---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---

# chuxin-embedding

<!-- Provide a quick summary of what the model is/does. -->
chuxin-embedding 是专为增强中文文本检索能力而设计的嵌入模型。它基于bge-m3-retromae[1]，实现了预训练、微调、精调全流程。该模型在来自各个领域的大量语料库上进行训练，语料库的批量非常大。截至 2024 年 8 月 27 日,chuxin-embedding 在检索任务中表现出色，在 C-MTEB 排行榜上排名第一，领先的性能得分为 78.23。

## Training Details
基于bge-m3-retromae[1]，主要改动如下：
<!-- Provide a longer summary of what this model is. -->
- 基于bge-m3-retromae[1]在亿级数据上实现了预训练。
- 在收集的公开亿级检索数据集上实现了微调。
- 在收集的公开百万级检索数据集和百万级LLM合成数据集上实现了精调。
  - 通过 LLM (QWEN-72B) 进行数据生成，使用 LLM 为message生成新query
  - 数据清洗：
    - 简单的基于规则清洗
    - LLM判断是否可作为搜索引擎查询的query 
    - rerank模型对(query,message)评分，舍弃pos中的负例，neg中的正例
    
## Collect more data for retrieval-type tasks
1. MTP
2. BGE-LARGE-zh data
3. PEG data
4. BGE-M3 data
5. miracl/miracl
6. FreedomIntelligence/Huatuo26M-Lite

## Generate Embedding for text
```python
from FlagEmbedding import BGEM3FlagModel

model = BGEM3FlagModel('chuxin/chuxin-embedding',  
                       use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation

sentences_1 = ["样例数据-1", "样例数据-2"]
sentences_2 = ["样例数据-3", "样例数据-1"]

embeddings_1 = model.encode(sentences_1, 
                            batch_size=12, 
                            max_length=1024, 
                            )['dense_vecs']
embeddings_2 = model.encode(sentences_2)['dense_vecs']
similarity = embeddings_1 @ embeddings_2.T
print(similarity)

```

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Reference
1. https://huggingface.co/BAAI/bge-m3-retromae
2. https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3
3. https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/baai_general_embedding
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->