Multimodal-OCR3 / requirements.txt
prithivMLmods's picture
Update requirements.txt
3e03fd3 verified
raw
history blame
516 Bytes
torch
torchvision
accelerate
einops
timm
numpy
transformers==4.55.0
transformers-stream-generator
https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.0.8/flash_attn-2.7.4.post1+cu126torch2.7-cp310-cp310-linux_x86_64.whl
huggingface_hub
sentencepiece
peft
qwen-vl-utils
hf_xet
spaces
opencv-python
albumentations
pillow
pyvips-binary
pyvips
av
supervision
pymupdf
pdf2image
python-docx
reportlab
fpdf
docling-core
html2text
markdown
requests
httpx
click
num2words
loguru
matplotlib
gradio