Update app.py

app.py

@@ -8,15 +8,28 @@ tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
 
 @spaces.GPU(duration=120)
-def predict(message, history):
+def predict(message, history, temperature, top_p):
     history.append({"role": "user", "content": message})
     input_text = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True)
     inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)  
-    outputs = model.generate(inputs, max_new_tokens=1024, temperature=0.7, top_p=0.9, do_sample=True)
+    outputs = model.generate(
+        inputs, 
+        max_new_tokens=1024, 
+        temperature=float(temperature), 
+        top_p=float(top_p), 
+        do_sample=True
+    )
     decoded = tokenizer.decode(outputs[0])
     response = decoded.split("<|start_header_id|>assistant<|end_header_id|>\n\n")[-1]
     return response
 
-demo = gr.ChatInterface(predict, type="messages")
+with gr.Blocks() as demo:
+    chatbot = gr.ChatInterface(
+        predict,
+        additional_inputs=[
+            gr.Slider(0.1, 2.0, value=0.7, step=0.1, label="Temperature"),
+            gr.Slider(0.1, 1.0, value=0.9, step=0.05, label="Top-P")
+        ]
+    )
 
 demo.launch()