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
lixinhao commited on
Commit
e0fa7fc
·
verified ·
1 Parent(s): a360cc2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -119,6 +119,8 @@ model_path = 'OpenGVLab/InternVideo2_5_Chat_8B'
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
 
123
  def build_transform(input_size):
124
  MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
 
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)
124
 
125
  def build_transform(input_size):
126
  MEAN, STD = IMAGENET_MEAN, IMAGENET_STD