VideoRefer-VideoLLaMA3 / requirements.txt
Lillyr's picture
init
a2e5f4e
raw
history blame
985 Bytes
--extra-index-url https://download.pytorch.org/whl/cu124
--extra-index-url https://download.pytorch.org/whl/cu121
--extra-index-url https://download.pytorch.org/whl/cu118
# basic dependencies
torch==2.4.0
torchvision==0.19.0
datasets==2.21.0
transformers==4.46.3
tokenizers==0.20.3
deepspeed==0.15.4
accelerate==1.0.1
peft==0.4.0
timm==1.0.3
numpy==1.24.4
# data processing
decord==0.6.0
imageio==2.34.0
imageio-ffmpeg==0.4.9
moviepy==1.0.3
scenedetect==0.6.3
opencv-python==4.6.0.66
pyarrow
pysubs2
ffmpeg-python
# misc
scikit-learn==1.2.2
huggingface_hub==0.23.4
sentencepiece==0.1.99
shortuuid
einops==0.6.1
einops-exts==0.0.4
bitsandbytes==0.43.3 # for cuda 124
pydantic>=2.0
markdown2[all]
gradio==5.34.0
gradio_client==1.10.3
httpx==0.24.1
requests
openai
uvicorn
fastapi
tensorboard
wandb
tabulate
Levenshtein
pycocotools==2.0.8
spaces
https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.3/flash_attn-2.7.3+cu12torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl