Update README.md

README.md

@@ -108,12 +108,13 @@ pip install flash-attn --no-build-isolation
 Then you could use our model:
 ```python
 from transformers import AutoModel, AutoTokenizer
+import torch
 
 # model setting
 model_path = 'OpenGVLab/VideoChat-Flash-Qwen2-7B_res224'
 
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
-model = AutoModel.from_pretrained(model_path, trust_remote_code=True).half().cuda()
+model = AutoModel.from_pretrained(model_path, trust_remote_code=True).to(torch.bfloat16).cuda()
 image_processor = model.get_vision_tower().image_processor
 
 mm_llm_compress = False # use the global compress or not