Skip to content
Local AI Wizard
Your machine
Theme

olmOCR-2-7B-1025-FP8

allenai · allenai/olmOCR-2-7B-1025-FP8

Weights license: Apache 2.0 · code and components may use other terms

Reported by the publisher8 resultsallenai's model card · read 2026-10-25 · not ranked · see them
Parameters8.3 BHub safetensors total
Repository updated2026-02-19A commit is not a release date

Not benchmarked or estimated yet

No comparable score, no memory figure to match against hardware and no published speed measurement for this checkpoint. Nothing is guessed.

How to run

Runtime compatibility and speed have not been measured for this entry. Published metadata does not prove a successful local run; check the files and terms at the source first.

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Setup stated first by the source · Transformers
pip install olmocr>=0.4.0
Transformers · model card · Manual Prompting
import torch
import base64
import urllib.request

from io import BytesIO
from PIL import Image
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration

from olmocr.data.renderpdf import render_pdf_to_base64png
from olmocr.prompts import build_no_anchoring_v4_yaml_prompt

# Initialize the model
model = Qwen2_5_VLForConditionalGeneration.from_pretrained("allenai/olmOCR-2-7B-1025-FP8", device_map="auto").eval()
processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

# Grab a sample PDF
urllib.request.urlretrieve("https://olmocr.allenai.org/papers/olmocr.pdf", "./paper.pdf")

# Render page 1 to an image
image_base64 = render_pdf_to_base64png("./paper.pdf", 1, target_longest_image_dim=1288)


# Build the full prompt
messages = [
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": build_no_anchoring_v4_yaml_prompt()},
                    {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{image_base64}"}},
                ],
            }
        ]

# Apply the chat template and processor
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
main_image = Image.open(BytesIO(base64.b64decode(image_base64)))

inputs = processor(
    text=[text],
    images=[main_image],
    padding=True,
    return_tensors="pt",
)
inputs = {key: value.to(device) for (key, value) in inputs.items()}


# Generate the output
output = model.generate(
            **inputs,
            temperature=0.1,
            max_new_tokens=50,
            num_return_sequences=1,
            do_sample=True,
        )

# Decode the output
prompt_length = inputs["input_ids"].shape[1]
new_tokens = output[:, prompt_length:]
text_output = processor.tokenizer.batch_decode(
    new_tokens, skip_special_tokens=True
)

print(text_output)
# ['---\nprimary_language: en\nis_rotation_valid: True\nrotation_correction: 0\nis_table: False\nis_diagram: False\n---\nolmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models\n\nJake Poz']

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / source
allenai/olmOCR-2-7B-1025-FP8
Task
image-text-to-text
Architecture
Qwen2_5_VLForConditionalGeneration
Library in source
transformers
Weight license
Apache 2.0
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Languages
enModel card metadata · read 2026-10-25source
Every stored field12 fields
Revision checked
40bd7202494b8264ee17ada08b401b5aab7a9ce1
Architecture
Qwen2_5_VLForConditionalGeneration
Library
transformers
Hub task tag
image-text-to-text
Declared base models
Qwen/Qwen2.5-VL-7B-Instruct
Formats
transformers, safetensors
Access
Open download
Publisher kind
Official
Repository created
2025-10-06creation is not the model's release
Repository updated
2026-02-19a commit is not a release date
Hub downloads (30 days) · likes
81,434 · 258this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Valid source snapshot: 2026-09-26. This source record has not received a complete technical review. Missing data remain unknown; a repository commit is not a model release date.