metadata
pipeline_tag: image-text-to-text
language:
- multilingual
tags:
- deepseek
- vision-language
- ocr
- custom_code
license: mit
library_name: transformers
base_model:
- prithivMLmods/DeepSeek-OCR-Latest-BF16.I64
- Dogacel/DeepSeek-OCR-Metal-MPS
- deepseek-ai/DeepSeek-OCR
th1nhhdk/DeepSeek-OCR-LatestTransformers-CPU
This is a DeepSeek-OCR fork, modified for CPU/MPS compatibility and patched to work with transformers version 4.57+
Refer to the original model card for more details on the model.