Update app.py

app.py

@@ -55,7 +55,7 @@ def load_model(model_name):
             tokenizer.pad_token = tokenizer.eos_token
             tokenizer.add_special_tokens({'pad_token': tokenizer.eos_token})
         
-        model = AutoModelForCausalLM.from_pretrained(models[model_name], token=hugging_face_token, trust_remote_code=True).to("cuda")
+        model = AutoModelForCausalLM.from_pretrained(models[model_name], token=hugging_face_token, trust_remote_code=True)
         selected_model = model_name
     except Exception as e:
         print(f"Error loading model {model_name}: {e}")
@@ -89,7 +89,7 @@ def interact(user_input, history, interaction_count):
         prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
         
         # Generate response using selected model
-        input_ids = tokenizer(prompt, return_tensors='pt').input_ids.to("cuda")
+        input_ids = tokenizer(prompt, return_tensors='pt').input_ids
         chat_history_ids = model.generate(input_ids, max_new_tokens=100, pad_token_id=tokenizer.eos_token_id, temperature=0.1)
         response = tokenizer.decode(chat_history_ids[:, input_ids.shape[-1]:][0], skip_special_tokens=True)