nielsr's picture
nielsr HF Staff
Add model card and metadata
ecb9f7f verified
|
raw
history blame
1.6 kB
metadata
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
tags:
  - speculative-decoding

TAPS: Task-Aware Proposal Distributions for Speculative Sampling

This repository contains a draft model introduced in the paper TAPS: Task Aware Proposal Distributions for Speculative Sampling.

Overview

TAPS (Task-Aware Proposal Distributions) investigates how the training distribution of draft models affects the efficiency of speculative decoding. In speculative decoding, a lightweight draft model proposes future tokens that a larger target model (like Meta-Llama-3-8B-Instruct) verifies in parallel.

This model is a lightweight LLaMA-style drafter (approximately 0.8B parameters with 1 layer) designed to accelerate autoregressive generation. The research demonstrates that task-specific training (e.g., on MathInstruct or ShareGPT) yields significant specialization, and that specialized drafters are best combined at inference time using strategies like confidence-based routing or merged-tree verification.

Resources

Citation

@article{zbib2026taps,
  title={TAPS: Task Aware Proposal Distributions for Speculative Sampling},
  author={Zbib, Mohamad and Bazzi, Mohamad and Mohanna, Ammar and Ghanem, Bernard and Hammoud, Hasan Abed Al Kader},
  year={2026},
  note={Technical report}
}