apurba-ocr-moe / README.md
apurba-tech's picture
Upload Apurba OCR MoE weights
224f9e8 verified
|
Raw
History Blame Contribute Delete
1.11 kB
---
license: other
tags:
- ocr
- document-ai
- moe
- fp8
- vllm
- multimodal
- apurba
---
# Apurba OCR MoE
FP8-quantized mixture-of-experts vision-language model for **document layout OCR**: bounding boxes, layout categories, and text extraction from images.
## Serve with vLLM
```bash
vllm serve apurbaTech/apurba-ocr-moe \
--host 0.0.0.0 \
--port 8010 \
--max-model-len 16384 \
--gpu-memory-utilization 0.85 \
--limit-mm-per-prompt '{"image": 1, "audio": 0}' \
--mm-processor-kwargs '{"max_soft_tokens": 1120}' \
--max-num-seqs 32 \
--max-num-batched-tokens 8192
```
## Recommended inference settings
| Parameter | Value |
|-----------|-------|
| `max_soft_tokens` | `1120` |
| `max_tokens` | `8192` |
| `temperature` | `0.0` |
| Guided JSON schema | enabled |
## Integration
For preprocess → vLLM call → post-process (pixel bboxes on origin image), see the Apurba OCR MoE application repository and `docs/VLLM_INTEGRATION.md`.
## License
Subject to the license terms included with this checkpoint. Contact [Apurba Tech](https://huggingface.co/apurbaTech) for commercial use.