Update app.py

app.py

@@ -48,7 +48,7 @@ def respond(
 
     # Format the conversation as a single string for the model
     prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, padding=True, max_length=1000)
+    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, padding=True, max_length=512)
     
     # Move inputs to device
     input_ids = inputs['input_ids'].to(device)
@@ -78,10 +78,10 @@ def respond(
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a Medical AI Assistant. Please be thorough and provide an informative answer. If you don't know the answer to a specific medical inquiry, advise seeking professional help.", label="System message", lines=3),
+        gr.Textbox(value="You are a Medical AI Assistant. You should help to answer the health issue. Please be thorough and provide an informative answer. If you don't know the answer to a specific medical inquiry, advise seeking professional help.", label="System message", lines=3),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="Top-p (nucleus sampling)"),
     ],
     title="Medical AI Assistant",
     description="Give me your symptoms and ask me a health problem. The AI will provide informative answers. If the AI doesn't know the answer, it will advise seeking professional help.",