Update app.py

app.py

@@ -22,14 +22,15 @@ LICENSE = """
 <p/>
 
 ---
-Built with Meta Llama 3
+CreativeWoks AI: Intelligence System for Advanced Dialogue and Organized Responses Assistance
+
 """
 
 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>
-   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Ask me anything...</p>
+   <img src="https://utfs.io/f/4c8a3309-2ac3-453b-8441-04e5c5a3ed0f-361e80.svg" style="width: 80%; max-width: 550px; height: auto; opacity: 0.55;  "> 
+   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">CreativeWorks Ai</h1>
+   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">CreativeWorks 7B Chat</p>
 </div>
 """
 
@@ -50,7 +51,7 @@ h1 {
 
 # Load the tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("CreativeWorksAi/CreativeWorks_Mistral_7b_Chat_V1")
-model = AutoModelForCausalLM.from_pretrained("CreativeWorksAi/CreativeWorks_Mistral_7b_Chat_V1", use_auth_token=HF_TOKEN, device_map="auto")
+model = AutoModelForCausalLM.from_pretrained("CreativeWorksAi/CreativeWorks_Mistral_7b_Chat_V1", token=HF_TOKEN, device_map="auto")
 #model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct", device_map="auto")  # to("cuda:0") 
 terminators = [
     tokenizer.eos_token_id,
@@ -89,6 +90,7 @@ def chat_llama3_8b(message: str,
         do_sample=True,
         temperature=temperature,
         eos_token_id=terminators,
+        pad_token_id=tokenizer.eos_token_id
     )
     # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.             
     if temperature == 0:
@@ -110,7 +112,7 @@ chatbot=gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterf
 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.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
     gr.ChatInterface(
         fn=chat_llama3_8b,
         chatbot=chatbot,
@@ -123,8 +125,8 @@ with gr.Blocks(fill_height=True, css=css) as demo:
                       value=0.95, 
                       label="Temperature", 
                       render=False),
-            gr.Slider(minimum=128, 
-                      maximum=4096,
+            gr.Slider(minimum=256, 
+                      maximum=8192,
                       step=1,
                       value=512, 
                       label="Max new tokens", 
@@ -143,5 +145,5 @@ with gr.Blocks(fill_height=True, css=css) as demo:
     gr.Markdown(LICENSE)
     
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(share=True)