Update app.py

app.py

@@ -1,21 +1,22 @@
 from huggingface_hub import InferenceClient
 import gradio as gr
 
-client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
+client = InferenceClient(
+    "mistralai/Mixtral-8x7B-Instruct-v0.1"
+)
+
 
-def tokenize(text):
-    return text
-    # return tok.encode(text, add_special_tokens=False)
-    
 def format_prompt(message, history):
-    prompt = ""
-    for user_prompt, bot_response in history:
-        prompt += "<s>" + tokenize("[INST]") + tokenize(user_prompt) + tokenize("[/INST]")
-        prompt += tokenize(bot_response) + "</s> "
-    prompt += tokenize("[INST]") + tokenize(message) + tokenize("[/INST]")
-    return prompt
+  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 generate(prompt, history, temperature=0.2, max_new_tokens=512, top_p=0.95, repetition_penalty=1.0):
+def generate(
+    prompt, history, system_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
+):
     temperature = float(temperature)
     if temperature < 1e-2:
         temperature = 1e-2
@@ -30,8 +31,7 @@ def generate(prompt, history, temperature=0.2, max_new_tokens=512, top_p=0.95, r
         seed=42,
     )
 
-    formatted_prompt = format_prompt(prompt, history)
-
+    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
 
@@ -49,7 +49,7 @@ additional_inputs=[
     ),
     gr.Slider(
         label="Temperature",
-        value=0.2,
+        value=0.9,
         minimum=0.0,
         maximum=1.0,
         step=0.05,
@@ -58,7 +58,7 @@ additional_inputs=[
     ),
     gr.Slider(
         label="Max new tokens",
-        value=512,
+        value=256,
         minimum=0,
         maximum=1048,
         step=64,
@@ -67,7 +67,7 @@ additional_inputs=[
     ),
     gr.Slider(
         label="Top-p (nucleus sampling)",
-        value=0.95,
+        value=0.90,
         minimum=0.0,
         maximum=1,
         step=0.05,
@@ -76,7 +76,7 @@ additional_inputs=[
     ),
     gr.Slider(
         label="Repetition penalty",
-        value=1,
+        value=1.2,
         minimum=1.0,
         maximum=2.0,
         step=0.05,
@@ -85,15 +85,19 @@ additional_inputs=[
     )
 ]
 
-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, 
-                        chatbot=mychatbot,
-                        additional_inputs=additional_inputs,
-                        title="Kamran's Mixtral 8x7b Chat",
-                        retry_btn=None,
-                        undo_btn=None
-                       )
+examples=[["I'm planning a vacation to Japan. Can you suggest a one-week itinerary including must-visit places and local cuisines to try?", None, None, None, None, None, ],
+          ["Can you write a short story about a time-traveling detective who solves historical mysteries?", None, None, None, None, None,],
+          ["I'm trying to learn French. Can you provide some common phrases that would be useful for a beginner, along with their pronunciations?", None, None, None, None, None,],
+          ["I have chicken, rice, and bell peppers in my kitchen. Can you suggest an easy recipe I can make with these ingredients?", None, None, None, None, None,],
+          ["Can you explain how the QuickSort algorithm works and provide a Python implementation?", None, None, None, None, None,],
+          ["What are some unique features of Rust that make it stand out compared to other systems programming languages like C++?", None, None, None, None, None,],
+         ]
 
-demo.queue().launch(show_api=False)
+gr.ChatInterface(
+    fn=generate,
+    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
+    additional_inputs=additional_inputs,
+    title="Mixtral 46.7B",
+    examples=examples,
+    concurrency_limit=20,
+).launch(show_api=False)