Hugging Face's logo

OpenGVLab
/
InternVideo2_5_Chat_8B

Video-Text-to-Text
Transformers
Safetensors
English
internvl_chat
feature-extraction
multimodal
custom_code
Eval Results (legacy)
Model card Files
xet
 Community
16
ynhe commited on
Commit
bff14a1
·
verified ·
1 Parent(s): 6dd8f38

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -117,7 +117,7 @@ from transformers import AutoModel, AutoTokenizer
117
  model_path = 'OpenGVLab/InternVideo2_5_Chat_8B'
118
 
119
  tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
120
- model = AutoModel.from_pretrained(model_path, trust_remote_code=True).half().cuda()
121
 
122
  IMAGENET_MEAN = (0.485, 0.456, 0.406)
123
  IMAGENET_STD = (0.229, 0.224, 0.225)
 
117
  model_path = 'OpenGVLab/InternVideo2_5_Chat_8B'
118
 
119
  tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
120
+ model = AutoModel.from_pretrained(model_path, trust_remote_code=True).half().cuda().to(torch.bfloat16)
121
 
122
  IMAGENET_MEAN = (0.485, 0.456, 0.406)
123
  IMAGENET_STD = (0.229, 0.224, 0.225)