| thon | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| device = "cuda" # the device to load the model onto | |
| model = AutoModelForCausalLM.from_pretrained("Qwen2/Qwen2-7B-Chat-beta", device_map="auto") | |
| tokenizer = AutoTokenizer.from_pretrained("Qwen2/Qwen2-7B-Chat-beta") | |
| prompt = "Give me a short introduction to large language model." |