|
--- |
|
tags: |
|
- mteb |
|
- sentence-transformers |
|
- transformers |
|
- Qwen2 |
|
- sentence-similarity |
|
- llama-cpp |
|
license: apache-2.0 |
|
--- |
|
## This version |
|
|
|
This model was converted from the 32-bit original safetensors format to a **16-bit GGUF format (`f16`)** from **[`Alibaba-NLP/gte-Qwen2-7B-instruct`](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct)** using `llama-quantize` built from [`llama.cpp`](https://github.com/ggerganov/llama.cpp). |
|
|
|
Custom conversion script settings: |
|
```json |
|
"gte-Qwen2-7B-instruct": { |
|
"model_name": "gte-Qwen2-7B-instruct", |
|
"hq_quant_type": "f16", |
|
"final_quant_type": "", |
|
"produce_final_quant": false, |
|
"parts_num": 4, |
|
"max_shard_size_gb": 4, |
|
"numexpr_max_thread": 8 |
|
} |
|
``` |
|
Please refer to the [original model card](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct) for more details on the unquantized model, including its metrics, which may be different (typically slightly worse) for this quantized version. |
|
|
|
|
|
## gte-Qwen2-7B-instruct |
|
|
|
**gte-Qwen2-7B-instruct** is the latest model in the gte (General Text Embedding) model family that ranks **No.1** in both English and Chinese evaluations on the Massive Text Embedding Benchmark [MTEB benchmark](https://huggingface.co/spaces/mteb/leaderboard) (as of June 16, 2024). |
|
|
|
Recently, the [**Qwen team**](https://huggingface.co/Qwen) released the Qwen2 series models, and we have trained the **gte-Qwen2-7B-instruct** model based on the [Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) LLM model. Compared to the [gte-Qwen1.5-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen1.5-7B-instruct) model, the **gte-Qwen2-7B-instruct** model uses the same training data and training strategies during the finetuning stage, with the only difference being the upgraded base model to Qwen2-7B. Considering the improvements in the Qwen2 series models compared to the Qwen1.5 series, we can also expect consistent performance enhancements in the embedding models. |
|
|
|
The model incorporates several key advancements: |
|
|
|
- Integration of bidirectional attention mechanisms, enriching its contextual understanding. |
|
- Instruction tuning, applied solely on the query side for streamlined efficiency |
|
- Comprehensive training across a vast, multilingual text corpus spanning diverse domains and scenarios. This training leverages both weakly supervised and supervised data, ensuring the model's applicability across numerous languages and a wide array of downstream tasks. |
|
|
|
|
|
## Model Information |
|
|
|
### Overview |
|
- Model Type: GTE (General Text Embeddings) |
|
- Model Size: 7B |
|
- Embedding Dimension: 3584 |
|
- Context Window: 131072 |
|
### Supported languages |
|
- North America: English |
|
- Western Europe: German, French, Spanish, Portuguese, Italian, Dutch |
|
- Eastern & Central Europe: Russian, Czech, Polish |
|
- Middle East: Arabic, Persian, Hebrew, Turkish |
|
- Eastern Asia: Chinese, Japanese, Korean |
|
- South-Eastern Asia: Vietnamese, Thai, Indonesian, Malay, Lao, Burmese, Cebuano, Khmer, Tagalog |
|
- Southern Asia: Hindi, Bengali, Urdu |
|
- [[source](https://qwenlm.github.io/blog/qwen2/)] |
|
### Details |
|
``` |
|
llama_model_loader: - kv 0: general.architecture str = qwen2 |
|
llama_model_loader: - kv 1: general.type str = model |
|
llama_model_loader: - kv 2: general.name str = gte-Qwen2-7B-instruct |
|
llama_model_loader: - kv 3: general.finetune str = instruct |
|
llama_model_loader: - kv 4: general.basename str = gte-Qwen2 |
|
llama_model_loader: - kv 5: general.size_label str = 7B |
|
llama_model_loader: - kv 6: general.license str = apache-2.0 |
|
llama_model_loader: - kv 7: general.tags arr[str,5] = ["mteb", "sentence-transformers", "tr... |
|
llama_model_loader: - kv 8: qwen2.block_count u32 = 28 |
|
llama_model_loader: - kv 9: qwen2.context_length u32 = 131072 |
|
llama_model_loader: - kv 10: qwen2.embedding_length u32 = 3584 |
|
llama_model_loader: - kv 11: qwen2.feed_forward_length u32 = 18944 |
|
llama_model_loader: - kv 12: qwen2.attention.head_count u32 = 28 |
|
llama_model_loader: - kv 13: qwen2.attention.head_count_kv u32 = 4 |
|
llama_model_loader: - kv 14: qwen2.rope.freq_base f32 = 1000000.000000 |
|
llama_model_loader: - kv 15: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 |
|
llama_model_loader: - kv 16: general.file_type u32 = 1 |
|
llama_model_loader: - kv 17: tokenizer.ggml.model str = gpt2 |
|
llama_model_loader: - kv 18: tokenizer.ggml.pre str = qwen2 |
|
llama_model_loader: - kv 19: tokenizer.ggml.tokens arr[str,151646] = ["!", "\"", "#", "$", "%", "&", "'", ... |
|
llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,151646] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... |
|
llama_model_loader: - kv 21: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... |
|
llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 151643 |
|
llama_model_loader: - kv 23: tokenizer.ggml.padding_token_id u32 = 151643 |
|
llama_model_loader: - kv 24: tokenizer.ggml.bos_token_id u32 = 151643 |
|
llama_model_loader: - kv 25: tokenizer.ggml.add_eos_token bool = true |
|
llama_model_loader: - kv 26: tokenizer.chat_template str = {% for message in messages %}{{'<|im_... |
|
llama_model_loader: - kv 27: general.quantization_version u32 = 2 |
|
llama_model_loader: - kv 28: split.no u16 = 0 |
|
llama_model_loader: - kv 29: split.count u16 = 4 |
|
llama_model_loader: - kv 30: split.tensors.count i32 = 339 |
|
llama_model_loader: - type f32: 141 tensors |
|
llama_model_loader: - type f16: 198 tensors |
|
llm_load_vocab: special tokens cache size = 3 |
|
llm_load_vocab: token to piece cache size = 0.9308 MB |
|
llm_load_print_meta: format = GGUF V3 (latest) |
|
llm_load_print_meta: arch = qwen2 |
|
llm_load_print_meta: vocab type = BPE |
|
llm_load_print_meta: n_vocab = 151646 |
|
llm_load_print_meta: n_merges = 151387 |
|
llm_load_print_meta: vocab_only = 0 |
|
llm_load_print_meta: n_ctx_train = 131072 |
|
llm_load_print_meta: n_embd = 3584 |
|
llm_load_print_meta: n_layer = 28 |
|
llm_load_print_meta: n_head = 28 |
|
llm_load_print_meta: n_head_kv = 4 |
|
llm_load_print_meta: n_rot = 128 |
|
llm_load_print_meta: n_swa = 0 |
|
llm_load_print_meta: n_embd_head_k = 128 |
|
llm_load_print_meta: n_embd_head_v = 128 |
|
llm_load_print_meta: n_gqa = 7 |
|
llm_load_print_meta: n_embd_k_gqa = 512 |
|
llm_load_print_meta: n_embd_v_gqa = 512 |
|
llm_load_print_meta: f_norm_eps = 0.0e+00 |
|
llm_load_print_meta: f_norm_rms_eps = 1.0e-06 |
|
llm_load_print_meta: f_clamp_kqv = 0.0e+00 |
|
llm_load_print_meta: f_max_alibi_bias = 0.0e+00 |
|
llm_load_print_meta: f_logit_scale = 0.0e+00 |
|
llm_load_print_meta: n_ff = 18944 |
|
llm_load_print_meta: n_expert = 0 |
|
llm_load_print_meta: n_expert_used = 0 |
|
llm_load_print_meta: causal attn = 1 |
|
llm_load_print_meta: pooling type = 0 |
|
llm_load_print_meta: rope type = 2 |
|
llm_load_print_meta: rope scaling = linear |
|
llm_load_print_meta: freq_base_train = 1000000.0 |
|
llm_load_print_meta: freq_scale_train = 1 |
|
llm_load_print_meta: n_ctx_orig_yarn = 131072 |
|
llm_load_print_meta: rope_finetuned = unknown |
|
llm_load_print_meta: ssm_d_conv = 0 |
|
llm_load_print_meta: ssm_d_inner = 0 |
|
llm_load_print_meta: ssm_d_state = 0 |
|
llm_load_print_meta: ssm_dt_rank = 0 |
|
llm_load_print_meta: ssm_dt_b_c_rms = 0 |
|
llm_load_print_meta: model type = 7B |
|
llm_load_print_meta: model ftype = F16 |
|
llm_load_print_meta: model params = 7.61 B |
|
llm_load_print_meta: model size = 14.18 GiB (16.00 BPW) |
|
llm_load_print_meta: general.name = gte-Qwen2-7B-instruct |
|
llm_load_print_meta: BOS token = 151643 '<|endoftext|>' |
|
llm_load_print_meta: EOS token = 151643 '<|endoftext|>' |
|
llm_load_print_meta: EOT token = 151645 '<|im_end|>' |
|
llm_load_print_meta: PAD token = 151643 '<|endoftext|>' |
|
llm_load_print_meta: LF token = 148848 'ÄĬ' |
|
llm_load_print_meta: EOG token = 151643 '<|endoftext|>' |
|
llm_load_print_meta: EOG token = 151645 '<|im_end|>' |
|
llm_load_print_meta: max token length = 256 |
|
llm_load_tensors: CPU_Mapped model buffer size = 3703.93 MiB |
|
llm_load_tensors: CPU_Mapped model buffer size = 3685.86 MiB |
|
llm_load_tensors: CPU_Mapped model buffer size = 3685.86 MiB |
|
llm_load_tensors: CPU_Mapped model buffer size = 3444.91 MiB |
|
........................................................................................ |
|
llama_new_context_with_model: n_seq_max = 1 |
|
llama_new_context_with_model: n_ctx = 131072 |
|
llama_new_context_with_model: n_ctx_per_seq = 131072 |
|
llama_new_context_with_model: n_batch = 2048 |
|
llama_new_context_with_model: n_ubatch = 512 |
|
llama_new_context_with_model: flash_attn = 0 |
|
llama_new_context_with_model: freq_base = 1000000.0 |
|
llama_new_context_with_model: freq_scale = 1 |
|
llama_kv_cache_init: CPU KV buffer size = 7168.00 MiB |
|
llama_new_context_with_model: KV self size = 7168.00 MiB, K (f16): 3584.00 MiB, V (f16): 3584.00 MiB |
|
llama_new_context_with_model: CPU output buffer size = 0.01 MiB |
|
llama_new_context_with_model: CPU compute buffer size = 7452.01 MiB |
|
llama_new_context_with_model: graph nodes = 986 |
|
llama_new_context_with_model: graph splits = 1 |
|
``` |
|
|
|
## Usage |
|
|
|
### Sentence Transformers |
|
|
|
### Transformers |
|
|
|
## Inference |
|
|
|
### Using `llama.cpp` to get embeddings in CPU and/or GPU |
|
First [build](https://github.com/ggerganov/llama.cpp/blob/master/docs/build.md) or [install](https://github.com/ggerganov/llama.cpp/blob/master/docs/install.md) **`llama-server`** binary from [`llama.cpp`](https://github.com/ggerganov/llama.cpp), preferably with GPU support. |
|
### CLI |
|
### Server |
|
```bash |
|
# using remote HF repo address (with model file(s) to be downloaded and cached locally) |
|
$ llama-server --hf-repo mirekphd/gte-Qwen2-7B-instruct-F16 --hf-file gte-Qwen2-7B-instruct-F16-00001-of-00004.gguf --n-gpu-layers 0 --ctx-size 131072 --embeddings |
|
|
|
# using a previously downloaded local model file(s) |
|
$ llama-server --model <path-to-hf-models>/mirekphd/gte-Qwen2-7B-instruct-F16/gte-Qwen2-7B-instruct-F16-00001-of-00004.gguf --n-gpu-layers 0 --ctx-size 131072 --embeddings |
|
|
|
``` |
|
|
|
## Evaluation |
|
|
|
### MTEB & C-MTEB |
|
|
|
## Cloud API Services |
|
|
|
## Citation |
|
If you find our paper or models helpful, please consider cite: |
|
|
|
``` |
|
@article{li2023towards, |
|
title={Towards general text embeddings with multi-stage contrastive learning}, |
|
author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan}, |
|
journal={arXiv preprint arXiv:2308.03281}, |
|
year={2023} |
|
} |
|
``` |
