73 lines
3.5 KiB
Markdown
73 lines
3.5 KiB
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
library_name: transformers
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
license: llama3
|
||
|
|
model_type: llama
|
||
|
|
---
|
||
|
|
|
||
|
|
# 🐟 Llama-3-CycleQD
|
||
|
|
|
||
|
|
🤗 [Models](https://huggingface.co/SakanaAI) | 📚 [Paper](https://arxiv.org/abs/2410.14735) | 🐦 [Twitter](https://twitter.com/SakanaAILabs)
|
||
|
|
|
||
|
|
This collection of agentic Language Models (LLMs) is based on Llama-3-8B-Instruct.
|
||
|
|
**Llama-3-8B-Instruct-CycleQD-CS** is created using the CycleQD method, which leverages:
|
||
|
|
|
||
|
|
- [SakanaAI/Llama-3-8B-Instruct-DB-Expert](https://huggingface.co/SakanaAI/Llama-3-8B-Instruct-DB-Expert)
|
||
|
|
- [SakanaAI/Llama-3-8B-Instruct-OS-Expert](https://huggingface.co/SakanaAI/Llama-3-8B-Instruct-OS-Expert)
|
||
|
|
- [SakanaAI/Llama-3-8B-Instruct-Coding-Expert](https://huggingface.co/SakanaAI/Llama-3-8B-Instruct-Coding-Expert)
|
||
|
|
|
||
|
|
Please refer to our [report](https://arxiv.org/abs/2410.14735) for more details.
|
||
|
|
We are grateful to the developers of the following source model and training data:
|
||
|
|
|
||
|
|
- [Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
||
|
|
- [Agent-FLAN](https://huggingface.co/datasets/internlm/Agent-FLAN)
|
||
|
|
- [Magicoder-Evol-Instruct-110K](https://huggingface.co/datasets/ise-uiuc/Magicoder-Evol-Instruct-110K)
|
||
|
|
- [Magicoder-OSS-Instruct-75K](https://huggingface.co/datasets/ise-uiuc/Magicoder-OSS-Instruct-75K)
|
||
|
|
|
||
|
|
<!-- ## Model Index
|
||
|
|
|
||
|
|
| Model | Link |
|
||
|
|
|---|---|
|
||
|
|
| DB expert | [SakanaAI/Llama-3-8B-Instruct-DB-Expert](https://huggingface.co/SakanaAI/Llama-3-8B-Instruct-DB-Expert) |
|
||
|
|
| OS expert | [SakanaAI/Llama-3-8B-Instruct-OS-Expert](https://huggingface.co/SakanaAI/Llama-3-8B-Instruct-OS-Expert) |
|
||
|
|
| Coding Expert | [SakanaAI/Llama-3-8B-Instruct-Coding-Expert](https://huggingface.co/SakanaAI/Llama-3-8B-Instruct-Coding-Expert) |
|
||
|
|
| CycleQD | [SakanaAI/Llama-3-8B-Instruct-CycleQD-CS](https://huggingface.co/SakanaAI/Llama-3-8B-Instruct-CycleQD-CS) |
|
||
|
|
-->
|
||
|
|
## Model Details
|
||
|
|
|
||
|
|
<!-- Provide a longer summary of what this model is. -->
|
||
|
|
|
||
|
|
- **Developed by:** [Sakana AI](https://sakana.ai/)
|
||
|
|
- **Model type:** Autoregressive Language Model
|
||
|
|
- **License:** [META LLAMA 3 COMMUNITY LICENSE](https://www.llama.com/llama3/license/)
|
||
|
|
- **Repository:** [SakanaAI/CycleQD](https://github.com/SakanaAI/CycleQD)
|
||
|
|
- **Paper:** https://arxiv.org/abs/2410.14735
|
||
|
|
|
||
|
|
|
||
|
|
## Uses
|
||
|
|
This model is provided for research and development purposes only and should be considered as an experimental prototype.
|
||
|
|
It is not intended for commercial use or deployment in mission-critical environments.
|
||
|
|
Use of this model is at the user's own risk, and its performance and outcomes are not guaranteed.
|
||
|
|
Sakana AI shall not be liable for any direct, indirect, special, incidental, or consequential damages, or any loss arising from the use of this model, regardless of the results obtained.
|
||
|
|
Users must fully understand the risks associated with the use of this model and use it at their own discretion.
|
||
|
|
|
||
|
|
## Acknowledgement
|
||
|
|
|
||
|
|
We would like to thank the developers of the source models and training datasets for their contributions and for making their work available. These models are based on results obtained from a project, JPNP20017, subsidized by the New Energy and Industrial Technology Development Organization (NEDO), and built with Meta Llama 3.
|
||
|
|
|
||
|
|
## Citation
|
||
|
|
|
||
|
|
```bibtex
|
||
|
|
@article{sakana2024cycleQD,
|
||
|
|
title={Agent Skill Acquisition for Large Language Models via CycleQD},
|
||
|
|
author={So Kuroki and Taishi Nakamura and Takuya Akiba and Yujin Tang},
|
||
|
|
year={2024},
|
||
|
|
eprint={2410.14735},
|
||
|
|
archivePrefix={arXiv},
|
||
|
|
primaryClass={cs.CL},
|
||
|
|
url={https://arxiv.org/abs/2410.14735},
|
||
|
|
}
|
||
|
|
```
|