DHSA-Gemma2-2b-it-BF16

This repository hosts the predictor weights for Gemma2-2b-it (BF16) used in Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM Inference (ICML 2026 Spotlight).

Usage

First, clone our repository and download the checkpoint files from Hugging Face:

git clone https://github.com/xiongsiheng/DHSA
cd DHSA/legacy

hf download sxiong/DHSA-Gemma2-2b-it-BF16 \
  --local-dir boundary_predictor_weights/DHSA-Gemma2-2b-it-BF16

Citation

@inproceedings{xionglong,
  title={Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM Inference},
  author={Xiong, Siheng and Zou, Joe and Fekri, Faramarz and Cho, Yae Jee},
  booktitle={Forty-third International Conference on Machine Learning}
}
Downloads last month
11
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including sxiong/DHSA-Gemma2-2b-it-BF16

Paper for sxiong/DHSA-Gemma2-2b-it-BF16