language:
- zh
- en
base_model: openbmb/MiniCPM-2B-dpo-bf16
RankCPM-R
RankCPM-R 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重排序模型，有如下特点：
- 出色的中文、英文重排序能力。
- 出色的中英跨语言重排序能力。
RankCPM-R 基于 MiniCPM-2B-sft-bf16 训练，结构上采取双向注意力。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：RankCPM-E
- 重排模型：RankCPM-R
- 面向 RAG 场景的 LoRA 插件：MiniCPM3-RAG-LoRA
RankCPM-R is a bilingual & cross-lingual text re-ranking model developed by ModelBest Inc. and THUNLP, featuring:
- Exceptional Chinese and English re-ranking capabilities.
- Outstanding cross-lingual re-ranking capabilities between Chinese and English.
RankCPM-R is trained based on MiniCPM-2B-sft-bf16 and incorporates bidirectional attention 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: RankCPM-E
- Re-ranking Model: RankCPM-R
- LoRA Plugin for RAG scenarios: MiniCPM3-RAG-LoRA
模型信息 Model Information
模型大小：2.4B
最大输入token数：1024
Model Size: 2.4B
Max Input Tokens: 1024
使用方法 Usage
输入格式 Input Format
本模型支持指令，输入格式如下：
RankCPM-R supports instructions in the following format:
<s>Instruction: {{ instruction }} Query: {{ query }}</s>{{ document }}
例如：
For example:
<s>Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？</s>（文档省略）
<s>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.</s>(document omitted)
也可以不提供指令，即采取如下格式：
RankCPM-R also works in instruction-free mode in the following format:
<s>Query: {{ query }}</s>{{ document }}
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。
When running evaluation on BEIR and C-MTEB/Retrieval, we use instructions in instructions.json. For other evaluations, we do not use instructions.
环境要求 Requirements
transformers==4.37.2
flash-attn>2.3.5
示例脚本 Demo
from transformers import AutoModel, AutoTokenizer, AutoModelForSequenceClassification
import torch
import numpy as np
model_name = "openbmb/RankCPM-R"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
tokenizer.padding_side = "right"
model = AutoModelForSequenceClassification.from_pretrained(model_name, trust_remote_code=True,attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
max_len_q, max_len_d = 512, 512
def tokenize_our(query,doc):
input_id_query = tokenizer.encode(query, add_special_tokens=False, max_length=max_len_q, truncation=True)
input_id_doc = tokenizer.encode(doc, add_special_tokens=False, max_length=max_len_d, truncation=True)
pad_input = {"input_ids": [tokenizer.bos_token_id] + input_id_query + [tokenizer.eos_token_id] + input_id_doc}
return tokenizer.pad(
pad_input,
padding="max_length",
max_length=max_len_q + max_len_d + 2,
return_tensors="pt",
)
@torch.no_grad()
def rerank(input_query, input_docs):
tokenized_inputs = [tokenize_our(input_query, input_doc).to("cuda") for input_doc in input_docs]
input_ids = {
"input_ids": [tokenized_input["input_ids"] for tokenized_input in tokenized_inputs],
"attention_mask": [tokenized_input["attention_mask"] for tokenized_input in tokenized_inputs]
}
for k in input_ids:
input_ids[k] = torch.stack(input_ids[k]).to("cuda")
outputs = model(**input_ids)
score = outputs.logits
return score.float().detach().cpu().numpy()
queries = ["中国的首都是哪里？"]
passages = [["beijing", "shanghai"]]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
scores = []
for i in range(len(queries)):
print(queries[i])
scores.append(rerank(queries[i],passages[i]))
print(np.array(scores)) # [[[-4.7421875][-8.8515625]]]
实验结果 Evaluation Results
中文与英文重排序结果 CN/EN Re-ranking Results
中文对bge-large-zh-v1.5检索的top-100进行重排，英文对bge-large-en-v1.5检索的top-100进行重排。
We re-rank top-100 docments from bge-large-zh-v1.5 in C-MTEB/Retrieval and from bge-large-en-v1.5 in BEIR.
| 模型 Model | C-MTEB/Retrieval (NDCG@10) | BEIR (NDCG@10) |
|---|---|---|
| bge-large-zh-v1.5（Retriever for Chinese） | 70.46 | - |
| bge-large-en-v1.5（Retriever for English） | - | 54.29 |
| bge-reranker-v2-m3 | 71.82 | 55.36 |
| bge-reranker-v2-minicpm-28 | 73.51 | 59.86 |
| bge-reranker-v2-gemma | 71.74 | 60.71 |
| bge-reranker-v2.5-gemma2 | - | 63.67 |
| RankCPM-R | 76.79 | 61.32 |
中英跨语言重排序结果 CN-EN Cross-lingual Re-ranking Results
对bge-m3(Dense)检索的top100进行重排。
We re-rank top-100 documents from bge-m3 (Dense).
| 模型 Model | MKQA EN-CN (Recall@20) | NeuCLIR22 (NDCG@10) | NeuCLIR23 (NDCG@10) |
|---|---|---|---|
| bge-m3 (Dense)（Retriever） | 66.4 | 30.49 | 41.09 |
| jina-reranker-v2-base-multilingual | 69.33 | 36.66 | 50.03 |
| bge-reranker-v2-m3 | 69.75 | 40.98 | 49.67 |
| gte-multilingual-reranker-base | 68.51 | 38.74 | 45.3 |
| RankCPM-R | 71.73 | 43.65 | 50.59 |
许可证 License
- 本仓库中代码依照 Apache-2.0 协议开源。
- RankCPM-R 模型权重的使用则需要遵循 MiniCPM 模型协议。
- RankCPM-R 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。
- The code in this repo is released under the Apache-2.0 License.
- The usage of RankCPM-R model weights must strictly follow MiniCPM Model License.md.
- The models and weights of RankCPM-R are completely free for academic research. After filling out a "questionnaire" for registration, RankCPM-R weights are also available for free commercial use.