Update app.py

app.py

@@ -8,17 +8,23 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
 
 
-def generate_response(prompt):
+def generate_response(prompt, temperature):
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
     outputs = model.generate(
         **inputs,
         do_sample=True,
-        temperature=1.0,
+        temperature=temperature,
         top_p=0.9
     )
 
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
     # return "Hello " + name + "!!"
 
-demo = gr.Interface(fn=generate_response, inputs="text", outputs="text")
+demo = gr.Interface(fn=generate_response, 
+                    inputs=[
+                        gr.Textbox(label="Prompt", lines=6, placeholder="Ask something..."),
+                        gr.Slider(0.1, 1.5, value=0.7, step=0.1, label="Temperature")
+                    ], 
+                    outputs="text"
+                   )
 demo.launch()