Update app.py

app.py

@@ -1,3 +1,19 @@
-import gradio as gr
+import torch
+from transformers import pipeline
 
-gr.load("models/meta-llama/Llama-3.2-1B").launch()
+model_id = "meta-llama/Llama-3.2-1B-Instruct"
+pipe = pipeline(
+    "text-generation",
+    model=model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+outputs = pipe(
+    messages,
+    max_new_tokens=256,
+)
+print(outputs[0]["generated_text"][-1])