Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,37 @@
+import gradio as gr
+import spaces
+from transformers import pipeline
+import torch
+
+MODEL_ID = "LLM360/K2-Think"
+
+pipe = pipeline(
+    "text-generation",
+    model=MODEL_ID,
+    torch_dtype="auto",
+    device_map="auto",
+)
+
+@spaces.GPU
+def respond(message, history):
+    if history is None:
+        history = []
+    new_history = history + [{"role": "user", "content": message}]
+    outputs = pipe(
+        new_history,
+        max_new_tokens=32768,
+    )
+    response = outputs[0]["generated_text"][-1]["content"]
+    new_history.append({"role": "assistant", "content": response})
+    return "", new_history
+
+with gr.Blocks(title="K2-Think Chat") as demo:
+    gr.Markdown("# K2-Think Chat App")
+    chatbot = gr.Chatbot(type="messages", height=500)
+    msg = gr.Textbox(placeholder="Type your message here...", scale=7)
+    clear_btn = gr.Button("Clear Chat")
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+    clear_btn.click(lambda: None, None, chatbot, queue=False)
+
+if __name__ == "__main__":
+    demo.launch()