YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

cense: cc-by-nc-nd-4.0

PosS: Position Specialist for Speculative Decoding

This repository provides the model checkpoint for PosS (Position Specialist), a speculative decoding method proposed in the paper:

PosS: Position Specialist Generates Better Draft for Speculative Decoding

PosS improves speculative decoding by training a position-specialized draft model that generates higher-quality drafts, leading to improved efficiency and acceptance rates during decoding.


πŸ”— Code

The full implementation, training details, and evaluation scripts are available at:

πŸ‘‰ GitHub: https://github.com/shrango/PosS


πŸ“¦ Files

If the model is not automatically downloaded by your framework, you may manually download the following files from this repository:

  • pytorch_model.bin β€” model weights
  • config.json β€” model configuration

πŸ“– Citation

If you use this model or the PosS method in your research, please cite:

@misc{huang2025posspositionspecialistgenerates,
  title        = {POSS: Position Specialist Generates Better Draft for Speculative Decoding},
  author       = {Langlin Huang and Chengsong Huang and Jixuan Leng and Di Huang and Jiaxin Huang},
  year         = {2025},
  eprint       = {2506.03566},
  archivePrefix= {arXiv},
  primaryClass = {cs.CL},
  url          = {https://arxiv.org/abs/2506.03566}
}
Downloads last month
7
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Collection including HINT-lab/PosS3-Llama3-8B-Instruct