lucidrains / grokfast-pytorchLinks
Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
☆101Updated 7 months ago
Alternatives and similar repositories for grokfast-pytorch
Users that are interested in grokfast-pytorch are comparing it to the libraries listed below
Sorting:
- ☆81Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jax☆89Updated last year
- Collection of autoregressive model implementation☆86Updated 3 months ago
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 6 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆18Updated last week
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated 11 months ago
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆88Updated last month
- Implementation of the Llama architecture with RLHF + Q-learning☆166Updated 6 months ago
- DeMo: Decoupled Momentum Optimization☆190Updated 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
- ☆100Updated last week
- Implementation of a Light Recurrent Unit in Pytorch☆48Updated 9 months ago
- Implementation of Infini-Transformer in Pytorch☆111Updated 7 months ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆52Updated 4 months ago
- σ-GPT: A New Approach to Autoregressive Models☆67Updated 11 months ago
- ☆34Updated 10 months ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆124Updated last year
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆120Updated 9 months ago
- ☆21Updated 8 months ago
- A byte-level decoder architecture that matches the performance of tokenized Transformers.☆64Updated last year
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 2 months ago
- ☆53Updated last year
- Utilities for PyTorch distributed☆24Updated 5 months ago
- A State-Space Model with Rational Transfer Function Representation.☆79Updated last year
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆37Updated 5 months ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆56Updated last year
- Fast, Modern, and Low Precision PyTorch Optimizers☆103Updated this week
- GoldFinch and other hybrid transformer components☆46Updated last year
- Implementation of Mind Evolution, Evolving Deeper LLM Thinking, from Deepmind☆56Updated 2 months ago
- Repository for code used in the xVal paper☆140Updated last year