README.md

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

# Unichat-llama3-Chinese-8B


## 介绍
* 中国联通发布业界第一个llama3中文指令微调模型
* 本模型以[**Meta Llama 3**](https://huggingface.co/collections/meta-llama/meta-llama-3-66214712577ca38149ebb2b6)为基础,增加中文数据进行训练,实现llama3模型高质量中文问答
* 基础模型 [**Meta-Llama-3-8B**](https://huggingface.co/meta-llama/Meta-Llama-3-8B)

### 📊 数据
- 中国联通自有指令数据，覆盖多个领域和行业，为模型训练提供充足的数据支持。
- 微调指令数据经过严格的人工筛查，保证优质的指令数据用于模型微调
  
## 快速开始

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "UnicomLLM/Unichat-llama3-Chinese-8B"

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 helpful assistant"},
    {"role": "user", "content": "Who are you?"},
]

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))
```

## 资源
更多模型,数据集和训练相关细节请参考:
* Github：[**Unichat-llama3-Chinese**](https://github.com/UnicomAI/Unichat-llama3-Chinese)