br> Dataset link to download: "https://www.kaggle.com/ejlok1/toronto-emotional-speech-set-tess" <br> Dataset stored on google drive at path: "/content/drive/MyDrive/Audiofiles/TESS Toronto emotional speech set data/"<br> There are folders in format OAF_angry, OAF_neural, OAF_disgust, YAF_sad and so on, where name after the underscore of the folder name contains the emotion information, so the name after the underscore of the folder name is taken and files residing insider the folders are labeled accordingly. 4) Surrey Audio Visual Expressed Emotion (Savee) dataset description:<br> Dataset link to download: "https://www.kaggle.com/ejlok1/surrey-audiovisual-expressed-emotion-savee" <br> Dataset stored on google drive at path: "/content/drive/MyDrive/Audiofiles/ALL/"<br> The files are in a format DC_a01.wav where a single character contains the emotion information , for example character 'a' after underscore in the file name "DC_a01.wav" means emotion is angry.<br> Similarly different emotion mappings are as follows:<br> {'a':'anger','d':'disgust','f':'fear','h':'happiness','n':'neutral','sa':'sadness','su':'surprise'} # Universal decorator fucntion to calculate total time ``` def calc_time(func): def inner(args, kwargs): st = time.time() result = func(args,*kwargs) end = time.time()-st print("Total time required: {:.3f} ms".format(end 1000)) return result return inner ``` # Description of important functions present in code (Model design and evaluation): <p align="justify">There are many functions in the program as functional programming style is used. Here I am going to describe a few important functions which call other functions inside the functions and generate files and results. Detailed description of each function and its use can be found in the code file.</p> * Audio_features_extract() this function is used to extract audio features and generates a csv file at path "/content/drive/MyDrive/Audiofiles /Audio_features_All_pr.csv" which contains audio features and their respective label information. * Below given image shows snapshot of the csv file, the file has a total of 33954 rows × 179 columns. ![csv file snapshot](https://user-images.githubusercontent.com/13017779/127515316-3c4e2752-e376-4e71-ad76-513cec61bf1d.png) * The csv file is loaded using pandas library, additional_preprocess() function carries out Exploratory Data Analysis and drop emotions with limited samples to avoid missclassifications and then dataset is divided into train, test and validation set. * Below image gives the detailed description of the whole process. ![Explorator Data Analysis and data preprocessing](https://user-images.githubusercontent.com/13017779/127515420-232f3180-34df-4531-8e34-93225748a0a6.png) * Deep learning model for speech recognition is trained using the training data and at every epoch or checkpoint validation accuracy is calucated. The epoch or checkpoint which gives highest validation accuracy, the best model is saved for that epoch or checkpoint at path "/content/drive/ MyDrive/Audiofiles/ emotionrecognition.hdf5", the model giving highest validation accuracy is only saved. ![model training snap shot](https://user-images.githubusercontent.com/13017779/127520834-e0b9fb86-2a60-4eed-a089-f28f5a028a48.png) # Description of testing model in real time: Once the model is build and training is completed the emotion recognition model can be loaded from the path "/content/drive/MyDrive/Audiofiles/emotion-recognition .hdf5" and can be tested for the given input speech in real time. * The data for real time model testing is recorded using the microphone. * The code to record audio speech using microphone is integrated from the link "https://ricardodeazambuja.com/deep_learning/2019/03/09/audio_and_video_google_colab/". * Then features are extracted from speech and passed to emotion recognition model which predicts one of the six emotions. * Below figure shows the audio waveform and output of the emotion recognition model. ![realtimeresult](https://user-images.githubusercontent.com/13017779/127523138-12df54f8-6af3-4907-9e80-56354bba12b8.png) # Results * Below figure shows the training, testing and validation accuracy achieved by the emotion recognition model. ![accuracy](https://user-images.githubusercontent.com/13017779/127524338-0209ab4e-eb82-4244-b519-e25cb4838859.png) * Below figure shows the classification report and it can be seen in the report that for all the classes the value is greater than 0.5 which means the model can predict the emotions accuratly to some extent. If the value is equal to 1.0 for all clases then it means model can predict accurrately always given the input speech. But its diffcult to achieve real time prediction and 100% accuracy on real time envoiurment as there is noise and many other factors which can affect the output. Given a challenge it can overcomed by training with big set of data in different languages to develop a universal model. ![classification](https://user-images.githubusercontent.com/13017779/127525847-6d2816a7-2e8b-4a3a-8385-e9c7a63bb870.png) * The 0,1,2,3,4,5 in classification report resembles to different emotions which can be decoded from below image. ![emotionsmapping](https://user-images.githubusercontent.com/13017779/127526209-2d8748ca-2d99-4f70-ae11-1da5371cce61.png) * Below figure shows output of confusion matrix.<br> ![confumatrix](https://user-images.githubusercontent.com/13017779/127526415-1aca3e8f-32f7-44ac-bf34-fea0fd412209.png) * Below figure shows the training loss and accuracy curves, despite the model giving the training accuracy of 100%, validation and testing accuracy is near to 75%-76%, my model gives the highest accuracy when compared to the authors who previously carried out the research work in this area. ![curves](https://user-images.githubusercontent.com/13017779/127526942-9432d473-e6cc-4ef6-9a77-958ea56f3af0.png) * Additionally to check wheather the model can work for all types of voices and on unlabeled data a test was carried out using combination of different voices and unlabled data. Below figure shows the results. ![unlabeltest](https://user-images.githubusercontent.com/13017779/127530261-ba33d4ea-640e-45ff-8bc9-7015eceb5e9f.png) * Below figures shows comparison of my model with other authors who worked previously in this area of emotion recognition from speech. ![comparison](https://user-images.githubusercontent.com/13017779/127533006-fac626bf-8bda-4bac-bbbb-fb72ef291f0a.png) # Installation To download and run my google colab file 1130532_ResearchMethodology_Project_Final.ipynb following changes need to be made: * Frist and foremost make sure all neccessary libraries mentioned above are installed. * To install any library in the computer machine just use command pip install library name. * Then install the data from the following links: * "https://www.kaggle.com/ejlok1/cremad" * "https://www.kaggle.com/uwrfkaggler/ravdess-emotional-speech-audio" * "https://www.kaggle.com/ejlok1/surrey-audiovisual-expressed-emotion-savee" * "https://www.kaggle.com/ejlok1/toronto-emotional-speech-set-tess" * Extract the downloaded data from the above given links * Once the data is extracted just use my code and pass the proper path information to the functions. * These paths are datapaths, csv file path and paths where reults are stored. * Correct path information needs to be given in the functions ravdess_data(), crema_data(), tess_data(), saveee_data(), fetch_data(), Audio_features_extract(), audio_features_final(), emotion_recognition_model(), test_realtime(), evaluate_model(), unknown_audio() and diff_lang_test() * Below given are snnipets of code where proper path information needs to be given for the above given functions. * ``` ravdess = "/content/drive/MyDrive/Audiofiles/audio_speech_actors_01-24/" ``` * ``` crema = "/content/drive/MyDrive/Audiofiles/AudioWAV/" ``` * ``` tess = "/content/drive/MyDrive/Audiofiles/TESS Toronto emotional speech set data/" ``` * ``` savee = "/content/drive/MyDrive/Audiofiles/ALL/" ``` * ``` final_combined.to_csv("/content/drive/MyDrive/preprocesseddata.csv",index=False,header=True) ``` * ``` Features.to_csv('/content/drive/MyDrive/Audiofiles/Audio_features_All_pr.csv',index=False) ``` * ``` df = additional_preprocess("/content/drive/MyDrive/Audiofiles/Audio_features_All_pr.csv") ``` * ``` filepath = "/content/drive/MyDrive/Audiofiles/emotion-recognition.hdf5" ``` * ``` res_model = load_model("/content/drive/MyDrive/Audiofiles/emotion-recognition.hdf5") ``` * ``` os.chdir('/content/drive/MyDrive/Audiofiles/realtimetested') ``` * ``` np.save('/content/drive/MyDrive/Audiofiles/realtimetested/audiorec{}.npy'.format(len(files)),audio) ``` * ``` plt.savefig("audiorec{}.png".format(len(files))) ``` * ``` df["path"][i] = '/content/drive/MyDrive/Audiofiles/realtimetested/audiorec{}.npy'.format(len(files)) ``` * ``` df.to_csv('/content/drive/MyDrive/Audiofiles/realtimetested/real_time_predicted_audio_features.csv', mode='a', index=False) ``` * ``` model = load_model("/content/drive/MyDrive/Audiofiles/emotion-recognition.hdf5") ``` * ``` path = '/content/drive/MyDrive/Audiofiles/realtimetested/testing on sample voices/' ``` * ``` Features.to_csv('/content/drive/MyDrive/Audiofiles/realtimetested/unkonwaudio.csv',index=False) ``` * ``` df = pd.read_csv('/content/drive/MyDrive/Audiofiles/realtimetested/unkonwaudio.csv') ``` * ``` res_model = load_model("/content/drive/MyDrive/Audiofiles/emotion-recognition.hdf5") ``` * So once the path information is given correctly its time to run the functions, run all the fuctions in the same sequence given in my colab file 1130532_ResearchMethodology_Project_Final.ipynb. * If one dosent want to train the model just test the model then they can use the model file "emotion-recognition.hdf5", change the paths in test_realtime() function and they can test the model. * Following path needs to be changed: * ``` res_model = load_model("/content/drive/MyDrive/Audiofiles/emotion-recognition.hdf5") ``` * ``` os.chdir('/content/drive/MyDrive/Audiofiles/realtimetested') ``` * ``` np.save('/content/drive/MyDrive/Audiofiles/realtimetested/audiorec{}.npy'.format(len(files)),audio) ``` * ``` plt.savefig("audiorec{}.png".format(len(files))) ``` * ``` df["path"][i] = '/content/drive/MyDrive/Audiofiles/realtimetested/audiorec{}.npy'.format(len(files)) ``` * ``` df.to_csv('/content/drive/MyDrive/Audiofiles/realtimetested/real_time_predicted_audio_features.csv', mode='a', index=False) ``` * If you want to develop or implement or setupt the whole code then as mentioned give proper paths and run all the functions its done. * Check out my colab file 1130532_ResearchMethodology_Project_Final.ipynb to see the time required by the individual process to complete. * The main() function does all the work of training the model and evaluating the model. Once the main function completes running the model is file is generated and can used for real time testing. * This is all about installation, building the model and feature extraction are one time process, once completed model is deployed in real time enviourment for testing and using the model for recognizing emotions from speech. # usage * As mentioned in the installation process, once libraries, datasets are downloaded, proper path information is given functions should be run in a sequence as mentioned in the colab file 1130532_ResearchMethodology_Project_Final.ipynb. * Following are the functions that required to run and the sequence is same as mentioned below and in the colab file 1130532_ResearchMethodology_Project_Final.ipynb * Remeber that every function requires amount of time to complete the process so. * Following is the list of sequence of functions which are required to run after running the import libraries code cell section: * Universal python decorator function to calculate total time. ``` def calc_time(func) ``` * Data preprocessing functions ``` def ravdess_data() def crema_data() def tess_data() def saveee_data() def fetch_data() ``` * Data augmentation functions ``` def noise(data) def stretch(data, rate=0.8) def shift(data) def pitch(data, sampling_rate, pitch_factor=0.7) ``` * Below given functions are for feature extraction, run this functions only once as it requires time to extract features form auido. Also features extraction is a one time process. Once features are extracted we can carry out further processing and train the emotion recognition model. ``` def extract_features(data,sample_rate) def get_features(path) def Audio_features_extract() ``` * function to plot loss and accuracy curves ``` def plotgraph(history) ``` * Function to perform additional preprocessing on data and splitting the datasets. ``` def additional_preprocess(filepath) def audio_features_final() ``` * function to build the emotion recognition model ``` def emotion_recognition_model(x_train,y_train,x_val,y_val) ``` * Run the full javascript template starting with ``` #this javascript is used to tell colab cell to open microphone and record audio AUDIO_HTML = """ <script> ``` * function to invoke microphone of user and record audio ``` def get_audio() ``` * function for getting input speech features and real time testing ``` def get_features_recorded(data,sr) def test_realtime(encoder) ``` * function to evaluate the performance of the model ``` def evaluate_model(x_train, x_test, y_train, y_test, x_val, y_val) ``` * main() function calls the functions in a sequence and after the execution of the main() function the deepl learning model for emotion recognition is ready. ``` @calc_time def main(): #get train,test data and labels x_train, x_test, y_train, y_test, x_val, y_val, encoder = audio_features_final() #call the emotion recognition model emotion_recognition_model(x_train,y_train,x_val,y_val) #evaluate the model performance evaluate_model(x_train, x_test, y_train, y_test, x_val, y_val) if __name__:main() ``` * Once the model is trained and model file is generated one can use the below fucntions to test the model in real time enviourment. ``` x_train, x_test, y_train, y_test, x_val, y_val, encoder = audio_features_final() test_realtime(encoder) ``` * If some one wants to used my trained model file directly then no need to run the main() function just run the above given two function to test in the real time enviourment. * Also if using google colab make sure the function which are called inside the audio_features_final() and realtime_tested() are executed in advance as these two functions are dependent on them. * Make sure all functions are called properly as mentioned in my colab file 1130532_ResearchMethodology_Project_Final.ipynb * Additionally for my research work I carried on unkown sample data in different languages. * So you can do if you want test on unkown samples by downloading additional data from this link "https://superkogito.github.io/SER-datasets/" * You will require to preprocess the data then you can use my get_features_recorded(audio,sr) function to get the audio features then pass the audio features to the<p align="justify"> model to predict the outcome. * I have already downloaded the few audio samples for testing on different voices and data is available on my google drive link, please sendme mail to access the data I will give acccess to the google dr</p> * For my custom data in different languages I have used below functions to test the emotion recognition models. ``` def unknown_audio() def diff_lang_test() ''' * Whenever using the code make sure the function used inside the fnctions are called prior to executing the required function and all functions are executed in a proper sequence. # Video on Installation / Usage <p align="justify">Below given is the video on installation and usage of my project code in colab file. The video guides you by showing where to make path changes and how to install and run the code and test the code. The datasets link to download are already given above. I would request to read the installation and usage section and then watch this video so it will give a clear idea of the whole project and its working. click on the below youtube image to launch the video.</p> <a href="https://youtu.be/kjttI89pIrI"><img src="https://img.shields.io/badge/youtube-red?style=flat&logo=youtube&labelColor=red"></a> # Support / Contact details Given below are few of my social media accounts where anyone can contact me.<br> <a href="https://in.linkedin.com/in/devansh-mody-5013aaab"><img src="https://img.shields.io/badge/LinkedIn-blue?style=flat&logo=linkedin&labelColor=blue"></a> <a href="https://mobile.twitter.com/modydevansh"><img src="https://img.shields.io/badge/twitter-blue?style=flat&logo=twitter&labelColor=blue"></a> <a href="https://www.youtube.com/channel/UCtc_46TMSXPUMpzVP0IAJUw"><img src="https://img.shields.io/badge/youtube-red?style=flat&logo=youtube&labelColor=red"></a> <a href="https://www.instagram.com/devansh_mody/?hl=en"><img src="https://img.shields.io/badge/instagram-purple?style=flat&logo=instagram&labelColor=pink"></a> <a href="https://devanshmody.blogspot.com/"><img src="https://img.shields.io/badge/My bloging website-yellow?style=flat&logo=blog&labelColor=lightyellow"></a> <br>One can also contact me by email <img src="https://img.shields.io/badge/gmail%20id-devanshmody2017%40gmail.com-red"><br> For access to my google drive to see the setup of the whole project mail me on gmail id mentioned above access will be given to the selected people for some amount of time. # Road-map (future ideas) <p align="justify">The backgorund noise may cause errors when testing the model in real time enviourment and thus it can affect the output of the model. To avoid the noise audio segmentation needs to be performed, so I am planning to develop an audio segmentation model which can seprate user speech from background noise so emotions can be predicted accurately. Also I will be collecting audio in different formats extract features and train the model so a universal model can be developed. Once audio model is build it can be applied to video also by combining audio model of emotion recognition with facial model for emotion recognition, this can help in acheving more accurate output. Additionally three models can be combined that is textual, voice and facial based but it requires huge computation power and there is very limited study available on combining three models for emotion recogniton, beaucse a avoting mechanism or strategy needs to be developed for predicting the emotion from three models as there can be cases where each model can predict different emotions or two model predict same emotion and one predicts another emotion. Moreover I would like to build a audionet kind of embeddings similar to imagenet and word embeddings which will help other researchers working in this area to use pretrained audio embeddings.</p> # How to contribute <p align="justify">One can contribute by extracting features from different auido files the code for extracting features can be used from my ipynb file, different dataset may reqire different data preprocessing so one also write a function for data preprocessing and send me both prerporcessing code and csv file, so I can integrate both data preprocessing function and csv file with my csv file Audio_features_All_pr.csv. Additionally I am planning to build three model audio segmentation model, facial emotion recognition model and textual model so one can contribute by writing the function for the same and integrate it. Send me a git merge request to integrate code or contact me so we can check the integrity of code and combine the code. One can also branch out create their own branch and then we can merge the branch. Additionaly one can also fork the repository.</p> # Google drive links * Model file link: https://drive.google.com/file/d/1dGCxq08cyNYO86u_XePg7tQzerrjdEFM/view?usp=share_link * Preprocessed dataset link: https://drive.google.com/file/d/17zqTlW2xqUJy1NA3fOBdXo43Ace4DruR/view?usp=share_link # Authors / Acknowledgements I would like to thank [@Ricardo]( https://ricardodeazambuja.com/deep_learning/2019/03/09/audio_and_video_google_colab/) for providing javascript code to inovke mircophone of user from google colab cell. As google colab dosent support audio recording using microphone so a javacript function needs to be written to inovke microphone and record auido. I would also like to thank [@Fadi Badine](https://keras.io/examples/audio/speaker_recognition_using_cnn/) my deep learning neural network model for emotion recognition is based on his model for automatic speech recognition.</p> # References [1] Francesc Alı́as, Joan Claudi Socoró and Xavier Sevillano, ”A Review of Physical and Perceptual Feature Extraction Techniques for Speech, Music and Environmental Sounds”, Appl. Sci. 2016.<br> [2] Kannan Venkataramanan and Haresh Rengaraj Rajamohan, ”Emotion Recognition from Speech”, arXiv:1912.10458v1 [cs.SD] 22 Dec 2019.<br> [3] Haiyang Xu, Hui Zhang, Kun Han, Yun Wang, Yiping Peng and Xian-gang Li, ”Learning Alignment for Multimodal Emotion Recognition from Speech”, arXiv:1909.05645v2 [cs.CL] 3 Apr 2020.<br> [4] Aharon Satt, Shai Rozenberg and Ron Hoory, ”Efficient Emotion Recognition from Speech Using Deep Learning on Spectrograms”, INTERSPEECH 2017, Stockholm, Sweden, August 20–24, 2017.<br> [5] Jia Rong, Gang Li and Yi Ping Phoebe Chen, ”Acoustic feature selection for automatic emotion recognition from speech”, Information Processing and Management 45 (2009) 315–328.<br> [6] K. Sreenivasa Rao, Tummala Pavan Kumar, Kusam Anusha, Bathina Leela, Ingilela Bhavana and Singavarapu V.S.K. Gowtham, ”Emotion Recognition from Speech”, (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 3 (2) , 2012,3603-3607.<br> [7] Vladimir Chernykh and Pavel Prikhodko, ”Emotion Recognition From Speech With Recurrent Neural Networks”, arXiv:1701.08071v2 [cs.CL] 5 Jul 2018.<br> [8] Sabur Ajibola Alim and Nahrul Khair Alang Rashid, ”Some Commonly Speech Feature Feature Extraction Algorithms”. Published: December 12 2018, DOI: 10.5772/intechopen.80419.<br> [9] Oh Wook Kwon, Kwokleung Chan, Jiucang Hao and Te Won Lee, ”Emotion Recognition by Speech Signals”, GENEVA, EUROSPEECH 2003.<br> [10] K.V.Krishna Kishore and P.Krishna Satish, ”Emotion Recognition in Speech Using MFCC and Wavelet Features”, IEEE International Advance Computing Conference (IACC), 2013.<br> [11] Panagiotis Tzirakis, Jiehao Zhang and Björn W. Schuller, ”END-TO-END SPEECH EMOTION RECOGNITION USING DEEP NEURAL NETWORKS”, IEEE International Advance Computing Conference (IACC), 2018.<br> # License [![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0) # Project Status <p align="justify">Emotion recognition model is finished and its ready and can be used in real time. The 1130532_ResearchMethodology_Project_Final.ipynb file can be downloaded and used by providing neccesary path changes as mentioned in installation and usage sections. I am looking forward to develop other models mentioned in road-map (future ideas) and integrate all those models with my current emotion recognition model.</p>
jerryzh168/llama3-8b-autoquant	jerryzh168	"2025-02-19T01:00:26Z"	58	0	transformers	[ "transformers", "pytorch", "llama", "text-generation", "torchao", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2025-01-02T22:50:36Z"	--- library_name: transformers tags: [torchao] --- # Description This model is a quantized version for original model "meta-llama/Meta-Llama-3-8B", quantized with torchao's autoquant API. It contains both model weights and compilation artifacts caches that records the itermediate compilation artifacts. # Quantization Details * Quantization Type: autoquant * min_sqnr: 20 # Usage You can use this model in your applications by loading it directly from the Hugging Face Hub: ``` from transformers import AutoModel model = AutoModel.from_pretrained("jerryzh168/llama3-8b-autoquant") from huggingface_hub import hf_hub_download import pickle hf_hub_download(repo_id="jerryzh168/llama3-8b-autoquant", filename="compile_artifacts.pt2", local_dir="/tmp/") with open("/tmp/compile_artifacts.pt2", "rb") as f: artifacts = pickle.load(f) artifact_bytes, cache_info = artifacts torch.compiler.load_cache_artifacts(artifact_bytes) ```
MOOsipenko/q-FrozenLake-v1-4x4-noSlippery	MOOsipenko	"2025-02-12T18:18:31Z"	0	0	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	"2025-02-12T18:18:26Z"	--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage ```python model = load_from_hub(repo_id="MOOsipenko/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
mytoon/toon_lora_fixed1	mytoon	"2023-11-27T13:53:41Z"	6	1	diffusers	[ "diffusers", "tensorboard", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "lora", "template:sd-lora", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]	text-to-image	"2023-11-27T13:20:54Z"	--- tags: - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers - lora - template:sd-lora base_model: stabilityai/stable-diffusion-xl-base-1.0 instance_prompt: 1girl in TOK style license: openrail++ --- # SDXL LoRA DreamBooth - mytoon/toon_lora_fixed1 <Gallery /> ## Model description These are mytoon/toon_lora_fixed1 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained using [DreamBooth](https://dreambooth.github.io/). LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Trigger words You should use 1girl in TOK style to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](mytoon/toon_lora_fixed1/tree/main) them in the Files & versions tab.
lothritz/Lb_mBERT	lothritz	"2023-09-26T12:02:35Z"	162	0	transformers	[ "transformers", "pytorch", "bert", "fill-mask", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	"2023-07-07T09:08:52Z"	# Lb_mBERT Lb_mBERT is a BERT-like language model for the Luxembourgish language. We used the weights of the multilingual BERT (mBERT) language model as a starting point and continued pre-training it on the MLM task using the same corpus that we used for our LuxemBERT model (https://huggingface.co/lothritz/LuxemBERT). We achieved higher performances on some downstream tasks than the original LuxemBERT, and another Luxembourgish BERT model called DA BERT (https://huggingface.co/iolariu/DA_BERT). If you would like to know more about our work, the pre-training corpus, or use our models or datasets, please check out/cite the following papers: ``` @inproceedings{lothritz-etal-2022-luxembert, title = "{L}uxem{BERT}: Simple and Practical Data Augmentation in Language Model Pre-Training for {L}uxembourgish", author = "Lothritz, Cedric and Lebichot, Bertrand and Allix, Kevin and Veiber, Lisa and Bissyande, Tegawende and Klein, Jacques and Boytsov, Andrey and Lefebvre, Cl{\'e}ment and Goujon, Anne", booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference", month = jun, year = "2022", address = "Marseille, France", publisher = "European Language Resources Association", url = "https://aclanthology.org/2022.lrec-1.543", pages = "5080--5089", abstract = "Pre-trained Language Models such as BERT have become ubiquitous in NLP where they have achieved state-of-the-art performance in most NLP tasks. While these models are readily available for English and other widely spoken languages, they remain scarce for low-resource languages such as Luxembourgish. In this paper, we present LuxemBERT, a BERT model for the Luxembourgish language that we create using the following approach: we augment the pre-training dataset by considering text data from a closely related language that we partially translate using a simple and straightforward method. We are then able to produce the LuxemBERT model, which we show to be effective for various NLP tasks: it outperforms a simple baseline built with the available Luxembourgish text data as well the multilingual mBERT model, which is currently the only option for transformer-based language models in Luxembourgish. Furthermore, we present datasets for various downstream NLP tasks that we created for this study and will make available to researchers on request.", } ``` ``` @inproceedings{lothritz2023comparing, title={Comparing Pre-Training Schemes for Luxembourgish BERT Models}, author={Lothritz, Cedric and Ezzini, Saad and Purschke, Christoph and Bissyande, Tegawend{\'e} Fran{\c{c}}ois D Assise and Klein, Jacques and Olariu, Isabella and Boytsov, Andrey and Lefebvre, Clement and Goujon, Anne}, booktitle={Proceedings of the 19th Conference on Natural Language Processing (KONVENS 2023)}, year={2023} } ```
BenevolenceMessiah/Yi-Coder-9B-Chat-8x-MoE	BenevolenceMessiah	"2024-09-18T00:14:35Z"	8	0	transformers	[ "transformers", "safetensors", "mixtral", "text-generation", "mergekit", "merge", "conversational", "arxiv:2306.01708", "arxiv:2403.04652", "base_model:01-ai/Yi-Coder-9B-Chat", "base_model:finetune:01-ai/Yi-Coder-9B-Chat", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-09-14T22:23:35Z"	--- base_model: - 01-ai/Yi-Coder-9B-Chat library_name: transformers tags: - mergekit - merge license: apache-2.0 --- # merge This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the [MoE](https://arxiv.org/abs/2306.01708) merge method using [01-ai/Yi-Coder-9B-Chat](https://huggingface.co/01-ai/Yi-Coder-9B-Chat) as a base. ### Models Merged The following models were included in the merge: * [01-ai/Yi-Coder-9B-Chat](https://huggingface.co/01-ai/Yi-Coder-9B-Chat) ### Configuration The following YAML configuration was used to produce this model: ```yaml base_model: 01-ai/Yi-Coder-9B-Chat gate_mode: random dtype: bfloat16 experts: - source_model: 01-ai/Yi-Coder-9B-Chat - source_model: 01-ai/Yi-Coder-9B-Chat - source_model: 01-ai/Yi-Coder-9B-Chat - source_model: 01-ai/Yi-Coder-9B-Chat - source_model: 01-ai/Yi-Coder-9B-Chat - source_model: 01-ai/Yi-Coder-9B-Chat - source_model: 01-ai/Yi-Coder-9B-Chat - source_model: 01-ai/Yi-Coder-9B-Chat ``` <picture> <img src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="120px"> </picture> </div> <p align="center"> <a href="https://github.com/01-ai">🐙 GitHub</a> • <a href="https://discord.gg/hYUwWddeAu">👾 Discord</a> • <a href="https://twitter.com/01ai_yi">🐤 Twitter</a> • <a href="https://github.com/01-ai/Yi-1.5/issues/2">💬 WeChat</a> <br/> <a href="https://arxiv.org/abs/2403.04652">📝 Paper</a> • <a href="https://01-ai.github.io/">💪 Tech Blog</a> • <a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#faq">🙌 FAQ</a> • <a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#learning-hub">📗 Learning Hub</a> </p> # Intro Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters. Key features: - Excelling in long-context understanding with a maximum context length of 128K tokens. - Supporting 52 major programming languages: ```bash 'java', 'markdown', 'python', 'php', 'javascript', 'c++', 'c#', 'c', 'typescript', 'html', 'go', 'java_server_pages', 'dart', 'objective-c', 'kotlin', 'tex', 'swift', 'ruby', 'sql', 'rust', 'css', 'yaml', 'matlab', 'lua', 'json', 'shell', 'visual_basic', 'scala', 'rmarkdown', 'pascal', 'fortran', 'haskell', 'assembly', 'perl', 'julia', 'cmake', 'groovy', 'ocaml', 'powershell', 'elixir', 'clojure', 'makefile', 'coffeescript', 'erlang', 'lisp', 'toml', 'batchfile', 'cobol', 'dockerfile', 'r', 'prolog', 'verilog' ``` For model details and benchmarks, see [Yi-Coder blog](https://01-ai.github.io/) and [Yi-Coder README](https://github.com/01-ai/Yi-Coder). <p align="left"> <img src="https://github.com/01-ai/Yi/blob/main/assets/img/coder/yi-coder-calculator-demo.gif?raw=true" alt="demo1" width="500"/> </p> # Models \| Name \| Type \| Length \| Download \| \|--------------------\|------\|----------------\|---------------------------------------------------------------------------------------------------------------------------------------------------\| \| Yi-Coder-9B-Chat \| Chat \| 128K \| [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-Coder-9B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-Coder-9B-Chat) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-Coder-9B-Chat) \| \| Yi-Coder-1.5B-Chat \| Chat \| 128K \| [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-Coder-1.5B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-Coder-1.5B-Chat) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-Coder-1.5B-Chat) \| \| Yi-Coder-9B \| Base \| 128K \| [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-Coder-9B) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-Coder-9B) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-Coder-9B) \| \| Yi-Coder-1.5B \| Base \| 128K \| [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-Coder-1.5B) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-Coder-1.5B) • [🟣 wisemodel](https://wisemodel.cn/models/01.AI/Yi-Coder-1.5B) \| \| \| # Benchmarks As illustrated in the figure below, Yi-Coder-9B-Chat achieved an impressive 23% pass rate in LiveCodeBench, making it the only model with under 10B parameters to surpass 20%. It also outperforms DeepSeekCoder-33B-Ins at 22.3%, CodeGeex4-9B-all at 17.8%, CodeLLama-34B-Ins at 13.3%, and CodeQwen1.5-7B-Chat at 12%. <p align="left"> <img src="https://github.com/01-ai/Yi/blob/main/assets/img/coder/bench1.webp?raw=true" alt="bench1" width="1000"/> </p> # Quick Start You can use transformers to run inference with Yi-Coder models (both chat and base versions) as follows: ```python from transformers import AutoTokenizer, AutoModelForCausalLM device = "cuda" # the device to load the model onto model_path = "01-ai/Yi-Coder-9B-Chat" tokenizer = AutoTokenizer.from_pretrained(model_path) model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto").eval() prompt = "Write a quick sort algorithm." messages = [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(device) generated_ids = model.generate( model_inputs.input_ids, max_new_tokens=1024, eos_token_id=tokenizer.eos_token_id ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] print(response) ``` For getting up and running with Yi-Coder series models quickly, see [Yi-Coder
mradermacher/Qwen2-0.5B-Chat_DPO-GGUF	mradermacher	"2024-06-11T22:14:00Z"	12	0	transformers	[ "transformers", "gguf", "llama-factory", "en", "base_model:JCHAVEROT/Qwen2-0.5B-Chat_DPO", "base_model:quantized:JCHAVEROT/Qwen2-0.5B-Chat_DPO", "endpoints_compatible", "region:us", "conversational" ]	null	"2024-06-11T22:11:34Z"	--- base_model: JCHAVEROT/Qwen2-0.5B-Chat_DPO language: - en library_name: transformers quantized_by: mradermacher tags: - llama-factory --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/JCHAVEROT/Qwen2-0.5B-Chat_DPO <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.Q3_K_S.gguf) \| Q3_K_S \| 0.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.IQ3_S.gguf) \| IQ3_S \| 0.4 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.IQ3_XS.gguf) \| IQ3_XS \| 0.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.Q2_K.gguf) \| Q2_K \| 0.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.IQ3_M.gguf) \| IQ3_M \| 0.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.IQ4_XS.gguf) \| IQ4_XS \| 0.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.Q3_K_M.gguf) \| Q3_K_M \| 0.5 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.Q3_K_L.gguf) \| Q3_K_L \| 0.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.Q4_K_S.gguf) \| Q4_K_S \| 0.5 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.Q4_K_M.gguf) \| Q4_K_M \| 0.5 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.Q5_K_S.gguf) \| Q5_K_S \| 0.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.Q5_K_M.gguf) \| Q5_K_M \| 0.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.Q6_K.gguf) \| Q6_K \| 0.6 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.Q8_0.gguf) \| Q8_0 \| 0.6 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-Chat_DPO-GGUF/resolve/main/Qwen2-0.5B-Chat_DPO.f16.gguf) \| f16 \| 1.1 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
NasimB/cbt_guten_rarity_neg_log_rarity	NasimB	"2023-07-23T00:17:26Z"	5	0	transformers	[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2023-07-22T21:18:11Z"	--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: cbt_guten_rarity_neg_log_rarity results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # cbt_guten_rarity_neg_log_rarity This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.1146 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 6 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 6.3504 \| 0.29 \| 500 \| 5.3411 \| \| 5.0303 \| 0.58 \| 1000 \| 4.9289 \| \| 4.7121 \| 0.87 \| 1500 \| 4.6855 \| \| 4.4511 \| 1.17 \| 2000 \| 4.5476 \| \| 4.3014 \| 1.46 \| 2500 \| 4.4314 \| \| 4.1955 \| 1.75 \| 3000 \| 4.3328 \| \| 4.0822 \| 2.04 \| 3500 \| 4.2592 \| \| 3.9003 \| 2.33 \| 4000 \| 4.2114 \| \| 3.8655 \| 2.62 \| 4500 \| 4.1524 \| \| 3.8301 \| 2.91 \| 5000 \| 4.1064 \| \| 3.6497 \| 3.21 \| 5500 \| 4.1041 \| \| 3.5826 \| 3.5 \| 6000 \| 4.0754 \| \| 3.5724 \| 3.79 \| 6500 \| 4.0452 \| \| 3.494 \| 4.08 \| 7000 \| 4.0400 \| \| 3.32 \| 4.37 \| 7500 \| 4.0387 \| \| 3.3162 \| 4.66 \| 8000 \| 4.0236 \| \| 3.308 \| 4.95 \| 8500 \| 4.0116 \| \| 3.1671 \| 5.24 \| 9000 \| 4.0252 \| \| 3.1406 \| 5.54 \| 9500 \| 4.0223 \| \| 3.1323 \| 5.83 \| 10000 \| 4.0221 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3
tomaszki/gemma-11	tomaszki	"2024-02-29T09:02:13Z"	114	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-02-29T08:55:16Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
jobeid1/Reinforce-pixel-copter	jobeid1	"2023-06-12T19:10:13Z"	0	0	null	[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	"2023-06-05T23:02:09Z"	--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-pixel-copter results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 53.20 +/- 26.04 name: mean_reward verified: false --- # Reinforce Agent playing Pixelcopter-PLE-v0 This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
kisejin/absa_step2	kisejin	"2024-05-23T10:58:38Z"	111	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	"2024-05-20T10:15:41Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
mradermacher/indo-gemma-2b-alpaca-GGUF	mradermacher	"2025-01-06T04:15:37Z"	23	0	transformers	[ "transformers", "gguf", "text-generation-inference", "unsloth", "gemma", "trl", "en", "base_model:firqaaa/indo-gemma-2b-alpaca", "base_model:quantized:firqaaa/indo-gemma-2b-alpaca", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	"2025-01-06T03:55:46Z"	--- base_model: firqaaa/indo-gemma-2b-alpaca language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - text-generation-inference - transformers - unsloth - gemma - trl --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/firqaaa/indo-gemma-2b-alpaca <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/indo-gemma-2b-alpaca-GGUF/resolve/main/indo-gemma-2b-alpaca.Q2_K.gguf) \| Q2_K \| 1.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/indo-gemma-2b-alpaca-GGUF/resolve/main/indo-gemma-2b-alpaca.Q3_K_S.gguf) \| Q3_K_S \| 1.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/indo-gemma-2b-alpaca-GGUF/resolve/main/indo-gemma-2b-alpaca.Q3_K_M.gguf) \| Q3_K_M \| 1.5 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/indo-gemma-2b-alpaca-GGUF/resolve/main/indo-gemma-2b-alpaca.Q3_K_L.gguf) \| Q3_K_L \| 1.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/indo-gemma-2b-alpaca-GGUF/resolve/main/indo-gemma-2b-alpaca.IQ4_XS.gguf) \| IQ4_XS \| 1.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/indo-gemma-2b-alpaca-GGUF/resolve/main/indo-gemma-2b-alpaca.Q4_K_S.gguf) \| Q4_K_S \| 1.7 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/indo-gemma-2b-alpaca-GGUF/resolve/main/indo-gemma-2b-alpaca.Q4_K_M.gguf) \| Q4_K_M \| 1.7 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/indo-gemma-2b-alpaca-GGUF/resolve/main/indo-gemma-2b-alpaca.Q5_K_S.gguf) \| Q5_K_S \| 1.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/indo-gemma-2b-alpaca-GGUF/resolve/main/indo-gemma-2b-alpaca.Q5_K_M.gguf) \| Q5_K_M \| 1.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/indo-gemma-2b-alpaca-GGUF/resolve/main/indo-gemma-2b-alpaca.Q6_K.gguf) \| Q6_K \| 2.2 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/indo-gemma-2b-alpaca-GGUF/resolve/main/indo-gemma-2b-alpaca.Q8_0.gguf) \| Q8_0 \| 2.8 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/indo-gemma-2b-alpaca-GGUF/resolve/main/indo-gemma-2b-alpaca.f16.gguf) \| f16 \| 5.1 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
facebook/mms-tts-mib	facebook	"2023-09-01T16:33:00Z"	107	0	transformers	[ "transformers", "pytorch", "safetensors", "vits", "text-to-audio", "mms", "text-to-speech", "arxiv:2305.13516", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]	text-to-speech	"2023-09-01T16:32:44Z"	--- license: cc-by-nc-4.0 tags: - mms - vits pipeline_tag: text-to-speech --- # Massively Multilingual Speech (MMS): Mixtec, Atatlahuca Text-to-Speech This repository contains the Mixtec, Atatlahuca (mib) language text-to-speech (TTS) model checkpoint. This model is part of Facebook's [Massively Multilingual Speech](https://arxiv.org/abs/2305.13516) project, aiming to provide speech technology across a diverse range of languages. You can find more details about the supported languages and their ISO 639-3 codes in the [MMS Language Coverage Overview](https://dl.fbaipublicfiles.com/mms/misc/language_coverage_mms.html), and see all MMS-TTS checkpoints on the Hugging Face Hub: [facebook/mms-tts](https://huggingface.co/models?sort=trending&search=facebook%2Fmms-tts). MMS-TTS is available in the 🤗 Transformers library from version 4.33 onwards. ## Model Details VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a speech waveform conditional on an input text sequence. It is a conditional variational autoencoder (VAE) comprised of a posterior encoder, decoder, and conditional prior. A set of spectrogram-based acoustic features are predicted by the flow-based module, which is formed of a Transformer-based text encoder and multiple coupling layers. The spectrogram is decoded using a stack of transposed convolutional layers, much in the same style as the HiFi-GAN vocoder. Motivated by the one-to-many nature of the TTS problem, where the same text input can be spoken in multiple ways, the model also includes a stochastic duration predictor, which allows the model to synthesise speech with different rhythms from the same input text. The model is trained end-to-end with a combination of losses derived from variational lower bound and adversarial training. To improve the expressiveness of the model, normalizing flows are applied to the conditional prior distribution. During inference, the text encodings are up-sampled based on the duration prediction module, and then mapped into the waveform using a cascade of the flow module and HiFi-GAN decoder. Due to the stochastic nature of the duration predictor, the model is non-deterministic, and thus requires a fixed seed to generate the same speech waveform. For the MMS project, a separate VITS checkpoint is trained on each langauge. ## Usage MMS-TTS is available in the 🤗 Transformers library from version 4.33 onwards. To use this checkpoint, first install the latest version of the library: ``` pip install --upgrade transformers accelerate ``` Then, run inference with the following code-snippet: ```python from transformers import VitsModel, AutoTokenizer import torch model = VitsModel.from_pretrained("facebook/mms-tts-mib") tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-mib") text = "some example text in the Mixtec, Atatlahuca language" inputs = tokenizer(text, return_tensors="pt") with torch.no_grad(): output = model(inputs).waveform ``` The resulting waveform can be saved as a `.wav` file: ```python import scipy scipy.io.wavfile.write("techno.wav", rate=model.config.sampling_rate, data=output) ``` Or displayed in a Jupyter Notebook / Google Colab: ```python from IPython.display import Audio Audio(output, rate=model.config.sampling_rate) ``` ## BibTex citation This model was developed by Vineel Pratap et al. from Meta AI. If you use the model, consider citing the MMS paper: ``` @article{pratap2023mms, title={Scaling Speech Technology to 1,000+ Languages}, author={Vineel Pratap and Andros Tjandra and Bowen Shi and Paden Tomasello and Arun Babu and Sayani Kundu and Ali Elkahky and Zhaoheng Ni and Apoorv Vyas and Maryam Fazel-Zarandi and Alexei Baevski and Yossi Adi and Xiaohui Zhang and Wei-Ning Hsu and Alexis Conneau and Michael Auli}, journal={arXiv}, year={2023} } ``` ## License The model is licensed as CC-BY-NC 4.0**.
dickheim/Gemma-2-9b-it-outcomes-F16-GGUF	dickheim	"2024-12-05T02:06:42Z"	10	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-lora", "base_model:dickheim/Gemma-2-9b-it-outcomes_orig", "base_model:quantized:dickheim/Gemma-2-9b-it-outcomes_orig", "endpoints_compatible", "region:us" ]	null	"2024-12-05T02:06:40Z"	--- library_name: transformers tags: - llama-cpp - gguf-my-lora base_model: dickheim/Gemma-2-9b-it-outcomes --- # dickheim/Gemma-2-9b-it-outcomes-F16-GGUF This LoRA adapter was converted to GGUF format from [`dickheim/Gemma-2-9b-it-outcomes`](https://huggingface.co/dickheim/Gemma-2-9b-it-outcomes) via the ggml.ai's [GGUF-my-lora](https://huggingface.co/spaces/ggml-org/gguf-my-lora) space. Refer to the [original adapter repository](https://huggingface.co/dickheim/Gemma-2-9b-it-outcomes) for more details. ## Use with llama.cpp ```bash # with cli llama-cli -m base_model.gguf --lora Gemma-2-9b-it-outcomes-f16.gguf (...other args) # with server llama-server -m base_model.gguf --lora Gemma-2-9b-it-outcomes-f16.gguf (...other args) ``` To know more about LoRA usage with llama.cpp server, refer to the [llama.cpp server documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/server/README.md).
Keltezaa/britney-spears-flux-model	Keltezaa	"2024-10-25T10:33:23Z"	67	0	diffusers	[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "migrated", "photorealistic", "celebrity", "britney spears", "flux1.d", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	"2024-10-25T10:15:03Z"	--- license: other license_name: bespoke-lora-trained-license license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True tags: - text-to-image - stable-diffusion - lora - diffusers - template:sd-lora - migrated - photorealistic - celebrity - britney spears - flux1.d base_model: black-forest-labs/FLUX.1-dev instance_prompt: britney widget: - text: ' ' output: url: >- 32347562.jpeg - text: ' ' output: url: >- 32948418.jpeg - text: ' ' output: url: >- 35870187.jpeg - text: ' ' output: url: >- 32349015.jpeg - text: ' ' output: url: >- 32347485.jpeg --- # Britney Spears Flux Model <Gallery /> ([CivitAI](https://civitai.com/models/)) ## Model description <p>Britney Jean Spears, born December 2, 1981, in McComb, MS, is an American recording artist and entertainer. Oft referred to as the "Princess of Pop,” she is credited with the revival of pop music during the late 1990s and early 2000s, and is recognized as an icon. Spears has sold an estimated 150 million records worldwide, making her one of the world's best-selling music artists. She ranks as the best-selling female albums artist of the 2000s, the eighth-biggest artist overall of the 2000s, and the fourth best-selling female albums artist and tenth best-selling digital artist in history. Spears has earned countless awards and accolades, including a Grammy Award, 15 Guinness World Records, Billboard’s Millennium Award, GLAAD’s Vanguard Award, the inaugural Radio Disney Icon Award, MTV’s Michael Jackson Video Vanguard Award, and a star on the Hollywood Walk of Fame. In 2020, Rolling Stone named her song “…Baby One More Time” the best debut single of all time. Time selected Spears as one of its 100 Most Influential People in 2021. </p><p></p><p>Spears made her local stage debut at age 5, singing “What Child Is This?” at her kindergarten graduation. Throughout her childhood, Spears took voice, dance, and gymnastic lessons, while competing in pageants and talent shows. For a short time, before turning her focus to music and dance, she trained with famed Olympics gymnastics coach Bela Karolyi. In 1993, Spears was cast on Disney's “The New Mickey Mouse Club," alongside other future stars like Christina Aguilera, Justin Timberlake, Ryan Gosling, and Keri Russell. She remained on the series until its cancellation two years later. Spears signed a record deal with Jive Records in 1997, when she was 15. Her first single, “…Baby One More Time,” was released in October 1998. Buoyed by its controversial music video, the song reached No. 1 in 23 countries, propelling Spears to international superstardom and ushering in a new era of pop music. Spears’ debut studio album, also titled “…Baby One More Time," arrived in January 1999. It debuted at No. 1 in the US, making Spears the first artist in history to have both the No. 1 song and album in the same week. In total, "...Baby One More Time" sold over 25 million copies worldwide.</p><p></p><p>Spears' sophomore album, "Oops!... I Did It Again" (2000), sold 1.3 million copies in its first week alone and held the record for the fastest-selling album by a female artist in the US for 15 years. Spears adopted a more mature sound and style for her third and fourth albums, 2001's "Britney" and 2003's "In the Zone." Despite backlash over Spears’ increasingly provocative image, both albums sold over 10 million copies worldwide.</p><p></p><p>Spears made her big-screen debut in the motion picture “Crossroads" (2002), written by Shonda Rhimes and co-starring Dan Ackroyd, Kim Cattrall, Zoe Saldana, and Taryn Manning. She has also guest-starred on “Glee,” “How I Met Your Mother,” “Will & Grace,” “Sabrina, the Teenage Witch,” and “Jane the Virgin,” and has twice hosted “Saturday Night Live” and appeared as musical guest three times. </p><p></p><p>In 2004, Spears partnered with Elizabeth Arden to launch her first perfume, Curious. Spears currently has over 30 fragrances to her name, available in 85 countries, with sales exceeding $1.5 billion.</p><p></p><p>Spears served as executive producer of her fifth studio album, “Blackout" (2007). Though it initially received lukewarm reviews, “Blackout” has since been recognized as one of the most influential albums of its time. In 2008, after a bout of personal struggles that were breathlessly documented by the media, Spears was placed in a conservatorship that stripped her of all personal autonomy and put her estranged father in control of her person and estate. (The conservatorship remained in place until November 2021. Spears has described the abuse, isolation, and forced labor that she endured while under her father’s control.) Soon after the conservatorship was implemented, Spears returned to work, releasing the chart-topping albums “Circus” (2008) and “Femme Fatale” (2011), both of which were supported by extensive worldwide concert tours.</p><p></p><p>In 2012, Spears appeared as a judge on "X-Factor USA," becoming, at the time, the highest-paid reality TV judge in history. That same year, Spears was featured on <a target="_blank" rel="ugc" href="http://will.i.am">will.i.am</a>'s single “Scream & Shout." Recpetion to the song was mixed, but it peaked at No. 3 on the Hot 100 and became the very first No. 1 on Billboard's new Dance/Electronic Songs chart. <a target="_blank" rel="ugc" href="http://will.i.am">will.i.am</a> later executive-produced Spears’ eighth studio album, “Britney Jean" (2013). In December 2013, Spears began a Las Vegas concert residency, “Britney: Piece of Me,” at Planet Hollywood Resort & Casino. The show was initially scheduled to run for two years, but was extended several times due to its enduring popularity. It ultimately concluded in December 2017. Spears and her residency revitalized the Vegas strip, and the show won numerous awards during its run, including Best Show in Vegas and Best Bachelorette Show in Vegas. In 2015, Spears released the single “Pretty Girls,” featuring Iggy Azalea, and contributed vocals to Giorgio Moroder's “Tom’s Diner.” Reportedly, Spears approached Moroder to collaborate on the song. Spears’ ninth studio album, “Glory,” arrived in August 2016, preceded by the Top 20 hit "Make Me..." with G-Eazy. Spears later took her Vegas show on the road throughout 2017 and 2018, with dates in some counties that she had never toured previously. "Glory" was re-released in 2020 with updated cover art and additional songs following a successful fan campaign to push “Mood Ring” - originally a Japan-only bonus track - to No. 1 on iTunes.</p><p></p><p>Spears teamed up with Elton John in 2022 to release the single "Hold Me Closer," which debuted at No. 6 on the Hot 100 and became Spears’ highest-charting single in a decade. Also in 2022, publishing house Simon & Schuster signed Spears to a book deal worth a staggering $15 million. Spears’ hotly-anticipated memoir, “The Woman in Me,” hit shelves in October 2023. In its first week, it sold 1.1 million copies in the US and 2.4 million copies worldwide, immediately becoming a New York Times #1 bestseller, as well as the fastest-selling title in Simon & Schuster’s history. A film adaptation of Spears’ memoir, to be directed by Jon Chu, was announced in 2024.</p><p></p><p>After reports surfaced that Spears was working on a new album, she clarified via Instagram that she currently has no plans to return to the music industry. </p> ## Trigger words You should use `britney` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/Keltezaa/britney-spears-flux-model/tree/main) them in the Files & versions tab. ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch device = "cuda" if torch.cuda.is_available() else "cpu" pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device) pipeline.load_lora_weights('Keltezaa/britney-spears-flux-model', weight_name='lora.safetensors') image = pipeline('`britney`').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
bartowski/Rhea-72b-v0.5-GGUF-broken	bartowski	"2024-03-26T08:35:47Z"	111	2	transformers	[ "transformers", "gguf", "text-generation", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	text-generation	"2024-03-26T05:00:38Z"	--- library_name: transformers license: apache-2.0 language: - en quantized_by: bartowski pipeline_tag: text-generation --- ## Llamacpp Quantizations of Rhea-72b-v0.5 Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2440">b2440</a> for quantization. Original model: https://huggingface.co/davidkim205/Rhea-72b-v0.5 Download a file (not the whole branch) from below: \| Filename \| Quant type \| File Size \| Description \| \| -------- \| ---------- \| --------- \| ----------- \| \| [Rhea-72b-v0.5-Q8_0.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/tree/main/Rhea-72b-v0.5-Q8_0.gguf) \| Q8_0 \| 76.82GB \| Extremely high quality, generally unneeded but max available quant. \| \| [Rhea-72b-v0.5-Q6_K.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/tree/main/Rhea-72b-v0.5-Q6_K.gguf) \| Q6_K \| 59.31GB \| Very high quality, near perfect, recommended. \| \| [Rhea-72b-v0.5-Q5_K_M.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/tree/main/Rhea-72b-v0.5-Q5_K_M.gguf) \| Q5_K_M \| 51.30GB \| High quality, very usable. \| \| [Rhea-72b-v0.5-Q5_K_S.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-Q5_K_S.gguf) \| Q5_K_S \| 49.88GB \| High quality, very usable. \| \| [Rhea-72b-v0.5-Q5_0.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-Q5_0.gguf) \| Q5_0 \| 49.88GB \| High quality, older format, generally not recommended. \| \| [Rhea-72b-v0.5-Q4_K_M.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-Q4_K_M.gguf) \| Q4_K_M \| 43.76GB \| Good quality, similar to 4.25 bpw. \| \| [Rhea-72b-v0.5-Q4_K_S.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-Q4_K_S.gguf) \| Q4_K_S \| 41.28GB \| Slightly lower quality with small space savings. \| \| [Rhea-72b-v0.5-IQ4_NL.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-IQ4_NL.gguf) \| IQ4_NL \| 41.25GB \| Good quality, similar to Q4_K_S, new method of quanting, \| \| [Rhea-72b-v0.5-IQ4_XS.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-IQ4_XS.gguf) \| IQ4_XS \| 39.09GB \| Decent quality, new method with similar performance to Q4. \| \| [Rhea-72b-v0.5-Q4_0.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-Q4_0.gguf) \| Q4_0 \| 41.00GB \| Decent quality, older format, generally not recommended. \| \| [Rhea-72b-v0.5-IQ3_M.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-IQ3_M.gguf) \| IQ3_M \| 33.25GB \| Medium-low quality, new method with decent performance. \| \| [Rhea-72b-v0.5-IQ3_S.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-IQ3_S.gguf) \| IQ3_S \| 31.56GB \| Lower quality, new method with decent performance, recommended over Q3 quants. \| \| [Rhea-72b-v0.5-Q3_K_L.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-Q3_K_L.gguf) \| Q3_K_L \| 38.48GB \| Lower quality but usable, good for low RAM availability. \| \| [Rhea-72b-v0.5-Q3_K_M.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-Q3_K_M.gguf) \| Q3_K_M \| 35.27GB \| Even lower quality. \| \| [Rhea-72b-v0.5-Q3_K_S.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-Q3_K_S.gguf) \| Q3_K_S \| 31.56GB \| Low quality, not recommended. \| \| [Rhea-72b-v0.5-Q2_K.gguf](https://huggingface.co/bartowski/Rhea-72b-v0.5-GGUF/blob/main/Rhea-72b-v0.5-Q2_K.gguf) \| Q2_K \| 27.07GB \| Extremely low quality, not recommended. Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF	MaziyarPanahi	"2024-01-26T06:35:03Z"	118	1	transformers	[ "transformers", "gguf", "mistral", "quantized", "2-bit", "3-bit", "4-bit", "5-bit", "6-bit", "8-bit", "GGUF", "safetensors", "text-generation", "merge", "mergekit", "7b", "lazymergekit", "mistralai/Mistral-7B-Instruct-v0.2", "fblgit/una-cybertron-7b-v2-bf16", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us", "base_model:MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp", "base_model:quantized:MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp", "conversational" ]	text-generation	"2024-01-24T07:09:40Z"	--- license: apache-2.0 tags: - quantized - 2-bit - 3-bit - 4-bit - 5-bit - 6-bit - 8-bit - GGUF - transformers - safetensors - mistral - text-generation - merge - mergekit - 7b - lazymergekit - mistralai/Mistral-7B-Instruct-v0.2 - fblgit/una-cybertron-7b-v2-bf16 - license:apache-2.0 - autotrain_compatible - endpoints_compatible - text-generation-inference - region:us model_name: una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF base_model: MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp inference: false model_creator: MaziyarPanahi pipeline_tag: text-generation quantized_by: MaziyarPanahi --- # [MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF](https://huggingface.co/MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF) - Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi) - Original model: [MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp](https://huggingface.co/MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp) ## Description [MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF](https://huggingface.co/MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF) contains GGUF format model files for [MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp](https://huggingface.co/MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp). ## How to use Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models: ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. ### Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw ## How to download GGUF files Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: [MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF](https://huggingface.co/MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF) and below it, a specific filename to download, such as: una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF.Q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` </details> <details> <summary>More advanced huggingface-cli download usage (click to read)</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download [MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF](https://huggingface.co/MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF) --local-dir . --local-dir-use-symlinks False --include='Q4_Kgguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 35 -m una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/). #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path="./una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF.Q4_K_M.gguf", # Download the model file first n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( "<\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant", # Prompt max_tokens=512, # Generate up to 512 tokens stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path="./una-cybertron-7b-v2-bf16-Mistral-7B-Instruct-v0.2-slerp-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] ) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
Best000/8af071e0-359b-463e-ac5f-f45207e2120f	Best000	"2025-02-04T17:33:39Z"	10	0	peft	[ "peft", "safetensors", "qwen2", "axolotl", "generated_from_trainer", "base_model:unsloth/Qwen2.5-14B", "base_model:adapter:unsloth/Qwen2.5-14B", "license:apache-2.0", "region:us" ]	null	"2025-02-04T16:54:51Z"	--- library_name: peft license: apache-2.0 base_model: unsloth/Qwen2.5-14B tags: - axolotl - generated_from_trainer model-index: - name: 8af071e0-359b-463e-ac5f-f45207e2120f results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) # 8af071e0-359b-463e-ac5f-f45207e2120f This model is a fine-tuned version of [unsloth/Qwen2.5-14B](https://huggingface.co/unsloth/Qwen2.5-14B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.2550 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
friendshipkim/Llama-3.1-8B-pruned-h0.5-i0.5-a0.0-d0.0	friendshipkim	"2024-12-04T02:30:35Z"	5	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-12-04T01:12:42Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
KimRina/Ko-BioMistral-7B-slerp	KimRina	"2024-05-30T10:01:57Z"	10	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "conversational", "base_model:BioMistral/BioMistral-7B", "base_model:merge:BioMistral/BioMistral-7B", "base_model:davidkim205/komt-mistral-7b-v1", "base_model:merge:davidkim205/komt-mistral-7b-v1", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-05-30T09:40:55Z"	--- base_model: - BioMistral/BioMistral-7B - davidkim205/komt-mistral-7b-v1 library_name: transformers tags: - mergekit - merge --- # output_folder This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the SLERP merge method. ### Models Merged The following models were included in the merge: * [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B) * [davidkim205/komt-mistral-7b-v1](https://huggingface.co/davidkim205/komt-mistral-7b-v1) ### Configuration The following YAML configuration was used to produce this model: ```yaml slices: - sources: - model: davidkim205/komt-mistral-7b-v1 layer_range: - 0 - 32 - model: BioMistral/BioMistral-7B layer_range: - 0 - 32 merge_method: slerp base_model: davidkim205/komt-mistral-7b-v1 parameters: t: - filter: self_attn value: - 0 - 0.5 - 0.3 - 0.7 - 1 - filter: mlp value: - 1 - 0.5 - 0.7 - 0.3 - 0 - value: 0.5 dtype: bfloat16 ```
B0yc4kra/emotion_finetuned_model	B0yc4kra	"2023-09-18T08:04:47Z"	220	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:google/vit-base-patch16-224-in21k", "base_model:finetune:google/vit-base-patch16-224-in21k", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	"2023-09-17T11:09:56Z"	--- license: apache-2.0 base_model: google/vit-base-patch16-224-in21k tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: emotion_finetuned_model results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: en-US split: train args: en-US metrics: - name: Accuracy type: accuracy value: 0.5 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # emotion_finetuned_model This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 1.3507 - Accuracy: 0.5 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 20 \| 1.6393 \| 0.4875 \| \| No log \| 2.0 \| 40 \| 1.5461 \| 0.4875 \| \| No log \| 3.0 \| 60 \| 1.4809 \| 0.4938 \| \| No log \| 4.0 \| 80 \| 1.4289 \| 0.4813 \| \| No log \| 5.0 \| 100 \| 1.3878 \| 0.4875 \| \| No log \| 6.0 \| 120 \| 1.3792 \| 0.4813 \| \| No log \| 7.0 \| 140 \| 1.3507 \| 0.5 \| \| No log \| 8.0 \| 160 \| 1.3376 \| 0.4938 \| \| No log \| 9.0 \| 180 \| 1.3379 \| 0.4875 \| \| No log \| 10.0 \| 200 \| 1.3305 \| 0.5 \| ### Framework versions - Transformers 4.33.2 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
ketchup123/qwen-2-7b-instruct-safety-100-HF	ketchup123	"2025-01-29T10:25:48Z"	107	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:Qwen/Qwen2-7B-Instruct", "base_model:adapter:Qwen/Qwen2-7B-Instruct", "license:apache-2.0", "region:us" ]	null	"2025-01-29T10:25:10Z"	--- library_name: peft license: apache-2.0 base_model: Qwen/Qwen2-7B-Instruct tags: - trl - sft - generated_from_trainer model-index: - name: qwen-2-7b-instruct-safety-100-HF results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # qwen-2-7b-instruct-safety-100-HF This model is a fine-tuned version of [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 4 - eval_batch_size: 8 - seed: 3407 - distributed_type: multi-GPU - num_devices: 8 - total_train_batch_size: 32 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results ### Framework versions - PEFT 0.14.0 - Transformers 4.45.2 - Pytorch 2.4.1+cu121 - Datasets 3.1.0 - Tokenizers 0.20.3
snowian/ImageNet_32_btViT_256_4_86	snowian	"2025-01-03T03:23:33Z"	5	0	null	[ "safetensors", "model_hub_mixin", "pytorch_model_hub_mixin", "region:us" ]	null	"2025-01-03T03:23:29Z"	--- tags: - model_hub_mixin - pytorch_model_hub_mixin --- This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration: - Library: [More Information Needed] - Docs: [More Information Needed]
SidXXD/dog5	SidXXD	"2023-12-06T16:41:20Z"	0	0	diffusers	[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "custom-diffusion", "base_model:CompVis/stable-diffusion-v1-4", "base_model:adapter:CompVis/stable-diffusion-v1-4", "license:creativeml-openrail-m", "region:us" ]	text-to-image	"2023-12-06T16:37:39Z"	--- license: creativeml-openrail-m base_model: CompVis/stable-diffusion-v1-4 instance_prompt: photo of a <new1> dog tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - custom-diffusion inference: true --- # Custom Diffusion - SidXXD/dog5 These are Custom Diffusion adaption weights for CompVis/stable-diffusion-v1-4. The weights were trained on photo of a <new1> dog using [Custom Diffusion](https://www.cs.cmu.edu/~custom-diffusion). You can find some example images in the following. For more details on the training, please follow [this link](https://github.com/huggingface/diffusers/blob/main/examples/custom_diffusion).
huggingtweets/nomia2011	huggingtweets	"2022-08-16T01:53:02Z"	105	0	transformers	[ "transformers", "pytorch", "gpt2", "text-generation", "huggingtweets", "en", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2022-08-16T01:51:39Z"	--- language: en thumbnail: http://www.huggingtweets.com/nomia2011/1660614778038/predictions.png tags: - huggingtweets widget: - text: "My dream is" --- <div class="inline-flex flex-col" style="line-height: 1.5;"> <div class="flex"> <div style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1403256770848505857/cE9TrrfP_400x400.jpg')"> </div> <div style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')"> </div> <div style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')"> </div> </div> <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div> <div style="text-align: center; font-size: 16px; font-weight: 800">نومیا</div> <div style="text-align: center; font-size: 14px;">@nomia2011</div> </div> I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets). Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)! ## How does it work? The model uses the following pipeline. ![pipeline](https://github.com/borisdayma/huggingtweets/blob/master/img/pipeline.png?raw=true) To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI). ## Training data The model was trained on tweets from نومیا. \| Data \| نومیا \| \| --- \| --- \| \| Tweets downloaded \| 3246 \| \| Retweets \| 51 \| \| Short tweets \| 565 \| \| Tweets kept \| 2630 \| [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/18at4zay/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline. ## Training procedure The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @nomia2011's tweets. Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1gvcfr4e) for full transparency and reproducibility. At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1gvcfr4e/artifacts) is logged and versioned. ## How to use You can use this model directly with a pipeline for text generation: ```python from transformers import pipeline generator = pipeline('text-generation', model='huggingtweets/nomia2011') generator("My dream is", num_return_sequences=5) ``` ## Limitations and bias The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias). In addition, the data present in the user's tweets further affects the text generated by the model. ## About Built by Boris Dayma [![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/intent/follow?screen_name=borisdayma) For more details, visit the project repository. [![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)
LHRuig/rodrigofriasx	LHRuig	"2025-03-25T09:09:46Z"	0	0	diffusers	[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "region:us" ]	text-to-image	"2025-03-25T09:09:20Z"	--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - text: suit output: url: images/suit.jpg base_model: black-forest-labs/FLUX.1-dev instance_prompt: rodrigofriasx --- # rodrigofriasx <Gallery /> ## Model description rodrigofriasx lora ## Trigger words You should use `rodrigofriasx` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/LHRuig/rodrigofriasx/tree/main) them in the Files & versions tab.
deepanshu30699/wizard-python-financial_6_gptq	deepanshu30699	"2023-10-04T13:19:16Z"	6	0	peft	[ "peft", "pytorch", "llama", "region:us" ]	null	"2023-10-04T07:45:07Z"	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: gptq - bits: 4 - tokenizer: None - dataset: None - group_size: 128 - damp_percent: 0.1 - desc_act: False - sym: True - true_sequential: True - use_cuda_fp16: False - model_seqlen: None - block_name_to_quantize: None - module_name_preceding_first_block: None - batch_size: 1 - pad_token_id: None - disable_exllama: True - max_input_length: None ### Framework versions - PEFT 0.5.0
ICEPVP8977/Uncensored_DeepSeek-R1-Distill-Qwen-1.5B	ICEPVP8977	"2025-03-02T17:43:15Z"	2	0	null	[ "gguf", "en", "dataset:ICEPVP8977/Uncensored_Tiny_Test_Time_Compute", "base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", "base_model:quantized:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", "endpoints_compatible", "region:us", "conversational" ]	null	"2025-03-01T20:58:22Z"	--- datasets: - ICEPVP8977/Uncensored_Tiny_Test_Time_Compute language: - en base_model: - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B --- # This model was fine-tuned on only 941 examples. As such, I guarantee nothing. ## Feel free to test it out and give me feedback if you want.
Solovo/AnyHTrain	Solovo	"2023-03-04T19:15:08Z"	0	0	null	[ "art", "en", "arxiv:1910.09700", "doi:10.57967/hf/0427", "license:other", "region:us" ]	null	"2023-03-04T18:39:02Z"	--- license: other language: - en tags: - art --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ### How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Lendobo/ddpm-celebahq-finetuned-butterflies-2epochs	Lendobo	"2025-02-11T13:21:23Z"	0	0	diffusers	[ "diffusers", "safetensors", "pytorch", "unconditional-image-generation", "diffusion-models-class", "license:mit", "diffusers:DDPMPipeline", "region:us" ]	unconditional-image-generation	"2025-02-11T13:20:51Z"	--- license: mit tags: - pytorch - diffusers - unconditional-image-generation - diffusion-models-class --- # Example Fine-Tuned Model for Unit 2 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class) Describe your model here ## Usage ```python from diffusers import DDPMPipeline pipeline = DDPMPipeline.from_pretrained('Lendobo/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image ```
diRECT-Sophie-Rain-SpiderMan-Streaming/Sophie.Rain.Spider-Man.Video	diRECT-Sophie-Rain-SpiderMan-Streaming	"2025-03-11T23:16:52Z"	0	0	null	[ "region:us" ]	null	"2025-03-11T23:13:52Z"	2 minutes ago Sophie Rain SpiderMan Viral Video Full Original Video Viral On Social Media X TikTok Trending <a href="https://tv2online.com/Leaked/?v=Sophie+Rain+Spiderman" rel="nofollow">►►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► 𝙁𝙪𝙡𝙡 𝙑𝙞𝙙𝙚𝙤️</a></p> <a href="https://tv2online.com/Leaked/?v=Sophie+Rain+Spiderman" rel="nofollow">🔴►𝐂𝐋𝐈𝐂𝐊 𝐇𝐄𝐑𝐄 🌐==►► 𝐃𝐨𝐰𝐧𝐥𝐨𝐚𝐝 𝐍𝐨𝐰⬇️⬇️</a></p> <p><a rel="nofollow" title="WATCH NOW" href="https://tv2online.com/Leaked/?v=Sophie+Rain+Spiderman"><img border="Sophie+Rain+Spidermanno" height="480" width="720" title="WATCH NOW" alt="WATCH NOW" src="https://i.ibb.co.com/xMMVF88/686577567.gif"></a></p>
LHRuig/elelasx	LHRuig	"2025-03-06T20:33:14Z"	0	0	diffusers	[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "region:us" ]	text-to-image	"2025-03-06T20:32:55Z"	--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - text: suit output: url: images/suit.jpg base_model: black-forest-labs/FLUX.1-dev instance_prompt: elelasx --- # elelasx <Gallery /> ## Model description elelasx lora ## Trigger words You should use `elelasx` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/LHRuig/elelasx/tree/main) them in the Files & versions tab.
kangnlp/mistral-7b-qlora-alpaca-gpt4-sciq-plw0.1-target-QV-r8-v0.1	kangnlp	"2024-12-21T12:05:42Z"	125	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	"2024-12-21T11:56:53Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF	mradermacher	"2024-11-07T01:48:00Z"	278	0	transformers	[ "transformers", "gguf", "nm-vllm", "sparse", "en", "base_model:neuralmagic/Nous-Hermes-2-SOLAR-10.7B-pruned2.4", "base_model:quantized:neuralmagic/Nous-Hermes-2-SOLAR-10.7B-pruned2.4", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	"2024-11-06T06:16:51Z"	--- base_model: neuralmagic/Nous-Hermes-2-SOLAR-10.7B-pruned2.4 language: - en library_name: transformers model_type: Llama quantized_by: mradermacher tags: - nm-vllm - sparse --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/neuralmagic/Nous-Hermes-2-SOLAR-10.7B-pruned2.4 <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-IQ1_S.gguf) \| i1-IQ1_S \| 2.5 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-IQ1_M.gguf) \| i1-IQ1_M \| 2.7 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 3.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-IQ2_S.gguf) \| i1-IQ2_S \| 3.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-IQ2_M.gguf) \| i1-IQ2_M \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q2_K.gguf) \| i1-Q2_K \| 4.1 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 4.3 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 4.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 4.8 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-IQ3_S.gguf) \| i1-IQ3_S \| 4.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-IQ3_M.gguf) \| i1-IQ3_M \| 4.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 5.3 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 5.8 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 5.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q4_0_4_4.gguf) \| i1-Q4_0_4_4 \| 6.2 \| fast on arm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q4_0_4_8.gguf) \| i1-Q4_0_4_8 \| 6.2 \| fast on arm+i8mm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q4_0_8_8.gguf) \| i1-Q4_0_8_8 \| 6.2 \| fast on arm+sve, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q4_0.gguf) \| i1-Q4_0 \| 6.2 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 6.2 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 6.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 7.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 7.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-SOLAR-10.7B-pruned2.4-i1-GGUF/resolve/main/Nous-Hermes-2-SOLAR-10.7B-pruned2.4.i1-Q6_K.gguf) \| i1-Q6_K \| 8.9 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
chainup244/Qwen-Qwen1.5-0.5B-1717467816	chainup244	"2024-06-04T02:24:08Z"	139	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	"2024-06-04T02:23:37Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
espressor/meta-llama.Llama-3.2-1B-Instruct_W8A8_FP8	espressor	"2024-11-28T13:22:20Z"	76	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "dataset:HuggingFaceH4/ultrachat_200k", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:quantized:meta-llama/Llama-3.2-1B-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "compressed-tensors", "region:us" ]	text-generation	"2024-11-28T13:20:55Z"	--- datasets: - HuggingFaceH4/ultrachat_200k base_model: - meta-llama/Llama-3.2-1B-Instruct library_name: transformers --- ## meta-llama/Llama-3.2-1B-Instruct - W8A8_FP8 Compression This is a compressed model using [llmcompressor](https://github.com/vllm-project/llm-compressor). ## Compression Configuration - Base Model: meta-llama/Llama-3.2-1B-Instruct - Compression Scheme: W8A8_FP8 - Dataset: HuggingFaceH4/ultrachat_200k - Dataset Split: train_sft - Number of Samples: 512 - Preprocessor: chat - Maximum Sequence Length: 131072 ## Sample Output #### Prompt: ``` <\|begin_of_text\|><\|start_header_id\|>system<\|end_header_id\|> Cutting Knowledge Date: December 2023 Today Date: 28 Nov 2024 <\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> Who is Alan Turing?<\|eot_id\|> ``` #### Output: ``` <\|begin_of_text\|><\|begin_of_text\|><\|start_header_id\|>system<\|end_header_id\|> Cutting Knowledge Date: December 2023 Today Date: 28 Nov 2024 <\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> Who is Alan Turing?<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|> Alan Turing (1912-1954) was a British mathematician, computer scientist, logician, philosopher, and cryptanalyst who made groundbreaking contributions to the development of computer science, artificial intelligence, and cryptography. He is widely regarded as one of the most influential figures in the history of computer science. Early Life and Education: Alan Turing was born on June 23, 1912, in Maida Vale, London, to a family of intellectuals. His father, Frank Turing, was a bank manager, and his mother, Mary (née Guiness), was a homemaker. Turing was a brilliant ``` ## Evaluation <TODO>

Subsets and Splits