Revert changes

app.py

@@ -1,4 +1,3 @@
-import os
 import threading
 import time
 
@@ -11,8 +10,6 @@ LLM = Llama.from_pretrained(
     repo_id="mradermacher/ZEUS-8B-V2-i1-GGUF",
     filename="*Q4_K_M.gguf",
     chat_format="chatml",
-    n_threads=os.cpu_count(),
-    verbose=True
 )
 
 
@@ -75,8 +72,8 @@ if __name__ == "__main__":
         type="messages",
         additional_inputs=[
             gr.Textbox(value="You are a friendly assistant.", label="System message"),
-            gr.Slider(minimum=200, maximum=4096, value=1024, step=2, label="Max new tokens"),
-            gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.05, label="Temperature"),
+            gr.Slider(minimum=1, maximum=2048, value=1024, step=1, label="Max new tokens"),
+            gr.Slider(minimum=0.1, maximum=4.0, value=0.8, step=0.1, label="Temperature"),
             gr.Slider(
                 minimum=0.1,
                 maximum=1.0,