Update app.py

app.py

@@ -71,7 +71,7 @@ def generate(prompt, history,max_new_tokens,temperature=temperature,top_p=top_p,
 
     for response in stream:
         output += response.token.text
-        yield "",[(prompt,output)]
+        yield "",[history,(prompt,output)]
 
     lines = output.strip().strip("\n").split("\n")
     #history=""
@@ -86,52 +86,7 @@ def generate(prompt, history,max_new_tokens,temperature=temperature,top_p=top_p,
             print(line)
         if line.startswith("5. "):
             print(line)            
-    return "",[(prompt,output)]
-
-
-additional_inputs=[
-    gr.Textbox(
-        label="System Prompt",
-        max_lines=1,
-        interactive=True,
-    ),
-    gr.Slider(
-        label="Temperature",
-        value=0.9,
-        minimum=0.0,
-        maximum=1.0,
-        step=0.05,
-        interactive=True,
-        info="Higher values produce more diverse outputs",
-    ),
-    gr.Slider(
-        label="Max new tokens",
-        value=1048,
-        minimum=0,
-        maximum=1048*10,
-        step=64,
-        interactive=True,
-        info="The maximum numbers of new tokens",
-    ),
-    gr.Slider(
-        label="Top-p (nucleus sampling)",
-        value=0.90,
-        minimum=0.0,
-        maximum=1,
-        step=0.05,
-        interactive=True,
-        info="Higher values sample more low-probability tokens",
-    ),
-    gr.Slider(
-        label="Repetition penalty",
-        value=1.2,
-        minimum=1.0,
-        maximum=2.0,
-        step=0.05,
-        interactive=True,
-        info="Penalize repeated tokens",
-    )
-]
+    return "",[history,(prompt,output)]
 
 
 def clear_fn():