|
--- |
|
language: |
|
- zh |
|
- en |
|
base_model: openbmb/MiniCPM-2B-sft-bf16 |
|
--- |
|
## MiniCPM-Embedding |
|
|
|
**MiniCPM-Embedding** 是面壁智能与清华大学自然语言处理实验室（THUNLP）共同开发的中英双语言文本嵌入模型，有如下特点： |
|
- 出色的中文、英文检索能力。 |
|
- 出色的中英跨语言检索能力。 |
|
|
|
MiniCPM-Embedding 基于 [MiniCPM-2B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16) 训练，结构上采取双向注意力和 Weighted Mean Pooling [1]。采取多阶段训练方式，共使用包括开源数据、机造数据、闭源数据在内的约 600 万条训练数据。 |
|
|
|
欢迎关注 RAG 套件系列： |
|
|
|
- 检索模型：[MiniCPM-Embedding](https://huggingface.co/openbmb/MiniCPM-Embedding) |
|
- 重排模型：[MiniCPM-Reranker](https://huggingface.co/openbmb/MiniCPM-Reranker) |
|
- 面向 RAG 场景的 LoRA 插件：[MiniCPM3-RAG-LoRA](https://huggingface.co/openbmb/MiniCPM3-RAG-LoRA) |
|
|
|
**MiniCPM-Embedding** is a bilingual & cross-lingual text embedding model developed by ModelBest Inc. and THUNLP, featuring: |
|
|
|
- Exceptional Chinese and English retrieval capabilities. |
|
- Outstanding cross-lingual retrieval capabilities between Chinese and English. |
|
|
|
MiniCPM-Embedding is trained based on [MiniCPM-2B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16) and incorporates bidirectional attention and Weighted Mean Pooling [1] in its architecture. The model underwent multi-stage training using approximately 6 million training examples, including open-source, synthetic, and proprietary data. |
|
|
|
We also invite you to explore the RAG toolkit series: |
|
|
|
- Retrieval Model: [MiniCPM-Embedding](https://huggingface.co/openbmb/MiniCPM-Embedding) |
|
- Re-ranking Model: [MiniCPM-Reranker](https://huggingface.co/openbmb/MiniCPM-Reranker) |
|
- LoRA Plugin for RAG scenarios: [MiniCPM3-RAG-LoRA](https://huggingface.co/openbmb/MiniCPM3-RAG-LoRA) |
|
|
|
[1] Muennighoff, N. (2022). Sgpt: Gpt sentence embeddings for semantic search. arXiv preprint arXiv:2202.08904. |
|
|
|
## 模型信息 Model Information |
|
|
|
- 模型大小：2.4B |
|
- 嵌入维度：2304 |
|
- 最大输入token数：512 |
|
|
|
- Model Size: 2.4B |
|
- Embedding Dimension: 2304 |
|
- Max Input Tokens: 512 |
|
|
|
## 使用方法 Usage |
|
|
|
### 输入格式 Input Format |
|
|
|
本模型支持 query 侧指令，格式如下： |
|
|
|
MiniCPM-Embedding supports query-side instructions in the following format: |
|
|
|
``` |
|
Instruction: {{ instruction }} Query: {{ query }} |
|
``` |
|
|
|
例如： |
|
|
|
For example: |
|
|
|
``` |
|
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？ |
|
``` |
|
|
|
``` |
|
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast. |
|
``` |
|
|
|
也可以不提供指令，即采取如下格式： |
|
|
|
MiniCPM-Embedding also works in instruction-free mode in the following format: |
|
|
|
``` |
|
Query: {{ query }} |
|
``` |
|
|
|
我们在 BEIR 与 C-MTEB/Retrieval 上测试时使用的指令见 `instructions.json`，其他测试不使用指令。文档侧直接输入文档原文。 |
|
|
|
When running evaluation on BEIR and C-MTEB/Retrieval, we use instructions in `instructions.json`. For other evaluations, we do not use instructions. On the document side, we directly use the bare document as the input. |
|
|
|
### 环境要求 Requirements |
|
|
|
``` |
|
transformers==4.37.2 |
|
flash-attn>2.3.5 |
|
``` |
|
|
|
### 示例脚本 Demo |
|
|
|
```python |
|
|
|
from transformers import AutoModel, AutoTokenizer |
|
import torch |
|
import torch.nn.functional as F |
|
|
|
model_name = "openbmb/MiniCPM-Embedding" |
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda") |
|
model.eval() |
|
|
|
def weighted_mean_pooling(hidden, attention_mask): |
|
attention_mask_ = attention_mask * attention_mask.cumsum(dim=1) |
|
s = torch.sum(hidden * attention_mask_.unsqueeze(-1).float(), dim=1) |
|
d = attention_mask_.sum(dim=1, keepdim=True).float() |
|
reps = s / d |
|
return reps |
|
|
|
@torch.no_grad() |
|
def encode(input_texts): |
|
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda") |
|
|
|
outputs = model(**batch_dict) |
|
attention_mask = batch_dict["attention_mask"] |
|
hidden = outputs.last_hidden_state |
|
|
|
reps = weighted_mean_pooling(hidden, attention_mask) |
|
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy() |
|
return embeddings |
|
|
|
queries = ["中国的首都是哪里？"] |
|
passages = ["beijing", "shanghai"] |
|
|
|
|
|
INSTRUCTION = "Query: " |
|
queries = [INSTRUCTION + query for query in queries] |
|
|
|
embeddings_query = encode(queries) |
|
embeddings_doc = encode(passages) |
|
|
|
scores = (embeddings_query @ embeddings_doc.T) |
|
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]] |
|
``` |
|
|
|
## 实验结果 Evaluation Results |
|
|
|
### 中文与英文检索结果 CN/EN Retrieval Results |
|
|
|
| 模型 Model | C-MTEB/Retrieval (NDCG@10) | BEIR (NDCG@10) | |
|
|------------------------------|-------------------|---------------| |
|
| bge-large-zh-v1.5 | 70.46 | - | |
|
| gte-large-zh | 72.49 | - | |
|
| Zhihui_LLM_Embedding | 76.74 | | |
|
| bge-large-en-v1.5 | - | 54.29 | |
|
| gte-en-large-v1.5 | - | 57.91 | |
|
| NV-Retriever-v1 | - | 60.9 | |
|
| bge-en-icl | - | 62.16 | |
|
| NV-Embed-v2 | - | 62.65 | |
|
| me5-large | 63.66 | 51.43 | |
|
| bge-m3(Dense) | 65.43 | 48.82 | |
|
| gte-multilingual-base(Dense) | 71.95 | 51.08 | |
|
| gte-Qwen2-1.5B-instruct | 71.86 | 58.29 | |
|
| gte-Qwen2-7B-instruct | 76.03 | 60.25 | |
|
| bge-multilingual-gemma2 | 73.73 | 59.24 | |
|
| MiniCPM-Embedding | **76.76** | 58.56 | |
|
| MiniCPM-Embedding+MiniCPM-Reranker | 77.08 | 61.61 | |
|
|
|
### 中英跨语言检索结果 CN-EN Cross-lingual Retrieval Results |
|
|
|
| 模型 Model | MKQA En-Zh_CN (Recall@20) | NeuCLIR22 (NDCG@10) | NeuCLIR23 (NDCG@10) | |
|
|------------------------------|--------------------|--------------------|--------------------| |
|
| me5-large | 44.3 | 9.01 | 25.33 | |
|
| bge-m3(Dense) | 66.4 | 30.49 | 41.09 | |
|
| gte-multilingual-base(Dense) | 68.2 | 39.46 | 45.86 | |
|
| gte-Qwen2-1.5B-instruct | 68.52 | 49.11 | 45.05 | |
|
| gte-Qwen2-7B-instruct | 68.27 | 49.14 | 49.6 | |
|
| MiniCPM-Embedding | **72.95** | **52.65** | **49.95** | |
|
| MiniCPM-Embedding+MiniCPM-Reranker | 74.33 | 53.21 | 54.12 | |
|
|
|
## 许可证 License |
|
|
|
- 本仓库中代码依照 [Apache-2.0 协议](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE)开源。 |
|
- MiniCPM-Embedding 模型权重的使用则需要遵循 [MiniCPM 模型协议](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md)。 |
|
- MiniCPM-Embedding 模型权重对学术研究完全开放。如需将模型用于商业用途，请填写[此问卷](https://modelbest.feishu.cn/share/base/form/shrcnpV5ZT9EJ6xYjh3Kx0J6v8g)。 |
|
|
|
* The code in this repo is released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License. |
|
* The usage of MiniCPM-Embedding model weights must strictly follow [MiniCPM Model License.md](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md). |
|
* The models and weights of MiniCPM-Embedding are completely free for academic research. After filling out a ["questionnaire"](https://modelbest.feishu.cn/share/base/form/shrcnpV5ZT9EJ6xYjh3Kx0J6v8g) for registration, MiniCPM-Embedding weights are also available for free commercial use. |
