Update app.py

app.py

@@ -77,7 +77,7 @@ def respond(request, file_content, system_message, max_tokens, temperature, top_
         
         # Generate response with streaming
         response = ""
-        streamer = TextIteratorStreamer(tokenizer, skip_special_tokens=True)
+        streamer = TextIteratorStreamer(tokenizer,skip_prompt = True , skip_special_tokens=True)
         
         generation_kwargs = dict(
             input_ids=inputs["input_ids"],
@@ -138,8 +138,8 @@ with gr.Blocks() as demo:
         temperature = gr.Slider(
             minimum=0.1,
             maximum=4.0,
-            value=0.7,
-            step=1,
+            value=1,
+            step=0.5,
             label="Temperature"
         )
         top_p = gr.Slider(