apple / ml-ademamix
☆46Updated last month
Related projects ⓘ
Alternatives and complementary repositories for ml-ademamix
- ☆122Updated this week
- ☆18Updated last month
- Experiment of using Tangent to autodiff triton☆72Updated 9 months ago
- ☆46Updated last month
- Collection of autoregressive model implementation☆66Updated last week
- Efficient optimizers☆58Updated this week
- ☆53Updated 9 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆112Updated 6 months ago
- ☆72Updated 4 months ago
- ☆76Updated 6 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆15Updated this week
- Triton Implementation of HyperAttention Algorithm☆46Updated 11 months ago
- ☆27Updated 7 months ago
- An implementation of the Llama architecture, to instruct and delight☆21Updated 2 months ago
- ☆30Updated 6 months ago
- Muon optimizer for neural networks: >30% extra sample efficiency, <3% wallclock overhead☆69Updated this week
- Explorations into the recently proposed Taylor Series Linear Attention☆89Updated 2 months ago
- ☆29Updated last month
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆84Updated last week
- ☆40Updated 7 months ago
- ☆50Updated last week
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆84Updated 2 months ago
- ☆31Updated 2 months ago
- ☆39Updated 9 months ago
- Efficient PScan implementation in PyTorch☆15Updated 10 months ago
- Scalable neural net training via automatic normalization in the modular norm.☆119Updated 2 months ago
- ☆61Updated 2 months ago
- ☆76Updated 5 months ago
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆69Updated 3 months ago