Update app.py

app.py

@@ -19,7 +19,11 @@ model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float
 def chat(input_text, history=[]):
     history.append(input_text)
     prompt = "\n".join(history) + "\nAI:"  # Simple conversational format
-    inputs = tokenizer(prompt, retur
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    output = model.generate(**inputs, max_length=512, pad_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(output[:, inputs.input_ids.shape[-1]:][0], skip_special_tokens=True)
+    history.append(f"AI: {response}")
+    return response, history
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
@@ -63,7 +67,7 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 """
 
 demo = gr.ChatInterface(
-    chat_response,
+    chat,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")