CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.olmo / olmOCR-7B-0825
From: allenai <huggingface.co/allenai>Newsgroups: alt.freeweights.olmoSubject:

olmOCR-7B-0825

Date: 2026-11-15Commit: f146341Signed: 2DC28CC7B26A283B ✓

Image text to text model with 8.3B parameters. Safetensors weights, 16.6 GB in all. Published by allenai under Apache-2.0.

8.3B params16.6GBolmOCR-7B-0825safetensorspermissive
FactsParams8.3BSize16.6 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get allenai/olmOCR-7B-0825
# manifest sha256 5034a11a7734… · 16.6 GB · 16 files
$ fw verify ./olmOCR-7B-0825 allenai/olmOCR-7B-0825
From sourceHosted (signed)allenai/olmOCR-7B-0825Last check: 2026-11-15 03:48 UTC
Run at homeGet help

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

Fine-tune of Qwen2.5-VL-7B-Instruct.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
16.6 GB
Weights
16.6 GB (safetensors)
Parameters
8.3B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
16, each with a sha256
Publisher
allenai
Added
2026-11-15
Section
alt.freeweights.olmo
Lineage

Original release from the publisher.

Base model: Qwen/Qwen2.5-VL-7B-Instruct

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.co2026-11-15 03:48 UTCpassed

Model card

From the publisher at commit f146341. Shown as plain text with links; images open at the publisher.

Image: olmOCR Logo

olmOCR-7B-0825#

This is a release of the olmOCR model that's fine tuned from Qwen2.5-VL-7B-Instruct using the olmOCR-mix-0225 dataset.

Quick links:

The best way to use this model is via the olmOCR toolkit. The toolkit comes with an efficient inference setup via sglang that can handle millions of documents at scale.

Usage#

This model expects as input a single document image, rendered such that the longest dimension is 1288 pixels.

The prompt must then contain the additional metadata from the document, and the easiest way to generate this is to use the methods provided by the olmOCR toolkit.

License and use#

olmOCR is licensed under the Apache 2.0 license. olmOCR is intended for research and educational use. For more information, please see our Responsible Use Guidelines.

Files

16 files · 16.6 GBWeights 16.6 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 16 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md1.57 KBeba556cd38283d30ec9b3740aa74ee9ae29b82ba403d78d762b93a284cc8f1bc
chat_template.json1.05 KBad60d90252ed0b0705ba14e2d0ad0fec0beac1ea955642b54059b36052d8bc96
config.json2.52 KB28ef0ce510b3b55f738c8100833bd27bf32b1edbe4934928ef58e99149589df3
generation_config.json260 B549bd3dd57183a0aab12c3cb40dd25644fb0f600e379541a1bfeaa745a703bec
merges.txt1.67 MB599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3
model-00001-of-00004.safetensors4.97 GB12a5d1b872ceb83af0be03b7db7d53379a4c57f72d9275b3a8642887cc04a305
model-00002-of-00004.safetensors4.99 GB8870622ece88dfc0e65173f0216e5b010323e76ab4203e973e2522000f360b29
model-00003-of-00004.safetensors4.93 GB013399fe44dd3441cf19b60acd17e9260999f3c04007cdab80238f8b9143d28b
model-00004-of-00004.safetensors1.69 GBf5a2b7b1d588ade04ec181d021ec078b4d56b3b6cfdd6d8cffceaee7678a9c5a
model.safetensors.index.json57.6 KB3067e9b0f35596ff3426a0d0ec8c982a51fa1e110c4fc30dcf3be9ea37409df6
preprocessor_config.json350 Bf2058c716eef96ccaed1cc1e2d0c08306b62586d535b28d9d08e691b2fab7ca0
tokenizer.json7.03 MBc0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539
tokenizer_config.json5.70 KB4abd3520120e266da84c0864fee064d1fb10806f02225911a47253dd38dc5f56
training_state.pt1.37 KB362155aa92b7f3a759b57478ade6cdabc99bf486beab2b92010becf3a21a726a
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
f1463418cd pinned now2026-11-15 03:48 UTC16 files · 16.6 GB

Use it

$ fw get allenai/olmOCR-7B-0825
# manifest sha256 5034a11a7734… · 16.6 GB · 16 files
$ fw verify ./olmOCR-7B-0825 allenai/olmOCR-7B-0825
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/allenai/olmOCR-7B-0825.json --dir ./olmOCR-7B-0825 $ python3 fw.py verify ./olmOCR-7B-0825 ./allenai__olmOCR-7B-0825.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download allenai/olmOCR-7B-0825 --revision f1463418cd4cc4af00a1db889378f72b53ebcaa6 --local-dir ./olmOCR-7B-0825
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("allenai/olmOCR-7B-0825", revision="f1463418cd4cc4af00a1db889378f72b53ebcaa6") model = AutoModelForImageTextToText.from_pretrained("allenai/olmOCR-7B-0825", revision="f1463418cd4cc4af00a1db889378f72b53ebcaa6", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve allenai/olmOCR-7B-0825 --revision f1463418cd4cc4af00a1db889378f72b53ebcaa6
Run at home

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. 2026-11-15
Text in
README.md
Text sha256
eba556cd38283d30ec9b3740aa74ee9ae29b82ba403d78d762b93a284cc8f1bc
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: allenai <huggingface.co/allenai>Newsgroups: alt.freeweights.olmoSubject: olmOCR-7B-0825Date: 2026-11-15Commit: f146341Signed: 2DC28CC7B26A283B ✓
Upstream
allenai/olmOCR-7B-0825
Pinned commit
f1463418cd4cc4af00a1db889378f72b53ebcaa6
Manifest
olmOCR-7B-0825.json · .minisig
Manifest sha256
5034a11a7734d4fb0439c2bdad7ffa5f78425d80504e9d40be9a7bbf50608bd1
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:48 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/allenai/olmOCR-7B-0825.json $ curl -O https://freeweights.allternit.com/manifests/allenai/olmOCR-7B-0825.json.minisig $ minisign -Vm olmOCR-7B-0825.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

Parent

Qwen/Qwen2.5-VL-7B-Instruct · this model is a finetune of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download allenai/olmOCR-7B-0825
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. olmOCR-7B-0825.json. Provenance. Takedown history: none.
Source
huggingface.co/allenai/olmOCR-7B-0825

Related models

All of alt.freeweights.olmo →
From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3-7B-Instruct-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3-7B-Think-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3.1-32B-Instruct-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3.1-32B-Think-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_olmOCR-2-7B-1025-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_olmOCR-7B-0225-preview-GGUF