---
license: other
---


![Aquila_logo](./log.jpeg)


<h4 align="center">
    <p>
        <b>English</b> |
        <a href="https://huggingface.co/BAAI/AquilaChat2-7B/blob/main/README_zh.md">简体中文</a> 
    </p>
</h4>

# 悟道·天鹰（Aquila2）

我们开源了我们的 **Aquila2** 系列，现在包括基础语言模型 **Aquila2-7B** 和 **Aquila2-34B** ，对话模型 **AquilaChat2-7B** 和 **AquilaChat2-34B**，长文本对话模型**AquilaChat2-7B-16k** 和 **AquilaChat2-34B-16k**

悟道 · 天鹰 Aquila 模型的更多细节将在官方技术报告中呈现。请关注官方渠道更新。

## Chat Model Performance

<br>
<p align="center">
    <img src="chat_metrics.jpeg" width="1024"/>
<p>
<br>

## Quick Start  AquilaChat-7B（Chat model）

### 1. Inference

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
device = torch.device("cuda")
model_info = "BAAI/AquilaChat2-7B"
tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_info, trust_remote_code=True)
model.eval()
model.to(device)
text = "请给出10个要到北京旅游的理由。"
tokens = tokenizer.encode_plus(text)['input_ids'][:-1]
tokens = torch.tensor(tokens)[None,].to(device)
stop_tokens = ["###", "[UNK]", "</s>"]
with torch.no_grad():
    out = model.generate(tokens, do_sample=True, max_length=512, eos_token_id=100007, bad_words_ids=[[tokenizer.encode(token)[0] for token in stop_tokens]])[0]
    out = tokenizer.decode(out.cpu().numpy().tolist())
    print(out)
```


## License

AquilaChat2-7B open-source model is licensed under [ BAAI Aquila Model Licence Agreement](https://huggingface.co/BAAI/AquilaChat-7B/resolve/main/BAAI%20Aquila%20Model%20License%20Agreement.pdf)