Update app.py

app.py

@@ -1,12 +1,18 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 import os
+
 """
-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
+For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/en/guides/inference
 """
-client = InferenceClient("meta-llama/Llama-3.2-1B")
-os.environ["HF_TOKEN"] 
 
+# Retrieve the Hugging Face token
+hf_token = os.environ.get("HF_TOKEN")
+if not hf_token:
+    raise ValueError("Please set the HF_TOKEN environment variable with your Hugging Face API token.")
+
+# Initialize the InferenceClient with a correct model
+client = InferenceClient("meta-llama/Llama-3.2-1B-Instruct", token=hf_token)
 
 def respond(
     message,
@@ -18,48 +24,51 @@ def respond(
 ):
     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]})
+    for user_input, assistant_response in history:
+        if user_input:
+            messages.append({"role": "user", "content": user_input})
+        if assistant_response:
+            messages.append({"role": "assistant", "content": assistant_response})
 
     messages.append({"role": "user", "content": message})
 
     response = ""
 
-    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
-
+    # Start the chat completion
+    try:
+        for msg in client.chat_completion(
+            messages=messages,
+            max_new_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            token = msg.delta.get("content", "")
+            response += token
+            yield response
+    except Exception as e:
+        yield f"Error during inference: {e}"
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=2048, 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=1, maximum=1024, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, step=0.01, label="Temperature"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
             value=0.95,
-            step=0.05,
+            step=0.01,
             label="Top-p (nucleus sampling)",
         ),
     ],
+    title="Chat with Llama 2",
+    description="A chat interface using Llama 2 model via Hugging Face Inference API.",
 )
 
-
 if __name__ == "__main__":
     demo.launch()