Update app.py

app.py

@@ -5,16 +5,10 @@ from transformers import GemmaTokenizer, AutoModelForCausalLM
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 from threading import Thread
 
-# Set an environment variable
-HF_TOKEN = os.environ.get("HF_TOKEN", None)
-
 
 DESCRIPTION = '''
 <div>
-<h1 style="text-align: center;">Meta Llama3 8B</h1>
-<p>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct"><b>Meta Llama3 8b Chat</b></a>. Meta Llama3 is the new open LLM and comes in two sizes: 8b and 70b. Feel free to play with it, or duplicate to run privately!</p>
-<p>🔎 For more details about the Llama3 release and how to use the model with <code>transformers</code>, take a look <a href="https://huggingface.co/blog/llama3">at our blog post</a>.</p>
-<p>🦕 Looking for an even more powerful model? Check out the <a href="https://huggingface.co/chat/"><b>Hugging Chat</b></a> integration for Meta Llama 3 70b</p>
+<h1 style="text-align: center;">OpenChat 3.6</h1>
 </div>
 '''
 
@@ -22,13 +16,13 @@ LICENSE = """
 <p/>
 
 ---
-Built with Meta Llama 3
+Built with OpenChat 3.6
 """
 
 PLACEHOLDER = """
 <div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
-   <img src="https://ysharma-dummy-chat-app.hf.space/file=/tmp/gradio/8e75e61cc9bab22b7ce3dec85ab0e6db1da5d107/Meta_lockup_positive%20primary_RGB.jpg" style="width: 80%; max-width: 550px; height: auto; opacity: 0.55;  "> 
-   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">Meta llama3</h1>
+   <img src="https://raw.githubusercontent.com/imoneoi/openchat/master/assets/logo_new.png" style="width: 80%; max-width: 550px; height: auto; opacity: 0.55;  "> 
+   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">OpenChat 3.6</h1>
    <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Ask me anything...</p>
 </div>
 """
@@ -46,24 +40,30 @@ h1 {
   background: #1565c0;
   border-radius: 100vh;
 }
+
+.gradio-container{max-width: 560px !important}
+
+footer {
+    visibility: hidden
+}
 """
 
 # Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
-model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct", device_map="auto")  # to("cuda:0") 
+tokenizer = AutoTokenizer.from_pretrained("openchat/openchat-3.6-8b-20240522")
+model = AutoModelForCausalLM.from_pretrained("openchat/openchat-3.6-8b-20240522", device_map="auto")  # to("cuda:0") 
 terminators = [
     tokenizer.eos_token_id,
     tokenizer.convert_tokens_to_ids("<|eot_id|>")
 ]
 
 @spaces.GPU(duration=120)
-def chat_llama3_8b(message: str, 
+def chat_openchat_36(message: str, 
               history: list, 
               temperature: float, 
               max_new_tokens: int
              ) -> str:
     """
-    Generate a streaming response using the llama3-8b model.
+    Generate a streaming response using the openchat-3.6 model.
     Args:
         message (str): The input message.
         history (list): The conversation history used by ChatInterface.
@@ -104,14 +104,14 @@ def chat_llama3_8b(message: str,
         
 
 # Gradio block
-chatbot=gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface')
+chatbot=gr.Chatbot(height=450, placeholder=PLACEHOLDER, show_label=False)
 
 with gr.Blocks(fill_height=True, css=css) as demo:
     
     gr.Markdown(DESCRIPTION)
     gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
     gr.ChatInterface(
-        fn=chat_llama3_8b,
+        fn=chat_openchat_36,
         chatbot=chatbot,
         fill_height=True,
         additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),