Multimodal-VLM-v1.0 / requirements.txt
prithivMLmods's picture
Update requirements.txt
0d8b416 verified
raw
history blame
241 Bytes
torch
torchvision
flash-attn==2.8.0.post2
transformers==4.51.3
transformers-stream-generator
qwen-vl-utils
modelscope
accelerate
openai
huggingface-hub
spaces
numpy
pillow
opencv-python
av
timm
PyMuPDF
requests
gradio
gradio_image_annotation