This is the original 3B BlockFFN checkpoint used in the paper
BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity
for acceleration tests.
You can load and use this model simply by using
AutoTokenizer
and
AutoModelForCausalLM
.
If you find our work useful for your research, please kindly cite our paper as follows:
@article{song2025blockffn,
title={{BlockFFN}: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity},
author={Chenyang Song and Weilin Zhao and Xu Han and Chaojun Xiao and Yingfa Chen and Yuxuan Li and Zhiyuan Liu and Maosong Sun},
journal={arXiv preprint arXiv:2507.08771},
year={2025},
url={https://arxiv.org/pdf/2507.08771},
}
Runs of SparseLLM BlockFFN-3B-SFT on huggingface.co
11
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About BlockFFN-3B-SFT huggingface.co Model
BlockFFN-3B-SFT huggingface.co is an AI model on huggingface.co that provides BlockFFN-3B-SFT's model effect (), which can be used instantly with this SparseLLM BlockFFN-3B-SFT model. huggingface.co supports a free trial of the BlockFFN-3B-SFT model, and also provides paid use of the BlockFFN-3B-SFT. Support call BlockFFN-3B-SFT model through api, including Node.js, Python, http.
BlockFFN-3B-SFT huggingface.co is an online trial and call api platform, which integrates BlockFFN-3B-SFT's modeling effects, including api services, and provides a free online trial of BlockFFN-3B-SFT, you can try BlockFFN-3B-SFT online for free by clicking the link below.
SparseLLM BlockFFN-3B-SFT online free url in huggingface.co:
BlockFFN-3B-SFT is an open source model from GitHub that offers a free installation service, and any user can find BlockFFN-3B-SFT on GitHub to install. At the same time, huggingface.co provides the effect of BlockFFN-3B-SFT install, users can directly use BlockFFN-3B-SFT installed effect in huggingface.co for debugging and trial. It also supports api for free installation.