Explainable-Vision-Language-Model

Running on Zero

File size: 409 Bytes

c6df80d
b9ef8a9
8bfbd60
fedbb19
 
d59f323
fedbb19
 
b9ef8a9
fedbb19
45d22e4
8e78e84
a8abdd5
a0dae6d
d41d226
c26750c
23e4b4f
ad2b5c4
be54efa
7c3ae67

torch==2.4.0
torchvision==0.19.0
transformers==4.50.0
opencv-python-headless<4.10
peft<0.14.0
timm==1.0.9
einops==0.8.0
#flash_attn
#https://github.com/Dao-AILab/flash-attention/releases/download/v2.6.3/flash_attn-2.6.3+cu123torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
sentencepiece==0.2.0
mmengine<1
accelerate
numpy<2
spaces
html2image
scipy
moviepy==1.0.3
imageio
pydantic==2.10.6
imgkit
wkhtmltopdf