Update app.py

app.py

@@ -6,7 +6,7 @@ import os
 hf_token = os.environ.get("HF_TOKEN")
 
 # Your model ID
-model_id = "mistral-community/Mistral-7B-v0.2"
+model_id = "mistralai/Mistral-7B-Instruct-v0.2
 
 # Load the tokenizer
 tokenizer = AutoTokenizer.from_pretrained(model_id, token=hf_token)
@@ -41,9 +41,11 @@ def generate(
 
     formatted_prompt = format_prompt(prompt, history)
 
-    inputs = tokenizer.apply_chat_template(formatted_prompt, return_tensors="pt").to("cuda")
+    
 
-    strea = model.generate(inputs, **generate_kwargs, stream=True, details=True, return_full_text=False)
+
+    inputs = tokenizer.apply_chat_template(formatted_prompt, return_tensors="pt")
+    stream = model.generate(inputs, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
 
     for response in stream: