---
license: mit
datasets:
- Fsoft-AIC/MainframeBench
tags:
- code
---

<p align="center">
  <img src="./asset/XMAiNframe.png"  width="560px" alt="logo">
</p>

<div align="center">
  
# XMAiNframe: A Large Language Model for Mainframe Modernization
</div>

## Introduction

We are introducing **XMAiNframe**, a state-of-the-art large language model (LLM) specifically designed with knowledge of mainframe legacy systems and COBOL codebases. XMAiNframe is built on top of DeepSeek-Coder 7B and is available with 7B and 10.5B parameters.
Additionally, we present [MainframeBench](https://huggingface.co/datasets/Fsoft-AIC/MainframeBench), a comprehensive benchmark for assessing mainframe knowledge, including multiple-choice questions, question answering, and COBOL code summarization. Our empirical evaluations demonstrate that XMAiNframe consistently outperforms existing state-of-the-art LLMs across these tasks. Specifically, XMAiNframe achieves 30% higher accuracy than DeepSeek-Coder on multiple-choice questions, doubles the BLEU score of Mixtral-Instruct 8x7B on question answering, and scores six times higher than GPT-3.5 on COBOL summarization. Our work highlights the potential of XMAiNframe to drive significant advancements in managing and modernizing legacy systems, thereby enhancing productivity and saving time for software developers.


## Model Versions

We release XMAiNframe with 7B and 10.5B parameters, including base and instruct models, to the public. XMAiNframe 10.5B is expanded from DeepSeek-Coder 7B by the depth up-scaling method without introducing additional modules or dynamic expert selection methods.

<div align="center">

|            **Model**            |      **Download**  |
| :-----------------------------: |  :----------------------------------------------------------: |
|   XMAiNframe-base-7b         | [🤗 HuggingFace](https://https://huggingface.co/Fsoft-AIC/XMAiNframe-base-7b/) |
| XMAiNframe-instruct-7b    | [🤗 HuggingFace](https://huggingface.co/Fsoft-AIC/XMAiNframe-instruct-7b) |
|     XMAiNframe-base-10.5b     |       [🤗 HuggingFace](https://huggingface.co/Fsoft-AIC/XMAiNframe-base-10.5b) |
|   XMAiNframe-instruct-10.5b   |   [🤗 HuggingFace](https://huggingface.co/Fsoft-AIC/XMAiNframe-instruct-10.5b) |

</div>


## Quickstart

Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.


```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Fsoft-AIC/XMAiNframe-instruct-10.5b")
model = AutoModelForCausalLM.from_pretrained("Fsoft-AIC/XMAiNframe-instruct-10.5b")
messages=[
    {'from':'system', 'value': "You are a helpful assistant"},
    {'from': 'human', 'value': 'What is the future of Mainframe?'}
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
 
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
```

## Additional Information
### Other Resources:
- Github: https://github.com/FSoft-AI4Code/XMainframe
- Paper: https://arxiv.org/abs/2408.04660


### License
[MIT License](LICENSE)

### Citation Information
More details can be found in our [paper](https://arxiv.org/abs/2408.04660). 

If you're using XMAiNframe, please cite using this BibTeX:
```
@misc{dau2024xmainframelargelanguagemodel,
      title={XMainframe: A Large Language Model for Mainframe Modernization}, 
      author={Anh T. V. Dau and Hieu Trung Dao and Anh Tuan Nguyen and Hieu Trung Tran and Phong X. Nguyen and Nghi D. Q. Bui},
      year={2024},
      eprint={2408.04660},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2408.04660}, 
}
```

# Contact us
If you have any questions, comments or suggestions, please do not hesitate to contact us.
- Website: [fpt-aicenter](https://www.fpt-aicenter.com/ai-residency/)
- Email: support.ailab@fpt.com