openbmb/MiniCPM-Reranker

MiniCPM-Reranker

MiniCPM-Reranker 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。

MiniCPM-Reranker 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：MiniCPM-Embedding
• 重排模型：MiniCPM-Reranker
• 面向 RAG 场景的 LoRA 插件：MiniCPM3-RAG-LoRA

MiniCPM-Reranker 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.

MiniCPM-Reranker 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: MiniCPM-Embedding
• Re-ranking Model: MiniCPM-Reranker
• 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：

MiniCPM-Reranker 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：

MiniCPM-Reranker 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/MiniCPM-Reranker"
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))  # [[[-4.7460938][-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
MiniCPM-Reranker	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-Zh_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
MiniCPM-Reranker	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。
• MiniCPM-Reranker 模型权重的使用则需要遵循 MiniCPM 模型协议。
• MiniCPM-Reranker 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 MiniCPM-Reranker model weights must strictly follow MiniCPM Model License.md.
• The models and weights of MiniCPM-Reranker are completely free for academic research. After filling out a "questionnaire" for registration, MiniCPM-Reranker weights are also available for free commercial use.