Update README.md
Browse files
README.md
CHANGED
|
@@ -3171,7 +3171,7 @@ model-index:
|
|
| 3171 |
|
| 3172 |
## gte-Qwen2-7B-instruct
|
| 3173 |
|
| 3174 |
-
**gte-Qwen2-7B-instruct** is the latest model in the gte (General Text Embedding) model family.
|
| 3175 |
|
| 3176 |
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.
|
| 3177 |
|
|
@@ -3302,6 +3302,19 @@ You can use the [scripts/eval_mteb.py](https://huggingface.co/Alibaba-NLP/gte-Qw
|
|
| 3302 |
|
| 3303 |
The gte series models have consistently released two types of models: encoder-only models (based on the BERT architecture) and decode-only models (based on the LLM architecture).
|
| 3304 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3305 |
## Citation
|
| 3306 |
|
| 3307 |
If you find our paper or models helpful, please consider cite:
|
|
|
|
| 3171 |
|
| 3172 |
## gte-Qwen2-7B-instruct
|
| 3173 |
|
| 3174 |
+
**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).
|
| 3175 |
|
| 3176 |
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.
|
| 3177 |
|
|
|
|
| 3302 |
|
| 3303 |
The gte series models have consistently released two types of models: encoder-only models (based on the BERT architecture) and decode-only models (based on the LLM architecture).
|
| 3304 |
|
| 3305 |
+
| Models | Language | Max Sequence Length | Dimension | Model Size (Memory Usage, fp32) |
|
| 3306 |
+
|:-------------------------------------------------------------------------------------:|:--------:|:-----: |:---------:|:-------------------------------:|
|
| 3307 |
+
| [GTE-large-zh](https://huggingface.co/thenlper/gte-large-zh) | Chinese | 512 | 1024 | 1.25GB |
|
| 3308 |
+
| [GTE-base-zh](https://huggingface.co/thenlper/gte-base-zh) | Chinese | 512 | 512 | 0.41GB |
|
| 3309 |
+
| [GTE-small-zh](https://huggingface.co/thenlper/gte-small-zh) | Chinese | 512 | 512 | 0.12GB |
|
| 3310 |
+
| [GTE-large](https://huggingface.co/thenlper/gte-large) | English | 512 | 1024 | 1.25GB |
|
| 3311 |
+
| [GTE-base](https://huggingface.co/thenlper/gte-base) | English | 512 | 512 | 0.21GB |
|
| 3312 |
+
| [GTE-small](https://huggingface.co/thenlper/gte-small) | English | 512 | 384 | 0.10GB |
|
| 3313 |
+
| [GTE-large-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5) | English | 8192 | 1024 | 1.74GB |
|
| 3314 |
+
| [GTE-base-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-base-en-v1.5) | English | 8192 | 768 | 0.51GB |
|
| 3315 |
+
| [GTE-Qwen1.5-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen1.5-7B-instruct) | Multilingual | 32000 | 4096 | 26.45GB |
|
| 3316 |
+
| [GTE-Qwen2-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct) | Multilingual | 32000 | 4096 | 26.45GB |
|
| 3317 |
+
|
| 3318 |
## Citation
|
| 3319 |
|
| 3320 |
If you find our paper or models helpful, please consider cite:
|