metadata
license: other
license_name: tencent-hunyuan-community
license_link: LICENSE
tags:
- ocr
- vision-language
- document-understanding
language:
- ko
- en
BrainOCR
High-accuracy OCR model optimized for Korean and English document processing.
Based on a vision-language architecture with embedding optimization for Korean/English focus.
Features
- Korean / English document OCR
- Table, form, and structured document support
- Markdown-formatted output
- Non-target language token embeddings zeroed for improved focus
Usage
Serve with vLLM:
vllm serve braincrew-dev/BrainOCR \
--hf-overrides '{"model_type": "hunyuan_vl", "architectures": ["HunYuanVLForConditionalGeneration"]}' \
--gpu-memory-utilization 0.8 \
--max-model-len 16384 \
--trust-remote-code
License
This model is a derivative work. See LICENSE for the original license terms.