tim-lawson / skip-middleLinks
Learning to Skip the Middle Layers of Transformers
☆15Updated 2 months ago
Alternatives and similar repositories for skip-middle
Users that are interested in skip-middle are comparing it to the libraries listed below
Sorting:
- [ICML 2025] Code for "R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts"☆16Updated 6 months ago
- Unofficial Implementation of Selective Attention Transformer☆17Updated 11 months ago
- ☆34Updated 6 months ago
- [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…☆26Updated 2 months ago
- Official implementation of the paper: "A deeper look at depth pruning of LLMs"☆15Updated last year
- AdaSplash: Adaptive Sparse Flash Attention (aka Flash Entmax Attention)☆26Updated last week
- ☆26Updated 3 weeks ago
- ☆19Updated 6 months ago
- HGRN2: Gated Linear RNNs with State Expansion☆54Updated last year
- ☆14Updated last year
- User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…☆25Updated 5 months ago
- Official PyTorch Implementation for Vision-Language Models Create Cross-Modal Task Representations, ICML 2025☆31Updated 5 months ago
- ☆19Updated 9 months ago
- [NAACL'25 🏆 SAC Award] Official code for "Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert…☆10Updated 8 months ago
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆14Updated 6 months ago
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆34Updated last year
- The official repo of continuous speculative decoding☆30Updated 6 months ago
- ☆61Updated 3 months ago
- [ICLR'25] Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization☆16Updated 3 months ago
- Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers☆21Updated 7 months ago
- Official Implementation of FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation☆24Updated 4 months ago
- Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…☆101Updated last month
- ☆18Updated 2 months ago
- ☆25Updated 2 months ago
- ☆24Updated 6 months ago
- Mixture-of-Basis-Experts for Compressing MoE-based LLMs☆18Updated 3 weeks ago
- Control LLM☆19Updated 6 months ago
- ☆15Updated last year
- Are gradient information useful for pruning of LLMs?☆46Updated last month
- Xmixers: A collection of SOTA efficient token/channel mixers☆15Updated last month