---
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.