|
--- |
|
library_name: transformers |
|
license: mit |
|
datasets: |
|
- shibing624/nli-zh-all |
|
- shibing624/nli_zh |
|
language: |
|
- en |
|
metrics: |
|
- spearmanr |
|
--- |
|
|
|
|
|
# AnglE📐: Angle-optimized Text Embeddings |
|
|
|
> It is Angle 📐, not Angel 👼. |
|
|
|
🔥 A New SOTA Model for Semantic Textual Similarity! |
|
|
|
Github: https://github.com/SeanLee97/AnglE |
|
|
|
<a href="https://arxiv.org/abs/2309.12871"> |
|
<img src="https://img.shields.io/badge/Arxiv-2306.06843-yellow.svg?style=flat-square" alt="https://arxiv.org/abs/2309.12871" /> |
|
</a> |
|
|
|
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sick-r-1?p=angle-optimized-text-embeddings) |
|
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sts16?p=angle-optimized-text-embeddings) |
|
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sts15?p=angle-optimized-text-embeddings) |
|
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sts14?p=angle-optimized-text-embeddings) |
|
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sts13?p=angle-optimized-text-embeddings) |
|
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sts12?p=angle-optimized-text-embeddings) |
|
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sts-benchmark?p=angle-optimized-text-embeddings) |
|
|
|
|
|
**STS Results** |
|
|
|
|
|
| Model | ATEC | BQ | LCQMC | PAWSX | STS-B | SOHU-dd | SOHU-dc | Avg. | |
|
| ------- |-------|-------|-------|-------|-------|--------------|-----------------|-------| |
|
| ^[shibing624/text2vec-bge-large-chinese](https://huggingface.co/shibing624/text2vec-bge-large-chinese) | 38.41 | 61.34 | 71.72 | 35.15 | 76.44 | 71.81 | 63.15 | 59.72 | |
|
| ^[shibing624/text2vec-base-chinese-paraphrase](https://huggingface.co/shibing624/text2vec-base-chinese-paraphrase) | 44.89 | 63.58 | 74.24 | 40.90 | 78.93 | 76.70 | 63.30 | 63.08 | |
|
| [SeanLee97/angle-roberta-wwm-base-zhnli-v1](https://huggingface.co/SeanLee97/angle-roberta-wwm-base-zhnli-v1) | 49.49 | 72.47 | 78.33 | 59.13 | 77.14 | 72.36 | 60.53 | **67.06** | |
|
| [SeanLee97/angle-llama-7b-zhnli-v1](https://huggingface.co/SeanLee97/angle-llama-7b-zhnli-v1) | 50.44 | 71.95 | 78.90 | 56.57 | 81.11 | 68.11 | 52.02 | 65.59 | |
|
|
|
^ denotes baselines, their results are retrieved from https://github.com/shibing624/text2vec |
|
|
|
## Usage |
|
|
|
```python |
|
from angle_emb import AnglE, Prompts |
|
|
|
angle = AnglE.from_pretrained('NousResearch/Llama-2-7b-hf', pretrained_lora_path='SeanLee97/angle-llama-7b-zhnli-v1') |
|
# 请选择对应的 prompt，此模型对应 Prompts.B |
|
print('All predefined prompts:', Prompts.list_prompts()) |
|
angle.set_prompt(prompt=Prompts.B) |
|
print('prompt:', angle.prompt) |
|
vec = angle.encode({'text': '你好世界'}, to_numpy=True) |
|
print(vec) |
|
vecs = angle.encode([{'text': '你好世界1'}, {'text': '你好世界2'}], to_numpy=True) |
|
print(vecs) |
|
``` |
|
|
|
## Citation |
|
|
|
You are welcome to use our code and pre-trained models. If you use our code and pre-trained models, please support us by citing our work as follows: |
|
|
|
```bibtex |
|
@article{li2023angle, |
|
title={AnglE-Optimized Text Embeddings}, |
|
author={Li, Xianming and Li, Jing}, |
|
journal={arXiv preprint arXiv:2309.12871}, |
|
year={2023} |
|
} |
|
``` |
