llama_model: "Video-LLaMA-2-7B-Finetuned/llama-2-7b-chat-hf"
imagebind_ckpt_path: "Video-LLaMA-2-7B-Finetuned/"
ckpt: 'Video-LLaMA-2-7B-Finetuned/VL_LLaMA_2_7B_Finetuned.pth' # you can use our pretrained ckpt from https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-2-13B-Pretrained/
ckpt_2: 'Video-LLaMA-2-7B-Finetuned/AL_LLaMA_2_7B_Finetuned.pth'
On both computers, it doesn't work. There's no logs when I'm uploading the file as well.
I tried multiple different jpeg, png, and mp4 files as well.
I installed Video-LLaMA on two machines, one on Google Cloud with 4 A100s and one on my person Ubuntu PC with a 4090.
I downloaded:
git clone https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-2-7B-Finetuned
My config file looks as follows:
On both computers, it doesn't work. There's no logs when I'm uploading the file as well.
I tried multiple different jpeg, png, and mp4 files as well.