huggingfacehttps://huggingface.co/meta-llama

from transformers import AutoTokenizer, LlamaForCausalLM

PATH_TO_CONVERTED_WEIGHTS = ''
PATH_TO_CONVERTED_TOKENIZER = ''  # 一般和模型地址一样

model = LlamaForCausalLM.from_pretrained(PATH_TO_CONVERTED_WEIGHTS)
tokenizer = AutoTokenizer.from_pretrained(PATH_TO_CONVERTED_TOKENIZER)
prompt = "Hey, are you conscious? Can you talk to me?"
inputs = tokenizer(prompt, return_tensors="pt")

# Generate
generate_ids = model.generate(inputs.input_ids, max_length=30)
tokenizer.batch_decode(generate_ids, skip_special_tokens=True,     
    clean_up_tokenization_spaces=False)[0]

> Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you.