Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-
 def respond(
     message,
     history: list[dict[str, str]],
@@ -12,34 +11,36 @@ def respond(
     hf_token: gr.OAuthToken,
 ):
     """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+    Generate a response using the Dolphin 2.9.1 Llama 3 70B model
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
+    client = InferenceClient(token=hf_token.token, model="dphn/dolphin-2.9.1-llama-3-70b")
+    
+    # Format the messages according to the ChatML template that Dolphin expects
+    formatted_prompt = f"<|im_start|>system\n{system_message}<|im_end|>\n"
+    
+    # Add history messages
+    for entry in history:
+        if entry["role"] == "user":
+            formatted_prompt += f"<|im_start|>user\n{entry['content']}<|im_end|>\n"
+        elif entry["role"] == "assistant":
+            formatted_prompt += f"<|im_start|>assistant\n{entry['content']}<|im_end|>\n"
+    
+    # Add the current user message
+    formatted_prompt += f"<|im_start|>user\n{message}<|im_end|>\n<|im_start|>assistant\n"
+    
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    
+    # Send the formatted prompt to the model
+    for token in client.text_generation(
+        formatted_prompt,
+        max_new_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
         response += token
         yield response
 
-
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
@@ -47,7 +48,7 @@ chatbot = gr.ChatInterface(
     respond,
     type="messages",
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are Dolphin, a helpful AI assistant.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
@@ -59,12 +60,15 @@ chatbot = gr.ChatInterface(
         ),
     ],
 )
-
 with gr.Blocks() as demo:
+    gr.Markdown("# Dolphin 2.9.1 Llama 3 70B Demo")
+    gr.Markdown("This is a demo of the Dolphin 2.9.1 Llama 3 70B model. Note that this model is uncensored.")
+    gr.Markdown("### Warning:")
+    gr.Markdown("This model is uncensored and may comply with any requests, including unethical ones. Use responsibly.")
+    
     with gr.Sidebar():
         gr.LoginButton()
     chatbot.render()
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()