---
title: Aquila2-34B
canonical_url: "https://www.modelscope.cn/models/BAAI/Aquila2-34B"
md_url: "https://www.modelscope.cn/models/BAAI/Aquila2-34B.md"
repository: BAAI/Aquila2-34B
last_updated: 2026-07-14
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - aquila
architectures:
  - AquilaForCausalLM
parameters: 34.2B
tensor_type:
  - F32
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
downloads: 2469
stars: 2
---

# Aquila2-34B

> Aquila2-34B - BAAI 在 ModelScope 开源的模型。悟道·天鹰（Aquila）由北京智源人工智能研究院研发,，是首个具备中英双语知识、支持商用许可协议、国内数据合规需求的开源语言大模型。参数规模有7B和34B。此仓库为Aquila基础模型。

BAAI/Aquila2-34B 是 ModelScope 魔搭社区上的 34.2B 参数text-generation模型，采用 other 许可。

- **Repository**: BAAI/Aquila2-34B
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 34.2B
- **Downloads**: 2469
- **Stars**: 2
- **Last updated**: 2026-07-14

Source: https://www.modelscope.cn/models/BAAI/Aquila2-34B

---

![Aquila_logo](./log.jpeg)

<h4 align="center">
    <p>
        <b>English</b> |
        <a href="https://huggingface.co/BAAI/Aquila2-34B/blob/main/README_zh.md">简体中文</a> |
    <p>
</h4>


We opensource our **Aquila2** series, now including **Aquila2**, the base language models, namely **Aquila2-7B** and **Aquila2-34B**, as well as **AquilaChat2**, the chat models, namely **AquilaChat2-7B** and **AquilaChat2-34B**, as well as the long-text chat models, namely **AquilaChat2-7B-16k** and **AquilaChat2-34B-16k**

The additional details of the Aquila model will be presented in the official technical report. Please stay tuned for updates on official channels.

## Updates 2024.6.6

We have updated the basic language model **Aquila2-34B**, which has the following advantages compared to the previous model:

* Replaced tokenizer with higher compression ratio:

| Tokenizer | Size  | Zh                       | En     | Code  | Math   | Average |
|-----------|-------|--------------------------|--------|-------|-------|---------|
| Aquila2-original   | 100k  | **4.70**                 | 4.42   | 3.20  | 3.77  | 4.02    |
| Qwen1.5   | 151k  | 4.27                     | 4.51   | 3.62  | 3.35  | 3.94    |
| Llama3    | 128k  | 3.45                     | **4.61**   | 3.77  | **3.88** | 3.93    |
| Aquila2-new     | 143k  | 4.60                     | **4.61** | **3.78** | **3.88**  | **4.22** |

* The maximum processing length supported by the model has increased from 2048 to 8192



## Quick Start  Aquila2-34B

### 1. Inference
Aquila2-34B is a base model that can be used for continuation.

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

device= "cuda:0"

# Model Name
model_name = 'BAAI/Aquila2-34B'

# load model and tokenizer
quantization_config=BitsAndBytesConfig(
                        load_in_4bit=True,
                        bnb_4bit_use_double_quant=True,
                        bnb_4bit_quant_type="nf4",
                        bnb_4bit_compute_dtype=torch.bfloat16,
                    )
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, trust_remote_code=True,
                        # quantization_config=quantization_config # Uncomment this one for 4-bit quantization
                        )

tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)

model.eval()

model.to(device)

# Example
text = "The meaning of life is"
tokens = tokenizer.encode_plus(text)['input_ids']
tokens = torch.tensor(tokens)[None,].to(device)

with torch.no_grad():
        out = model.generate(tokens, do_sample=False, max_length=128, eos_token_id=tokenizer.eos_token_id)[0]
        out = tokenizer.decode(out.cpu().numpy().tolist())
        print(out)
```


## License

Aquila2 series open-source model is licensed under [ BAAI Aquila Model Licence Agreement](https://huggingface.co/BAAI/Aquila2-34B/blob/main/BAAI-Aquila-Model-License%20-Agreement.pdf)

## Citation
Feel free to cite the repo if you think Aquila2 is useful.

```python
@misc{zhang2024aquila2technicalreport,
      title={Aquila2 Technical Report}, 
      author={Bo-Wen Zhang and Liangdong Wang and Jijie Li and Shuhao Gu and Xinya Wu and Zhengduo Zhang and Boyan Gao and Yulong Ao and Guang Liu},
      year={2024},
      eprint={2408.07410},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2408.07410}, 
}
```


# Acknowledgements

This work is supported by the National Science and Technology Major Project (No. 2022ZD0116300).
本项目受新一代人工智能国家科技重大专项（No. 2022ZD0116300）支持。