apple / ml-ademamixLinks
☆68Updated 11 months ago
Alternatives and similar repositories for ml-ademamix
Users that are interested in ml-ademamix are comparing it to the libraries listed below
Sorting:
- supporting pytorch FSDP for optimizers☆83Updated 10 months ago
- ☆220Updated 10 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆56Updated 7 months ago
- ☆120Updated 4 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- Accelerated First Order Parallel Associative Scan☆189Updated last year
- H-Net Dynamic Hierarchical Architecture☆80Updated last month
- research impl of Native Sparse Attention (2502.11089)☆62Updated 8 months ago
- ☆91Updated last year
- Focused on fast experimentation and simplicity☆75Updated 10 months ago
- Efficient optimizers☆275Updated 2 weeks ago
- 📄Small Batch Size Training for Language Models☆63Updated 3 weeks ago
- Supporting code for the blog post on modular manifolds.☆94Updated last month
- ☆58Updated last year
- ☆53Updated 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
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆170Updated 4 months ago
- WIP☆93Updated last year
- DeMo: Decoupled Momentum Optimization☆195Updated 10 months ago
- Experiment of using Tangent to autodiff triton☆80Updated last year
- Normalized Transformer (nGPT)☆192Updated 11 months ago
- ☆19Updated 5 months ago
- ☆45Updated last week
- ☆30Updated 10 months ago
- Dion optimizer algorithm☆374Updated last month
- ☆81Updated last year
- Explorations into the recently proposed Taylor Series Linear Attention☆99Updated last year
- Collection of autoregressive model implementation☆86Updated 6 months ago
- Griffin MQA + Hawk Linear RNN Hybrid☆89Updated last year
- ☆310Updated last year