PaddlePaddle/PaddleOCR-VL

Clean up Real5-OmniDocBench evaluation metadata for PaddleOCR-VL (#100)

Add Real5-OmniDocBench evaluation results for PaddleOCR-VL (#99)

Add new model metadata so the model card gets a pointer to the newer version of the model (#97)

Update README.md

Fix PaddleOCR-VL image size inference for ambiguous RGB shapes (#96)

Update tokenizer_config.json

Update modeling_paddleocr_vl.py (#91)

Update README.md (#87)

update chat_template and tokenizer_config.json to be compatible with transformers (#80)

Update README.md

Update README.md

To rename for future compatibility with transformers (#71)

docs: Readme Updated for optimized Usage with transformers library (#60)

Update README.md

Update README.md

PaddleOCR-VL-0.9B is now officially supported on vLLM (#65)

remove unnecessary output messages from smart_resize (#61)

add pad_token_id to model’s generation_config.json to fix warning (#57)

Create LICENSE (#56)

update chat_template for TRL (#55)

Update README.md

chat_template (#49)

Update chat_template.jinja

Update README.md

Update README.md

add transformers usage of PaddleOCR-VL-0.9B (#32)

Move PaddleOCR-VL-0.9B files to root directory (#31)

Delete local imgs (#26)

Use external img url to replace local img (#25)

Update README.md

Update README.md

Update README.md

Improve model card: Add paper, code, and project page links (#15)

Update README.md

Update README.md

Adding `PaddleOCR` as the library name (#7)

update report url

Create config.json

update readme

upload formula_zh

update readme.md

`use this model` is not supported yet

update width

`use this model` is not supported yet

Upload folder using huggingface_hub

initial commit