cloneofsimo / scaling-guideLinks
WIP
☆93Updated 11 months ago
Alternatives and similar repositories for scaling-guide
Users that are interested in scaling-guide are comparing it to the libraries listed below
Sorting:
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆130Updated last year
- supporting pytorch FSDP for optimizers☆84Updated 7 months ago
- ☆83Updated last year
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆84Updated last year
- Focused on fast experimentation and simplicity☆76Updated 7 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆149Updated last month
- ☆53Updated last year
- ☆34Updated 10 months ago
- These papers will provide unique insightful concepts that will broaden your perspective on neural networks and deep learning☆48Updated last year
- Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"☆113Updated 3 months ago
- ☆23Updated last year
- research impl of Native Sparse Attention (2502.11089)☆60Updated 5 months ago
- ☆304Updated last year
- Efficient optimizers☆252Updated last week
- ☆30Updated 8 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆55Updated 4 months ago
- ☆53Updated last year
- ☆21Updated 9 months ago
- ☆115Updated last month
- Synthetic Alphabet Dataset☆19Updated 4 months ago
- 🧱 Modula software package☆210Updated last week
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated 11 months ago
- Train VAE like a boss☆287Updated 9 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆94Updated last week
- ☆53Updated 8 months ago
- DeMo: Decoupled Momentum Optimization☆190Updated 8 months ago
- ☆65Updated 8 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆127Updated 11 months ago
- ☆206Updated 8 months ago
- Dion optimizer algorithm☆193Updated this week