Update app.py

app.py

@@ -1,26 +1,31 @@
-
-
 # Import required libraries
 import gradio as gr
-from huggingface_hub import InferenceClient
 from transformers import pipeline
 import torch
-import huggingfacehub as infer
 import threading
 import time
 import tensorflow as tf
-from transformers import pipeline
-
-
-
-
-
 
 # Initialize the text generation pipeline with the specified model
-pipe = pipeline("text-generation", model="chargoddard/Yi-34B-Llama", device=0)
+pipe = pipeline("text-generation", model="chargoddard/Yi-34B-Llama")
 
 def respond(
     message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
 
     response = ""
 
@@ -33,19 +38,25 @@ def respond(
         top_p=top_p,
     )
 
-
     response = result[0]['generated_text']
-    yield response)
+    yield response
 
 # Gradio interface setup
-
-
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()