Update app.py

app.py

@@ -94,15 +94,18 @@ def generate_response(model, tokenizer, instruction, max_new_tokens=2048):
 @app.post("/generate")
 async def generate_text(input: ModelInput):
     try:
+        print(f"Received prompt: {input.prompt}")  # Log the prompt received
         response = generate_response(
             model=model,
             tokenizer=tokenizer,
             instruction=input.prompt,
             max_new_tokens=input.max_new_tokens
         )
+        print(f"Generated response: {response}")  # Log the generated response
         return {"generated_text": response}
 
     except Exception as e:
+        print(f"Error: {str(e)}")  # Log the error
         raise HTTPException(status_code=500, detail=str(e))
 
 @app.get("/")