Update app.py

app.py

@@ -5,7 +5,7 @@ from huggingface_hub import InferenceClient
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
- 
+
 
 def respond(
     message,
@@ -14,6 +14,9 @@ def respond(
     max_tokens,
     temperature,
     top_p,
+    repetition_penalty,
+    top_k,
+    truncate,
 ):
     messages = [{"role": "system", "content": system_message}]
 
@@ -33,12 +36,16 @@ def respond(
         stream=True,
         temperature=temperature,
         top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        top_k=top_k,
+        truncate=truncate,
     ):
         token = message.choices[0].delta.content
 
         response += token
         yield response
 
+
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
@@ -55,9 +62,12 @@ demo = gr.ChatInterface(
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),
+        gr.Slider(minimum=1.0, maximum=2.0, value=1.2, step=0.1, label="Repetition Penalty"),
+        gr.Slider(minimum=1, maximum=100, value=50, step=1, label="Top-k"),
+        gr.Slider(minimum=1, maximum=2000, value=1000, step=1, label="Truncate"),
     ],
 )
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()