alt.freeweights.embed / mxbai-colbert-large-v1
From: mixedbread-ai <huggingface.co/mixedbread-ai>Newsgroups: alt.freeweights.embedSubject:

mxbai-colbert-large-v1

Date: 2026-11-14Commit: d092c67Signed: 2DC28CC7B26A283B ✓

Sentence similarity model with 335M parameters. Onnx and safetensors weights, 3.01 GB in all. Published by mixedbread-ai under Apache-2.0.

335M params3.01GBmxbai-colbert-large-v1onnx safetensorspermissive
FactsParams335MSize3.01 GBFormatsonnx, safetensorsTasksentence similarityLicenseApache-2.0From sourcepermissive
$ fw get mixedbread-ai/mxbai-colbert-large-v1
# manifest sha256 1e035a054fc6… · 3.01 GB · 13 files
$ fw verify ./mxbai-colbert-large-v1 mixedbread-ai/mxbai-colbert-large-v1
From sourceHosted (signed)mixedbread-ai/mxbai-colbert-large-v1Last 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
3.01 GB
Weights
671 MB (safetensors)
Parameters
335M
Formats
onnx, safetensors
Task
sentence similarity
License
Apache-2.0 (permissive)
Files
13, 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 d092c67. 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.

mixedbread-ai/mxbai-colbert-large-v1#

This is our first English ColBERT model, which is built upon our sentence embedding model mixedbread-ai/mxbai-embed-large-v1. You can learn more about the models in our blog post.

Quickstart#

Using Sentence Transformers#

This checkpoint also loads with Sentence Transformers as a multi-vector (ColBERT-style late interaction) retriever via the MultiVectorEncoder.

pip install "sentence-transformers>=6.0.0"
from sentence_transformers import MultiVectorEncoder

model = MultiVectorEncoder("mixedbread-ai/mxbai-colbert-large-v1")

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.",
]

query_embeddings = model.encode_query([query])
document_embeddings = model.encode_document(documents)
print(query_embeddings[0].shape, document_embeddings[0].shape)
# (128, 128) (34, 128)

# MaxSim late-interaction scoring
scores = model.similarity(query_embeddings, document_embeddings)
print(scores)
# tensor([[119.3276,  95.9337, 114.1252,  76.5609]])
Using RAGatouille#

This model can also be used with RAGatouille:

pip install ragatouille
from ragatouille import RAGPretrainedModel

# Let's create a ragatouille instance 
RAG = RAGPretrainedModel.from_pretrained("mixedbread-ai/mxbai-colbert-large-v1")

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."
]

# index documents
RAG.index(documents, index_name="mockingbird")

# search
query = "Who wrote 'To Kill a Mockingbird'?"
results = RAG.search(query)

The result looks like this:

[
  {
    'content': "'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.",
    'score': 28.453125,
    'rank': 1,
    'document_id': '9d564e82-f14f-433a-ab40-b10bda9dc370',
    'passage_id': 0
  },
 {
    'content': "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.",
    'score': 27.03125,
    'rank': 2,
    'document_id': 'a35a89c3-b610-4e2e-863e-fa1e7e0710a6',
    'passage_id': 2
  },
  ...
]

Evaluation#

1. Reranking Performance#

Setup: we use BM25 as the first-stage retrieval model, and then use ColBERT for reranking. We evaluate the out-of-domain performance on 13 public BEIR datasets. Following common practice, we report NDCG@10 as the metrics.

Here, we compare our model with two widely used ColBERT models, as follows:

DatasetColBERTv2Jina-ColBERT-v1mxbai-colbert-large-v1
ArguAna29.9933.4233.11
ClimateFEVER16.5120.6620.85
DBPedia31.8042.1640.61
FEVER65.1381.0780.75
FiQA23.6135.6035.86
HotPotQA63.3068.8467.62
NFCorpus33.7536.6936.37
NQ30.5551.2751.43
Quora78.8685.1886.95
SCIDOCS14.9015.3916.98
SciFact67.8970.271.48
TREC-COVID59.4775.0081.04
Webis-touché202044.2232.1231.70
Average43.0849.8250.37

Find more in our blog-post.

2. Retrieval Performance#

We also test our model's performance on retrieval tasks on a subset of the BEIR benchmarks. We'll be providing the full results for the benchmark soon (actively working on it).

Due to resource limitations, we only test our model on three beir tasks. NDCG@10 servers as the main metric.

ModelColBERTv2Jina-ColBERT-V1mxbai-colbert-large-v1
NFCorpus33.733.836.5
SciFact68.970.171.3
TREC-COVID72.675.080.5

Although our ColBERT also performs well on retrieval tasks, we still recommend using our flagship embedding model mixedbread-ai/mxbai-embed-large-v1 for that.

Community#

Please join our Discord Community and share your feedback and thoughts! We are here to help and also always happy to chat.

License#

Apache 2.0

Files

13 files · 3.01 GBWeights 671 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 13 files with their sha256
FileSizesha256
.gitattributes1.56 KBae0aef653cb4215c3e40122f92d3a3a0bda4559a482795645284ce42e626a806
LICENSE10.8 KB4b0dfefcb74f1e50a8df72a9f2bf0088753f8568bc479387292469b4948705d4
README.md47.4 KB9d3564fd7990a76236155aba8580a64ddc3f5960bf34d4fed18972d794fedae4
artifact.metadata1.53 KB19500fb061b8b11c88aceea91de652da7c0830e3b7b4e07995ad520b115a5cc2
config.json674 Bee0d1ad785b8a0d6423dc1ef6568e6dac512b4bdba7bc3d763a87b5c16434f23
model.safetensors671 MB1a66baadbcbf529a00cd2fb21c00a5658fbd9a04ae131ec2e4822c10c8327245
onnx/model.onnx1.34 GB5bb56be92d5b571548330fc7a30a720dbc8bc8c4c7a5788d0cbc4a04a67cf2f9
onnx/model_fp16.onnx669 MBe6a3929fbc21b26bcdef3dfe2557bc5e03142028a50f6d64f38ad6c8139a9e7d
onnx/model_int8.onnx336 MBdc3138c406f4459d7ea7906eb3e690e95daecfc3d1227432b112d0715f72ba80
special_tokens_map.json695 B5d5b662e421ea9fac075174bb0688ee0d9431699900b90662acd44b2a350503a
tokenizer.json711 KBd241a60d5e8f04cc1b2b3e9ef7a4921b27bf526d9f6050ab90f9267a1f9e5c66
tokenizer_config.json1.24 KB0b29c7bfc889e53b36d9dd3e686dd4300f6525110eaa98c76a5dafceb2029f53
vocab.txt232 KB07eced375cec144d27c900241f3e339478dec958f92fddbc551f295c992038a3
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
d092c678f4 pinned now manifest updated, same commit2026-11-14 21:09 UTC13 files · 3.01 GB
d092c678f42026-11-14 21:09 UTC13 files · 3.01 GB

Use it

$ fw get mixedbread-ai/mxbai-colbert-large-v1
# manifest sha256 1e035a054fc6… · 3.01 GB · 13 files
$ fw verify ./mxbai-colbert-large-v1 mixedbread-ai/mxbai-colbert-large-v1
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-colbert-large-v1.json --dir ./mxbai-colbert-large-v1 $ python3 fw.py verify ./mxbai-colbert-large-v1 ./mixedbread-ai__mxbai-colbert-large-v1.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mixedbread-ai/mxbai-colbert-large-v1 --revision d092c678f449647d1945569dc17b4d8917a687e0 --local-dir ./mxbai-colbert-large-v1
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModel, AutoTokenizer tok = AutoTokenizer.from_pretrained("mixedbread-ai/mxbai-colbert-large-v1", revision="d092c678f449647d1945569dc17b4d8917a687e0") model = AutoModel.from_pretrained("mixedbread-ai/mxbai-colbert-large-v1", revision="d092c678f449647d1945569dc17b4d8917a687e0", device_map="auto")

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-colbert-large-v1Date: 2026-11-14Commit: d092c67Signed: 2DC28CC7B26A283B ✓
Upstream
mixedbread-ai/mxbai-colbert-large-v1
Pinned commit
d092c678f449647d1945569dc17b4d8917a687e0
Manifest
mxbai-colbert-large-v1.json · .minisig
Manifest sha256
1e035a054fc67bf436588ae718bf86bb5b5082b52c27d094efc856bd7dce3dec
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-colbert-large-v1.json $ curl -O https://freeweights.allternit.com/manifests/mixedbread-ai/mxbai-colbert-large-v1.json.minisig $ minisign -Vm mxbai-colbert-large-v1.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-colbert-large-v1
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. mxbai-colbert-large-v1.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