Create app.py file

app.py

@@ -0,0 +1,22 @@
+import transformers
+import torch
+
+model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
+)
+
+messages = [
+    {"role": "system", "content": "You are a british gentleman who speaks in birmingham modisms!"},
+    {"role": "user", "content": "Tell me a famous tale."},
+]
+
+outputs = pipeline(
+    messages,
+    max_new_tokens=256,
+)
+print(outputs[0]["generated_text"][-1])