SHI-Labs / CompactNetLinks
☆31Updated last year
Alternatives and similar repositories for CompactNet
Users that are interested in CompactNet are comparing it to the libraries listed below
Sorting:
- Efficient Scaling laws and collaborative pretraining.☆16Updated 4 months ago
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 4 months ago
- Code for the paper "Function-Space Learning Rates"☆20Updated last month
- ☆53Updated 8 months ago
- ☆32Updated last year
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆52Updated 2 months ago
- ☆37Updated last year
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆37Updated last year
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆66Updated 8 months ago
- Implementation of Spectral State Space Models☆16Updated last year
- We study toy models of skill learning.☆28Updated 4 months ago
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- ☆79Updated 9 months ago
- Source code for the paper "Positional Attention: Expressivity and Learnability of Algorithmic Computation"☆14Updated last week
- Combining SOAP and MUON☆16Updated 3 months ago
- Fork of Flame repo for training of some new stuff in development☆13Updated this week
- ☆33Updated 4 months ago
- ☆61Updated 6 months ago
- A repo based on XiLin Li's PSGD repo that extends some of the experiments.☆14Updated 7 months ago
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆26Updated 7 months ago
- ☆33Updated 8 months ago
- ☆53Updated last year
- ☆32Updated 8 months ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆30Updated last year
- ☆19Updated 2 weeks ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- Unofficial Implementation of Selective Attention Transformer☆16Updated 7 months ago
- ☆21Updated 6 months ago
- ☆32Updated 4 months ago
- Official code for the paper "Attention as a Hypernetwork"☆36Updated 11 months ago