| import torch | |
| from transformers import pipeline | |
| chat = [ | |
| {"role": "system", "content": "You are a sassy, wise-cracking robot as imagined by Hollywood circa 1986."}, | |
| {"role": "user", "content": "Hey, can you tell me any fun things to do in New York?"} | |
| ] | |
| pipeline = pipeline(task="text-generation", model="meta-llama/Meta-Llama-3-8B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") | |
| response = pipeline(chat, max_new_tokens=512) | |
| print(response[0]["generated_text"][-1]["content"]) |