cloneofsimo / scaling-guideLinks
WIP
☆93Updated last year
Alternatives and similar repositories for scaling-guide
Users that are interested in scaling-guide are comparing it to the libraries listed below
Sorting:
- supporting pytorch FSDP for optimizers☆83Updated 10 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆85Updated last year
- Focused on fast experimentation and simplicity☆75Updated 10 months ago
- ☆91Updated last year
- ☆53Updated last year
- Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"☆122Updated 6 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆166Updated 3 months ago
- ☆34Updated last year
- Synthetic Alphabet Dataset☆19Updated 6 months ago
- Supporting code for the blog post on modular manifolds.☆86Updated 3 weeks ago
- ☆30Updated 10 months ago
- ☆22Updated last year
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆56Updated 7 months ago
- ☆23Updated last year
- research impl of Native Sparse Attention (2502.11089)☆62Updated 8 months ago
- These papers will provide unique insightful concepts that will broaden your perspective on neural networks and deep learning☆48Updated 2 years ago
- ☆309Updated last year
- Efficient optimizers☆274Updated last week
- Train VAE like a boss☆295Updated last year
- Mixture of A Million Experts☆48Updated last year
- ☆53Updated last year
- ☆56Updated 11 months ago
- Minimal (truly) muP implementation, consistent with TP4 and TP5 papers notation☆14Updated 5 months ago
- Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…☆101Updated last month
- 📄Small Batch Size Training for Language Models☆63Updated 3 weeks ago
- DeMo: Decoupled Momentum Optimization☆194Updated 10 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆129Updated last year
- Automatically take good care of your preemptible TPUs☆37Updated 2 years ago
- ☆67Updated 11 months ago