MAS-GPT-32B

This model can generate query-specific LLM-based multi-agent system, which is fine-tuned on Qwen/Qwen2.5-Coder-32B-Instruct.

See our paper MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems.

Citation

@article{ye2025mas,
  title={MAS-GPT: Training LLMs to build LLM-based multi-agent systems},
  author={Ye, Rui and Tang, Shuo and Ge, Rui and Du, Yaxin and Yin, Zhenfei and Chen, Siheng and Shao, Jing},
  journal={arXiv preprint arXiv:2503.03686},
  year={2025}
}
Downloads last month
193
Safetensors
Model size
32.8B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for MASWorks/MAS-GPT-32B

Base model

Qwen/Qwen2.5-32B
Finetuned
(94)
this model
Quantizations
2 models