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 7 months ago
- ☆30Updated last month
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆36Updated last year
- [ICLR 2025] Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization☆18Updated 3 weeks ago
- ☆34Updated 7 months ago
- HGRN2: Gated Linear RNNs with State Expansion☆55Updated last year
- AdaSplash: Adaptive Sparse Flash Attention (aka Flash Entmax Attention)☆29Updated 3 weeks ago
- [NeurIPS '25] Multi-Token Prediction Needs Registers☆23Updated last month
- [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…☆26Updated 3 months ago
- Official PyTorch Implementation for Vision-Language Models Create Cross-Modal Task Representations, ICML 2025☆31Updated 5 months ago
- Official code for the paper "Attention as a Hypernetwork"☆44Updated last year
- Official implementation of the paper: "A deeper look at depth pruning of LLMs"☆15Updated last year
- M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models☆44Updated 3 months ago
- ☆14Updated last year
- ☆19Updated 7 months ago
- Unofficial Implementation of Selective Attention Transformer☆17Updated 11 months ago
- Xmixers: A collection of SOTA efficient token/channel mixers☆29Updated last month
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆94Updated 11 months ago
- Are gradient information useful for pruning of LLMs?☆47Updated 2 months ago
- Triton implement of bi-directional (non-causal) linear attention☆56Updated 8 months ago
- [ICLR 2025] Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better☆16Updated 8 months ago
- The official repo of continuous speculative decoding☆30Updated 7 months ago
- Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…☆101Updated 2 months ago
- Here we will test various linear attention designs.☆61Updated last year
- Mixture-of-Basis-Experts for Compressing MoE-based LLMs☆19Updated last month
- SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining (NeurIPS 2024)☆35Updated 11 months ago
- Official Implementation of FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation☆25Updated 5 months ago
- [NeurIPS 2024] VeLoRA : Memory Efficient Training using Rank-1 Sub-Token Projections☆21Updated last year
- Resa: Transparent Reasoning Models via SAEs☆44Updated last month
- [ICML2024 Spotlight] Fine-Tuning Pre-trained Large Language Models Sparsely☆22Updated last year