alt.freeweights.embed / mxbai-rerank-base-v2
From: mixedbread-ai <huggingface.co/mixedbread-ai>Newsgroups: alt.freeweights.embedSubject:

mxbai-rerank-base-v2

Date: 2026-11-14Commit: 3ea9d4dSigned: 2DC28CC7B26A283B ✓

Text ranking model with 494M parameters. Safetensors weights, 1.00 GB in all. Published by mixedbread-ai under Apache-2.0.

494M params1.00GBmxbai-rerank-base-v2safetensorspermissive
FactsParams494MSize1.00 GBFormatssafetensorsTasktext rankingLicenseApache-2.0From sourcepermissive
$ fw get mixedbread-ai/mxbai-rerank-base-v2
# manifest sha256 a1c9fcaa4a68… · 1.00 GB · 17 files
$ fw verify ./mxbai-rerank-base-v2 mixedbread-ai/mxbai-rerank-base-v2
From sourceHosted (signed)mixedbread-ai/mxbai-rerank-base-v2Last check: 2026-11-14 21:09 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Works with

Evaluate with

Overview

Size
1.00 GB
Weights
988 MB (safetensors)
Parameters
494M
Formats
safetensors
Task
text ranking
License
Apache-2.0 (permissive)
Files
17, each with a sha256
Publisher
mixedbread-ai
Added
2026-11-14
Section
alt.freeweights.embed
Lineage

Original release from the publisher.

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-14 21:09 UTCpassed

Model card

From the publisher at commit 3ea9d4d. Shown as plain text with links; images open at the publisher.

The crispy rerank family from Mixedbread.

🍞 Looking for a simple end-to-end retrieval solution? Meet Omni, our multimodal and multilingual model. Get in touch for access.

🍞 mxbai-rerank-base-v2 (a.k.a ProRank-0.5B)#

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:

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

βš™οΈ Usage#

Using Sentence Transformers#

Install Sentence Transformers:

pip install sentence_transformers
from sentence_transformers import CrossEncoder

model = CrossEncoder("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.",
]

pairs = [(query, doc) for doc in documents]
scores = model.predict(pairs)
print(scores)
# [9.750735   1.3697281  8.080784   2.6611633  0.8729458  0.39884853]

rankings = model.rank(query, documents)
print(rankings)
# [{'corpus_id': 0, 'score': np.float32(9.750735)}, {'corpus_id': 2, 'score': np.float32(8.080784)}, {'corpus_id': 3, 'score': np.float32(2.6611633)}, {'corpus_id': 1, 'score': np.float32(1.3697281)}, {'corpus_id': 4, 'score': np.float32(0.8729458)}, {'corpus_id': 5, 'score': np.float32(0.39884853)}]
Using mxbai-rerank#
  1. Install mxbai-rerank
pip install mxbai-rerank
  1. 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#
ModelBEIR AvgMultilingualChineseCode SearchLatency (s)
mxbai-rerank-large-v257.4929.7984.1632.050.89
mxbai-rerank-base-v255.5728.5683.7031.730.67
mxbai-rerank-large-v149.3221.8872.5330.722.24

*Latency measured on A100 GPU

Training Details#

The models were trained using a three-step process:

  1. GRPO (Guided Reinforcement Prompt Optimization)
  2. Contrastive Learning
  3. Preference Learning

For more details, check our technical report and technical blog post.

πŸŽ“ Citation#

If you find our models useful, please consider giving a star and citation

arXiv:

@article{li2025prorank,
  title={ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking},
  author={Xianming Li and Aamir Shakir and Rui Huang and Julius Lipp and Benjamin ClaviΓ© and Jing Li},
  journal={arXiv preprint arXiv:2506.03487},
  year={2025}
}

blog post:

@online{v2rerank2025mxbai,
  title={Baked-in Brilliance: Reranking Meets RL with mxbai-rerank-v2},
  author={Sean Lee and Rui Huang and Aamir Shakir and Julius Lipp},
  year={2025},
  url={https://www.mixedbread.com/blog/mxbai-rerank-v2},
}

Files

17 files Β· 1.00 GBWeights 988 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 17 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
1_LogitScore/config.json50 B2554429e789efe4bb7b78977ed56bb03dd9321d63b1e304c04f94ba61c0281d3
LICENSE10.8 KB4b0dfefcb74f1e50a8df72a9f2bf0088753f8568bc479387292469b4948705d4
README.md46.9 KBd5246419d50ce8652f9340f117568ec4f8b10385cc059f2b5c90aacba87ac9df
added_tokens.json605 B58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
chat_template.jinja576 B6922504e8481a822f50ecdf80da9d41f09cb01601c82d1acae04bdba654deafc
config.json766 Ba0c0e4d41f64c29c861548344b62e6f4237a2f0c5664454089dc0db127f8eaed
config_sentence_transformers.json204 Bb2787b4c078bc8d55f1a4a904b2e7b52dadfd9b26424517645bb130d9aa3f9b0
generation_config.json242 B722a06091ec871c6cbc3dda5412f294267bcd5d9310f4ffbef1d358000dd3bfc
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model.safetensors988 MBc01649fe56b3fe32e52da43c69e084dff7c2252cf231a38c56d5a291a674338f
modules.json281 B8b0cf4a17b264e13b267907ee1026e551b1cde537691dd71af4c8aa55a889769
sentence_bert_config.json309 B8c98fdfffa489b1b78843150aeb7b2992800e0dc8138079ddc4d72a98fd40348
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MB9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
tokenizer_config.json4.69 KB0a04a9d7d4a62b28482bdfe726c122756de85714fb64166ace92ae75b8f57614
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
3ea9d4dffa pinned now manifest updated, same commit2026-11-14 21:09 UTC17 files Β· 1.00 GB
3ea9d4dffa2026-11-14 21:09 UTC17 files Β· 1.00 GB

Use it

$ fw get mixedbread-ai/mxbai-rerank-base-v2
# manifest sha256 a1c9fcaa4a68… · 1.00 GB · 17 files
$ fw verify ./mxbai-rerank-base-v2 mixedbread-ai/mxbai-rerank-base-v2
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mixedbread-ai/mxbai-rerank-base-v2.json --dir ./mxbai-rerank-base-v2 $ python3 fw.py verify ./mxbai-rerank-base-v2 ./mixedbread-ai__mxbai-rerank-base-v2.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mixedbread-ai/mxbai-rerank-base-v2 --revision 3ea9d4dffa7d12a4f366be8e275c349de9fc9865 --local-dir ./mxbai-rerank-base-v2

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-14
Text in
LICENSE
Text sha256
4b0dfefcb74f1e50a8df72a9f2bf0088753f8568bc479387292469b4948705d4
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: mixedbread-ai <huggingface.co/mixedbread-ai>Newsgroups: alt.freeweights.embedSubject: mxbai-rerank-base-v2Date: 2026-11-14Commit: 3ea9d4dSigned: 2DC28CC7B26A283B ✓
Upstream
mixedbread-ai/mxbai-rerank-base-v2
Pinned commit
3ea9d4dffa7d12a4f366be8e275c349de9fc9865
Manifest
mxbai-rerank-base-v2.json Β· .minisig
Manifest sha256
a1c9fcaa4a6812da65084b387047bc25f10762e976e24cadc5a0a1fc4c0b4226
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:09 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mixedbread-ai/mxbai-rerank-base-v2.json $ curl -O https://freeweights.allternit.com/manifests/mixedbread-ai/mxbai-rerank-base-v2.json.minisig $ minisign -Vm mxbai-rerank-base-v2.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mixedbread-ai/mxbai-rerank-base-v2
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. mxbai-rerank-base-v2.json. Provenance. Takedown history: none.
From: sentence-transformers <huggingface.co/sentence-transformers>Subject: all-MiniLM-L6-v1
From: unsloth <huggingface.co/unsloth>Subject: all-MiniLM-L6-v2
From: mlx-community <huggingface.co/mlx-community>Subject: all-MiniLM-L6-v2-4bit
From: sentence-transformers <huggingface.co/sentence-transformers>Subject: all-mpnet-base-v1
From: sentence-transformers <huggingface.co/sentence-transformers>Subject: allenai-specter
From: sentence-transformers <huggingface.co/sentence-transformers>Subject: bert-base-nli-max-tokens