Update app.py

app.py

@@ -1,10 +1,7 @@
 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 format_prompt(message, history):
   prompt = "<s>"
@@ -15,7 +12,7 @@ def format_prompt(message, history):
   return prompt
 
 def generate(
-    prompt, history, system_prompt, temperature=0.9, max_new_tokens=1024, 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,
 ):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -31,7 +28,8 @@ def generate(
         seed=42,
     )
 
-    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
+    formatted_prompt = format_prompt(prompt, history)
+
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
 
@@ -40,64 +38,15 @@ def generate(
         yield output
     return output
 
+    
+mychatbot = gr.Chatbot(
+    avatar_images=["./user.png", "./botm.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
 
-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=256,
-        minimum=0,
-        maximum=1048,
-        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",
-    )
-]
-
-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 = gr.ChatInterface(fn=generate, 
+                        chatbot=mychatbot,
+                        title="globecen Mixtral 8x7b Chat",
+                        retry_btn=None,
+                        undo_btn=None
+                       )
 
-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="globecen bot",
-    examples=examples,
-    concurrency_limit=20,
-).launch(show_api=False)
+demo.queue().launch(show_api=False)