Update app.py

app.py

@@ -1,18 +1,19 @@
-from huggingface_hub import InferenceClient
+import os
 import gradio as gr
+from huggingface_hub import InferenceClient
 
 client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
-def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
+def format_prompt(message, history, context):
+    prompt = " "
+    for user_prompt, bot_response in history:
+        prompt += f"[INST] {user_prompt} [/{{
+    prompt += f" {context}
+    prompt += f"[INST] {message} [/
+    return prompt
 
 def generate(
-    prompt, history, temperature=0.2, max_new_tokens=4096, top_p=0.95, repetition_penalty=1.0,
+    prompt, history, temperature=0.2, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0, context="",
 ):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -28,7 +29,7 @@ def generate(
         seed=42,
     )
 
-    formatted_prompt = format_prompt(prompt, history)
+    formatted_prompt = format_prompt(prompt, history, context)
 
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
@@ -42,7 +43,7 @@ def generate(
 mychatbot = gr.Chatbot(
     avatar_images=["./user.png", "./botm.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
 
-demo = gr.ChatInterface(fn=generate, 
+demo = gr.ChatInterface(fn=generate,
                         chatbot=mychatbot,
                         title="Mixtral 8x7b Chat",
                         retry_btn=None,