Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 import os
 import spaces
-from transformers import GemmaTokenizer, AutoModelForCausalLM
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 from threading import Thread
 
@@ -12,35 +11,10 @@ HF_TOKEN = os.environ.get("HF_TOKEN", None)
 DESCRIPTION = '''
 <div>
 <h1 style="text-align: center;">Mistral 7B Instruct v0.3</h1>
-<p>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3"><b>mistralai/Mistral-7B-Instruct-v0.3</b></a>. The Mistral-7B-Instruct-v0.3 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.3, which is a Mistral-7B-v0.2 with extended vocabulary. Feel free to play with it, or duplicate to run privately!</p>
-<p>🔎 For more details about the release and how to use the model with <code>transformers</code>, visit the model-card linked above.</p>
-<p>🦕 The Instruct model - Has Extended vocabulary to 32768. Supports v3 Tokenizer. Supports function calling.</p>
 </div>
 '''
 
 
-PLACEHOLDER = """
-<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
-   <img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/models/mistralai/Mistral-7B-Instruct-v0.3.png" style="width: 70%; max-width: 550px; height: auto; opacity: 0.55;  "> 
-   <p style="font-size: 20px; margin-bottom: 2px; opacity: 0.65;">Ask me anything...</p>
-</div>
-"""
-
-
-css = """
-h1 {
-  text-align: center;
-  display: block;
-}
-
-#duplicate-button {
-  margin: auto;
-  color: white;
-  background: #1565c0;
-  border-radius: 100vh;
-}
-"""
-
 # Load the tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
 model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3", device_map="auto")
@@ -92,44 +66,14 @@ def chat_mistral7b_v0dot3(message: str,
     outputs = []
     for text in streamer:
         outputs.append(text)
-        #print(outputs)
         yield "".join(outputs)
-        
-
-# Gradio block
-chatbot=gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface')
 
-with gr.Blocks(fill_height=True, css=css) as demo:
+with gr.Blocks() as demo:
     
-    gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
-    gr.ChatInterface(
+    gr.Interface(
         fn=chat_mistral7b_v0dot3,
-        chatbot=chatbot,
-        fill_height=True,
-        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
-        additional_inputs=[
-            gr.Slider(minimum=0,
-                      maximum=1, 
-                      step=0.1,
-                      value=0.95, 
-                      label="Temperature", 
-                      render=False),
-            gr.Slider(minimum=128, 
-                      maximum=4096,
-                      step=1,
-                      value=512, 
-                      label="Max new tokens", 
-                      render=False ),
-            ],
-        examples=[
-            ['How to setup a human base on Mars? Give short answer.'],
-            ['Explain theory of relativity to me like I’m 8 years old.'],
-            ['What is 9,000 * 9,000?'],
-            ['Write a pun-filled happy birthday message to my friend Alex.'],
-            ['Justify why a penguin might make a good king of the jungle.']
-            ],
-        cache_examples=False,
+        inputs=[gr.Textbox(), gr.Textbox(), gr.Numbers(), gr.Numbers()],
+        outputs=[gr.Texbox()]
                      )