Upload NewForSequenceClassification

README.md

@@ -0,0 +1,199 @@
+---
+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]

config.json

@@ -0,0 +1,93 @@
+{
+  "_name_or_path": "Alibaba-NLP/gte-multilingual-base",
+  "architectures": [
+    "NewForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
+  "classifier_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "H\u00f4 h\u1ea5p - Ph\u1ed5i",
+    "1": "Chuy\u00ean khoa M\u1eaft",
+    "2": "B\u1ec7nh Vi\u00eam gan",
+    "3": "N\u1ed9i khoa",
+    "4": "Th\u1ea7n kinh",
+    "5": "Ti\u00eau ho\u00e1",
+    "6": "Tim m\u1ea1ch",
+    "7": "Th\u1eadn - Ti\u1ebft ni\u1ec7u",
+    "8": "Ti\u1ec3u \u0111\u01b0\u1eddng - N\u1ed9i ti\u1ebft",
+    "9": "C\u01a1 X\u01b0\u01a1ng Kh\u1edbp",
+    "10": "Tai M\u0169i H\u1ecdng",
+    "11": "Ch\u1ea5n th\u01b0\u01a1ng ch\u1ec9nh h\u00ecnh",
+    "12": "Ung b\u01b0\u1edbu",
+    "13": "Da li\u1ec5u",
+    "14": "Nha khoa",
+    "15": "Nam h\u1ecdc",
+    "16": "Ph\u1ee5c h\u1ed3i ch\u1ee9c n\u0103ng",
+    "17": "C\u1ed9t s\u1ed1ng",
+    "18": "Nhi khoa",
+    "19": "T\u1ea1o h\u00ecnh H\u00e0m M\u1eb7t",
+    "20": "Ngo\u1ea1i th\u1ea7n kinh",
+    "21": "Ph\u1eabu thu\u1eadt H\u1eadu m\u00f4n - Tr\u1ef1c tr\u00e0ng"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B\u1ec7nh Vi\u00eam gan": 2,
+    "Chuy\u00ean khoa M\u1eaft": 1,
+    "Ch\u1ea5n th\u01b0\u01a1ng ch\u1ec9nh h\u00ecnh": 11,
+    "C\u01a1 X\u01b0\u01a1ng Kh\u1edbp": 9,
+    "C\u1ed9t s\u1ed1ng": 17,
+    "Da li\u1ec5u": 13,
+    "H\u00f4 h\u1ea5p - Ph\u1ed5i": 0,
+    "Nam h\u1ecdc": 15,
+    "Ngo\u1ea1i th\u1ea7n kinh": 20,
+    "Nha khoa": 14,
+    "Nhi khoa": 18,
+    "N\u1ed9i khoa": 3,
+    "Ph\u1eabu thu\u1eadt H\u1eadu m\u00f4n - Tr\u1ef1c tr\u00e0ng": 21,
+    "Ph\u1ee5c h\u1ed3i ch\u1ee9c n\u0103ng": 16,
+    "Tai M\u0169i H\u1ecdng": 10,
+    "Th\u1ea7n kinh": 4,
+    "Th\u1eadn - Ti\u1ebft ni\u1ec7u": 7,
+    "Tim m\u1ea1ch": 6,
+    "Ti\u00eau ho\u00e1": 5,
+    "Ti\u1ec3u \u0111\u01b0\u1eddng - N\u1ed9i ti\u1ebft": 8,
+    "T\u1ea1o h\u00ecnh H\u00e0m M\u1eb7t": 19,
+    "Ung b\u01b0\u1edbu": 12
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pack_qkv": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "rope",
+  "problem_type": "single_label_classification",
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "ntk"
+  },
+  "rope_theta": 20000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 1,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 250048
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27bf27e473e71b0fc15a1d7709f1b81de069818393504a240ad176568017b090
+size 1223918808