Update app.py

app.py

@@ -16,11 +16,13 @@ model_name = "Qwen/Qwen2.5-7B-Instruct"
 # )
 # model = Qwen2VLForConditionalGeneration.from_pretrained(model_name, trust_remote_code=True, torch_dtype="auto").cuda().eval()
 # model = Qwen2VLForConditionalGeneration.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda").eval()
+
+# tokenizer = AutoTokenizer.from_pretrained(model_name)
+
 model = Qwen2VLForConditionalGeneration.from_pretrained(
-    "Qwen/Qwen2-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
+    "Qwen/Qwen2-VL-72B-Instruct-AWQ", torch_dtype="auto", device_map="auto"
 )
 processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
-# tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 @spaces.GPU
 def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):
@@ -36,7 +38,6 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
             ],
         }
     ]
-    
     # Preparation for inference
     text = processor.apply_chat_template(
         messages, tokenize=False, add_generation_prompt=True