bloc97 / DeMo
DeMo: Decoupled Momentum Optimization
☆182Updated 3 months ago
Alternatives and similar repositories for DeMo:
Users that are interested in DeMo are comparing it to the libraries listed below
- supporting pytorch FSDP for optimizers☆79Updated 3 months ago
- Normalized Transformer (nGPT)☆156Updated 3 months ago
- Focused on fast experimentation and simplicity☆69Updated 2 months ago
- PyTorch implementation of models from the Zamba2 series.☆177Updated last month
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆222Updated last month
- ☆89Updated last month
- Collection of autoregressive model implementation☆83Updated 3 weeks ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆196Updated 7 months ago
- Efficient optimizers☆181Updated this week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆99Updated 3 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆107Updated 2 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆123Updated 3 months ago
- ☆53Updated last year
- ☆101Updated 2 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆83Updated 2 weeks ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆167Updated last month
- Fast, Modern, Memory Efficient, and Low Precision PyTorch Optimizers☆86Updated 7 months ago
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆274Updated 4 months ago
- 🧱 Modula software package☆169Updated this week
- ☆49Updated 11 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆121Updated 6 months ago
- ☆126Updated 6 months ago
- When it comes to optimizers, it's always better to be safe than sorry☆213Updated 2 weeks ago
- ☆97Updated 5 months ago
- WIP☆93Updated 6 months ago
- smolLM with Entropix sampler on pytorch☆150Updated 4 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆122Updated 10 months ago