Update app.py

app.py

@@ -130,7 +130,7 @@ def chat_with_model(user_input, chat_history=[]):
     # Pass both user_input and context to construct_prompt
     prompt = construct_prompt(user_input, context, chat_history) # This line is changed
     print("prompt: ------------------------------------- \n"+prompt)
-    input_ids = tokenizer.encode(prompt, return_tensors="pt", truncation=True, max_length=4096).to("cuda")
+    input_ids = tokenizer.encode(prompt, return_tensors="pt", truncation=True, max_length=4096).to("cpu")
     tokenizer.pad_token = tokenizer.eos_token
     attention_mask = torch.ones_like(input_ids).to("cpu")
     outputs = model.generate(input_ids, attention_mask=attention_mask,