alt.freeweights.qwen / olmOCR-7B-0225-preview-FP8
From: allenai <huggingface.co/allenai>Newsgroups: alt.freeweights.qwenSubject:

olmOCR-7B-0225-preview-FP8

Date: 2026-11-15Commit: 6889c39Signed: 2DC28CC7B26A283B ✓

Image text to text model with 8.3B parameters. Safetensors weights, 10.1 GB in all. Published by allenai under Apache-2.0.

8.3B params10.1GBolmOCR-7B-0225-preview-FP8safetensorspermissive
FactsParams8.3BSize10.1 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get allenai/olmOCR-7B-0225-preview-FP8
# manifest sha256 44c0ab104db1… · 10.1 GB · 16 files
$ fw verify ./olmOCR-7B-0225-preview-FP8 allenai/olmOCR-7B-0225-preview-FP8
From sourceHosted (signed)allenai/olmOCR-7B-0225-preview-FP8Last check: 2026-11-15 05:12 UTC

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

Quantized of Qwen2-VL-7B-Instruct.

Works with

Overview

Size
10.1 GB
Weights
10.1 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.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen2-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 05:12 UTCpassed

Model card

From the publisher at commit 6889c39. Shown as plain text with links; images open at the publisher.

Image: olmOCR Logo

olmOCR-7B-0225-preview-FP8#

This is the official FP8 quantized version of olmOCR-7B-0225-preview for use with the olmOCR pipeline.

Be sure you have olmOCR v0.1.75 or newer and run:

# Download a sample PDF
curl -o olmocr-sample.pdf https://olmocr.allenai.org/papers/olmocr_3pg_sample.pdf

# Convert it to markdown
python -m olmocr.pipeline ./localworkspace --markdown --pdfs olmocr-sample.pdf --model allenai/olmOCR-7B-0225-preview-FP8

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 · 10.1 GBWeights 10.1 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 16 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.11 KBddfc71185aa90f400727af936498458732c4ab1592fa242611d94bb62b1ebe51
added_tokens.json392 B7fa54985b58718a8fdb4f4d97484c4bd908db114847675e4bf3afe3e1d5d7bd4
config.json6.66 KB36830e2c1fb587f4928786e88df7c38f5e9305ec88aade1961435aa2c2e54d03
generation_config.json215 B4b0f3bea71ca65668bc7e65dc0def040af20b3e7f0991c940eb8149ac3139a7c
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00003.safetensors4.94 GB64af3e0583b66d09b1f83716632507df347369bb9908fc4c578a13668a322eb1
model-00002-of-00003.safetensors4.03 GB5c73ae2d932124e2f824a0dc3f85bfc4eeeacd8d4253abf9e0a46549d6577fd5
model-00003-of-00003.safetensors1.09 GB7897ef0fbe66cca1041bba2982a92e5aa226416cd33e4df4462c438dde6be755
model.safetensors.index.json73.5 KBd63895bef8f872f89c9761e2b1c62cc1b85a7edcdf6b61e762c4c641c02b5e39
preprocessor_config.json347 Bb5eaad0c2815f07631535dcc58f3c462b0d73693638ad21d19f3c50820eae1cc
recipe.yaml158 B5cae577124a9e040c784ee1323e381cb2cfa8c58df16f18fd4c52c6a2d2821a9
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MB091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
tokenizer_config.json4.29 KB4d40b77ead594aa030d09ea5f0cce7f7b3ebffdd4515b96fbb95152c889ac94f
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
6889c39bb6 pinned now2026-11-15 05:12 UTC16 files · 10.1 GB

Use it

$ fw get allenai/olmOCR-7B-0225-preview-FP8
# manifest sha256 44c0ab104db1… · 10.1 GB · 16 files
$ fw verify ./olmOCR-7B-0225-preview-FP8 allenai/olmOCR-7B-0225-preview-FP8
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-0225-preview-FP8.json --dir ./olmOCR-7B-0225-preview-FP8 $ python3 fw.py verify ./olmOCR-7B-0225-preview-FP8 ./allenai__olmOCR-7B-0225-preview-FP8.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download allenai/olmOCR-7B-0225-preview-FP8 --revision 6889c39bb6d0e03c02e7da36b56dc883e95e29f9 --local-dir ./olmOCR-7B-0225-preview-FP8
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-0225-preview-FP8", revision="6889c39bb6d0e03c02e7da36b56dc883e95e29f9") model = AutoModelForImageTextToText.from_pretrained("allenai/olmOCR-7B-0225-preview-FP8", revision="6889c39bb6d0e03c02e7da36b56dc883e95e29f9", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve allenai/olmOCR-7B-0225-preview-FP8 --revision 6889c39bb6d0e03c02e7da36b56dc883e95e29f9

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
ddfc71185aa90f400727af936498458732c4ab1592fa242611d94bb62b1ebe51
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.qwenSubject: olmOCR-7B-0225-preview-FP8Date: 2026-11-15Commit: 6889c39Signed: 2DC28CC7B26A283B ✓
Upstream
allenai/olmOCR-7B-0225-preview-FP8
Pinned commit
6889c39bb6d0e03c02e7da36b56dc883e95e29f9
Manifest
olmOCR-7B-0225-preview-FP8.json · .minisig
Manifest sha256
44c0ab104db19a466b1dad32b443f53c8c6324d4689c7513ec59d0d978f72409
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:12 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/allenai/olmOCR-7B-0225-preview-FP8.json $ curl -O https://freeweights.allternit.com/manifests/allenai/olmOCR-7B-0225-preview-FP8.json.minisig $ minisign -Vm olmOCR-7B-0225-preview-FP8.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-VL-7B-Instruct · this model is a quantization 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-0225-preview-FP8
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-0225-preview-FP8.json. Provenance. Takedown history: none.
From: BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen
From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1
From: BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923
From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct
From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA
From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF