mxbai-rerank-base-v2-seq

michaelfeil/mxbai-rerank-base-v2-seq

mxbai-rerank-base-v2-seq is a text ranking model from michaelfeil. Use it for the text ranking task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

Downloads · 30 days

2% of all-time downloads

All-time downloads

3.8K

Public

Parameters

494M

1000 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors988 MB · 98%

At a glance

Task: Text Ranking
Library: transformers
License: apache-2.0
Model type: qwen2
Access: Public
Created: Mar 14, 2025
Updated: Apr 2, 2025
SHA: a9f89869

Model card

From the Hugging Face model README

Rewritten Mixedbread Reranker as classifier

This repo is the Mixedbread reranker rewritten as Classifier that is as of March 2025 the most powerful reranker, e.g. for RAG.

FP8 Deployment on H100

build_commands: []
environment_variables: {}
external_package_dirs: []
model_metadata:
  example_model_input:
    input: 'ERROR: This redirects to the embedding endpoint. Use the /sync API to
      reach /sync/predict'
model_name: BEI-mixedbread-ai-mxbai-rerank-base-v2-reranker-fp8-truss-example
python_version: py39
requirements: []
resources:
  accelerator: L4
  cpu: '1'
  memory: 10Gi
  use_gpu: true
secrets: {}
system_packages: []
trt_llm:
  build:
    base_model: encoder
    checkpoint_repository:
      repo: michaelfeil/mxbai-rerank-base-v2-seq
      revision: main
      source: HF
    max_num_tokens: 32768
    max_seq_len: 1000001
    num_builder_gpus: 4
    quantization_type: fp8

To push the deployment on Baseten.co

truss push --publish

More info: https://github.com/basetenlabs/truss-examples/tree/main/11-embeddings-reranker-classification-tensorrt/BEI-mixedbread-ai-mxbai-rerank-base-v2-reranker-fp8

Usage as classifier

For usage with Baseten.co or with github.com/michaelfeil/infinity, you should use the classification API. You need to manually create the following prompt template that is very specfic to this model. This template follows the reference implementation at https://github.com/mixedbread-ai/mxbai-rerank/tree/main.

def create_mxbai_v2_reranker_prompt_template(query: str, document: str, instruction: str = "") -> str:
    """
    Create a carefully formatted chat template string (without tokenizer) for ranking relevance.

    Parameters:
        query (str): The search query.
        document (str): The document text to evaluate.
        instruction (str): Special instructions (e.g., "You are an expert for Mockingbirds.")

    Returns:
        str: The formatted chat template.
    """
    instruction = f"instruction: {instruction}\n" if instruction else ""    
    # fixed system prompt, keep as is.
    system_prompt = "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."
    assert not "\n" in system_prompt
    assert not "\n" in instruction[:-1]
    assert isinstance(query, str)
    assert isinstance(document, str)
    templated = (
        # keep spacing, newlines as is.
        # template for mixedbread reranker v2
        # https://huggingface.co/michaelfeil/mxbai-rerank-base-v2-seq/
       f"<|endoftext|><|im_start|>system\n{system_prompt}\n"
        "<|im_end|>\n"
        "<|im_start|>user\n"
        f"{instruction}"
        f"query: {query} \n"
        f"document: {document} \n"
        "You are a search relevance expert who evaluates how well documents match search queries. "
        "For each query-document pair, carefully analyze the semantic relationship between them, then provide your binary relevance judgment (0 for not relevant, 1 for relevant).\n"
        "Relevance:<|im_end|>\n"
        "<|im_start|>assistant\n"
    )
    return templated

🍞 mxbai-rerank-base-v2

This is the base model in our family of powerful reranker models. You can learn more about the models in our blog post.

We have two models:

mxbai-rerank-base-v2 (🍞)
mxbai-rerank-large-v2

The technical report is coming soon!

🌟 Features

state-of-the-art performance and strong efficiency
multilingual support (100+ languages, outstanding English and Chinese performance)
code support
long-context support

⚙️ Usage

Install mxbai-rerank

pip install mxbai-rerank

Inference

from mxbai_rerank import MxbaiRerankV2

model = MxbaiRerankV2("mixedbread-ai/mxbai-rerank-base-v2")

query = "Who wrote 'To Kill a Mockingbird'?"
documents = [
    "'To Kill a Mockingbird' is a novel by Harper Lee published in 1960. It was immediately successful, winning the Pulitzer Prize, and has become a classic of modern American literature.",
    "The novel 'Moby-Dick' was written by Herman Melville and first published in 1851. It is considered a masterpiece of American literature and deals with complex themes of obsession, revenge, and the conflict between good and evil.",
    "Harper Lee, an American novelist widely known for her novel 'To Kill a Mockingbird', was born in 1926 in Monroeville, Alabama. She received the Pulitzer Prize for Fiction in 1961.",
    "Jane Austen was an English novelist known primarily for her six major novels, which interpret, critique and comment upon the British landed gentry at the end of the 18th century.",
    "The 'Harry Potter' series, which consists of seven fantasy novels written by British author J.K. Rowling, is among the most popular and critically acclaimed books of the modern era.",
    "'The Great Gatsby', a novel written by American author F. Scott Fitzgerald, was published in 1925. The story is set in the Jazz Age and follows the life of millionaire Jay Gatsby and his pursuit of Daisy Buchanan."
]

# Lets get the scores
results = model.rank(query, documents, return_documents=True, top_k=3)

print(results)

Performance

Benchmark Results

Model	BEIR Avg	Multilingual	Chinese	Code Search	Latency (s)
mxbai-rerank-large-v2	57.49	29.79	84.16	32.05	0.89
mxbai-rerank-base-v2	55.57	28.56	83.70	31.73	0.67
mxbai-rerank-large-v1	49.32	21.88	72.53	30.72	2.24

*Latency measured on A100 GPU

Training Details

The models were trained using a three-step process:

GRPO (Guided Reinforcement Prompt Optimization)
Contrastive Learning
Preference Learning

For more details, check our technical blog post.

Paper following soon.

🎓 Citation

@online{rerank2025mxbai,
  title={Every Byte Matters: Introducing mxbai-embed-xsmall-v1},
  author={Sean Lee and Aamir Shakir and Julius Lipp and Rui Huang},
  year={2025},
  url={https://www.mixedbread.com/blog/mxbai-rerank-v2},
}

Task: Text Ranking
Library: transformers
Type: qwen2
License: apache-2.0
Languages: en, zh, de, ja, ko, es
Created: Mar 14, 2025
Updated: Apr 2, 2025