Update app.py

app.py

@@ -138,8 +138,9 @@ def chat_llama3_8b(message: str,
     input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
     
     streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
-    print(max_new_tokens)
+    # print(max_new_tokens)
     max_new_tokens=4096
+    temperature=0.9
     generate_kwargs = dict(
         input_ids= input_ids,
         streamer=streamer,
@@ -180,14 +181,16 @@ with gr.Blocks(fill_height=True, css=css) as demo:
                         gr.Slider(minimum=0,
                                 maximum=1, 
                                 step=0.1,
-                                value=0.95, 
+                                value=0.9, 
                                 label="Temperature", 
+                                interactive = False,
                                 render=False),
                         gr.Slider(minimum=128, 
                                 maximum=4096,
                                 step=1,
                                 value=4096, 
                                 label="Max new tokens", 
+                                interactive = False,
                                 render=False),
                         ],
                     examples=[