ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation

[📂 GitHub] [📜 Paper]

If you find this project useful in your research, please consider citing:

@article{wang2025alto,
  title={ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation},
  author={Wang, Lingfeng and Lin, Hualing and Chen, Senda and Wang, Tao and Cheng, Changxu and Zhong, Yangyang and Zheng, Dong and Zhao, Wuyue},
  journal={arXiv preprint arXiv:2505.16495},
  year={2025}
}
Downloads last month
167
Safetensors
Model size
9.04B params
Tensor type
BF16
·
BOOL
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for yayafengzi/ALToLLM-8B

Finetuned
(18)
this model

Collection including yayafengzi/ALToLLM-8B