olmOCR-2-7B-1025 — CrispEmbed GGUF
GGUF conversion of allenai/olmOCR-2-7B-1025 (Apache-2.0, a Qwen2.5-VL-7B document-OCR fine-tune) for the CrispEmbed native runtime.
| file | quant | size | notes |
|---|---|---|---|
olmocr-2-7b-q8_0.gguf |
Q8_0 | 8.4 GiB | norms/bias/embeddings F32 |
olmocr-2-7b-q4_k.gguf |
Q4_K | 5.3 GiB | vision kept at Q8_0 floor |
Converted with models/convert-qwen2vl-to-gguf.py (F16 intermediate) and
crispembed-quantize.
Usage
crispembed --ocr-pipeline page.png --ocr-engine olmocr
The runtime auto-detects the olmOCR contract from the model name: the exact
no-anchoring fine-tune prompt, text-before-image user turn, longest-side-1288
input scaling, and 8000-token output budget. The model answers in markdown
with a YAML front-matter block (language / rotation / table / diagram flags);
CrispEmbed strips it by default (CRISPEMBED_OLMOCR_RAW=1 keeps the raw
output).
Attribution
All model weights derive from allenai/olmOCR-2-7B-1025 (Ai2), Apache-2.0.
See the upstream model card for training details and the olmOCR toolkit.
- Downloads last month
- 97
8-bit