Update app.py

app.py

@@ -0,0 +1,79 @@
+import os
+import gradio as gr
+from cerebras.cloud.sdk import Cerebras
+
+client = Cerebras(
+    api_key=os.environ.get("CEREBRAS_API_KEY"),
+)
+
+TTILE = """
+<h1 align="center">Try the world's fastest inference 🚀</h1>
+"""
+NOTICE = """
+Current only support Llama3.1 8B and Llama 3.1 70B.
+"""
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    model_id,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    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 = ""
+
+    stream = client.chat.completions.create(
+        messages=[
+            {
+                "role": "user",
+                "content": "Why is fast inference important?",
+            }
+        ],
+        model=model_id,
+        max_tokens=max_tokens,
+        temperature=temperature,
+        top_p=top_p,
+        stream=True,
+    )
+
+    for chunk in stream:
+        token = chunk.choices[0].delta.content or ""
+        response += token
+        yield response
+
+chatbot = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Dropdown(
+            ["llama3.1-8b", "llama3.1-70b"],
+            value="llama3.1-8b",
+            label="Models"
+        ),
+        gr.Slider(minimum=1, maximum=8192, value=4096, 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)",
+        ),
+    ],
+)
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.HTML(TTILE)
+    gr.HTML(NOTICE)
+    chatbot.render()
+
+if __name__ == "__main__":
+    demo.launch(debug=True, show_error=True)