Update app.py

app.py

@@ -5,7 +5,7 @@ import torch
 # Load the Hugging Face model and tokenizer
 model_name = "HuggingFaceH4/zephyr-7b-beta"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
 
 # Define custom system content
 custom_system_content = """
@@ -15,7 +15,7 @@ Please provide thoughtful and concise responses.
 
 # Function to generate chatbot responses
 def chatbot_response(user_input):
-    inputs = tokenizer(custom_system_content + user_input, return_tensors="pt").to("cuda")
+    inputs = tokenizer(custom_system_content + user_input, return_tensors="pt")
     outputs = model.generate(**inputs, max_length=256)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return response[len(custom_system_content):]
@@ -28,7 +28,7 @@ with gr.Blocks() as demo:
     with gr.Row():
         with gr.Column():
             user_input = gr.Textbox(label="Your message", placeholder="Type your message here...")
-            chatbot_output = gr.Textbox(label="Chatbot Response", placeholder="Chatbot will respond here...")
+            chatbot_output = gr.Chatbot(label="Chatbot Response", placeholder="Chatbot will respond here...")
 
         with gr.Column():
             submit_btn = gr.Button("Send")