Update app.py

app.py

@@ -1,3 +1,68 @@
 import gradio as gr
+from huggingface_hub import InferenceClient
 
-gr.load("nold/starcoder2-15b-GGUF").launch()
+"""
+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("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
+
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    max_tokens,
+    temperature,
+    top_p,
+):
+
+    name = "Ernest"
+
+    system_message = f"""You are an expert programmer called {name}, who knows Python, PHP, CoffeeScript and Javascript. You are to assist users in solving their coding problems."""
+    
+    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})
+
+    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
+
+        if token:
+            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.Slider(minimum=1, maximum=8192, value=6144, 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=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()