BoyangZ/

Llama3-chinese_chat_ft

from transformers import AutoTokenizer, AutoModelForCausalLM import torch

model_id = "BoyangZ/Llama3-chinese_chat_ft"

tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto", )

messages = [ {"role": "system", "content": "You are a LLM assistant. Users will ask you questions in Chinese, You will answer questions in Chinese"}, {"role": "user", "content": "李白是哪个朝代的人?"}, ]

input_ids = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt" ).to(model.device)

terminators = [ tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|eot_id|>") ]

outputs = model.generate( input_ids, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.6, top_p=0.9, ) response = outputs[0][input_ids.shape[-1]:] print(tokenizer.decode(response, skip_special_tokens=True))