How to use OpenGVLab/InternVideo2_5_Chat_8B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenGVLab/InternVideo2_5_Chat_8B", trust_remote_code=True, dtype="auto")
The error happens when when running:
model = AutoModel.from_pretrained(model_path, trust_remote_code=True).half().cuda()
· Sign up or log in to comment