KindXiaoming / grow-crystalsLinks
Getting crystal-like representations with harmonic loss
☆190Updated 2 months ago
Alternatives and similar repositories for grow-crystals
Users that are interested in grow-crystals are comparing it to the libraries listed below
Sorting:
- An implementation of PSGD Kron second-order optimizer for PyTorch☆91Updated 2 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆101Updated 6 months ago
- The AdEMAMix Optimizer: Better, Faster, Older.☆183Updated 9 months ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆251Updated 3 months ago
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆284Updated 3 weeks ago
- Efficient optimizers☆220Updated this week
- ☆188Updated 6 months ago
- Focused on fast experimentation and simplicity☆74Updated 6 months ago
- When it comes to optimizers, it's always better to be safe than sorry☆241Updated 2 months ago
- DeMo: Decoupled Momentum Optimization☆188Updated 6 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆101Updated 3 months ago
- ICLR 2025 - official implementation for "I-Con: A Unifying Framework for Representation Learning"☆96Updated last week
- ☆303Updated last year
- σ-GPT: A New Approach to Autoregressive Models☆65Updated 10 months ago
- ☆98Updated 5 months ago
- supporting pytorch FSDP for optimizers☆82Updated 6 months ago
- ☆81Updated last year
- ☆150Updated 10 months ago
- ☆55Updated 7 months ago
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆84Updated last week
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources☆140Updated last month
- ☆36Updated 6 months ago
- Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"☆425Updated 6 months ago
- open source alpha evolve☆64Updated last month
- Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.…☆92Updated 5 months ago
- Explorations into whether a transformer with RL can direct a genetic algorithm to converge faster☆70Updated last month
- Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".☆127Updated 2 weeks ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆127Updated 10 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆66Updated 2 months ago
- ☆157Updated 2 months ago