Update app.py

app.py

@@ -22,6 +22,12 @@ model_id = "mistralai/Mistral-7B-v0.3"
 model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
 
 
+tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)
+
+model = AutoModelForCausalLM.from_pretrained(model_id, token= token, torch_dtype=torch.bfloat16,    
+                                             # attn_implementation="flash_attention_2",
+                                            )
+
 
 
 @spaces.GPU(duration=180)
@@ -34,11 +40,7 @@ def respond(
     top_p,
 ):
     
-    tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)
-
-    model = AutoModelForCausalLM.from_pretrained(model_id, token= token, torch_dtype=torch.bfloat16,attn_implementation="flash_attention_2",)
-
-
+  
     messages = [
     {"role": "user", "content": "What is your favourite condiment?"},
     {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},