-
TransMLA Public
TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)
-
-
peft Public
Forked from huggingface/peft🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
-
-
Pruning-Filter-in-Filter Public
Pruning Filter in Filter(NeurIPS2020)
-
NotionNext Public
Forked from tangly1024/NotionNext使用 NextJS + Notion API 实现的，支持多种部署方案的静态博客，无需服务器、零门槛搭建网站，为Notion和所有创作者设计。 (A static blog built with NextJS and Notion API, supporting multiple deployment options. No server required, zero threshold t…
JavaScript MIT License UpdatedAug 17, 2023 -
RMNet Public
RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.
-
filter-grafting Public
Filter Grafting for Deep Neural Networks(CVPR 2020)
{{ message }}