Update run_model.py

run_model.py

@@ -49,7 +49,7 @@ async def generate_response(prompt: str, context: str = "", history: list = [])
     with torch.no_grad():
         prompt_text = "\n".join([f"{m['role']}: {m['content']}" for m in message])
         inputs = tokenizer(prompt_text, return_tensors="pt").to(model.device)
-        outputs = mode.generate(**inputs, **generation_args) 
+        outputs = model.generate(**inputs, **generation_args) 
         outputs = tokenizer.decode(outputs[0], skip_special_tokens=True)
         
     # return outputs[0]["generated_text"]