---
license: apache-2.0
language:
- zh
pipeline_tag: text-generation
---

How to use：
------

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))

example1
---
![image/png](https://cdn-uploads.huggingface.co/production/uploads/644a78de7c5c68c7762886eb/uvOKN0WPumRVwE_kPkFKj.png)

example2
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/644a78de7c5c68c7762886eb/FoExkJHBp-yM6-XFwaDpG.png)

example3
---


![image/png](https://cdn-uploads.huggingface.co/production/uploads/644a78de7c5c68c7762886eb/1EorUSsh-28LZFZpp768k.png)