Update space

app.py

@@ -1,73 +1,64 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from typing import List, Dict
 
-# Initialize client with your model
-client = InferenceClient("ivwhy/lora_model")
+"""
+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
+"""
+client = InferenceClient("emeses/lab2_model")
+
 
 def respond(
-    message: str,
-    history: List[Dict[str, str]],
-    system_message: str = "You are a helpful assistant.",
-    max_tokens: int = 512,
-    temperature: float = 0.7,
-    top_p: float = 0.95,
-) -> str:
-    # Format conversation using new messages format
-    conversation = system_message + "\n\n"
-    for msg in history:
-        role = msg["role"]
-        content = msg["content"]
-        conversation += f"{role.capitalize()}: {content}\n"
-    conversation += f"User: {message}\nAssistant: "
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
 
-    # Stream response
     response = ""
-    try:
-        for token in client.text_generation(
-            conversation,
-            max_new_tokens=max_tokens,
-            temperature=temperature,
-            top_p=top_p,
-            stream=True,
-        ):
-            response += token
-            yield response
-    except Exception as e:
-        yield f"Error: {str(e)}"
 
-# Create Gradio interface
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.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
+"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(
-            value="You are a helpful assistant.", 
-            label="System message"
-        ),
-        gr.Slider(
-            minimum=1, 
-            maximum=2048, 
-            value=512, 
-            step=1, 
-            label="Max tokens"
-        ),
+        gr.Textbox(value="You are a friendly Chatbot.", 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(
-            minimum=0.1, 
-            maximum=2.0, 
-            value=0.7, 
-            step=0.1, 
-            label="Temperature"
-        ),
-        gr.Slider(
-            minimum=0.1, 
-            maximum=1.0, 
-            value=0.95, 
-            step=0.05, 
-            label="Top-p"
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
         ),
     ],
-    title="AI Assistant",
 )
 
+
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

requirements.txt

@@ -1,3 +1,2 @@
 huggingface_hub==0.25.2
 gradio>=3.50.0
-typing-extensions>=4.5.0