lucidrains / grokfast-pytorchLinks
Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
☆101Updated 8 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:
- ☆82Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jax☆90Updated last year
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated last year
- Collection of autoregressive model implementation☆86Updated 4 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆128Updated last year
- Implementation of a Light Recurrent Unit in Pytorch☆48Updated 11 months ago
- Implementation of the Llama architecture with RLHF + Q-learning☆166Updated 7 months ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆124Updated last year
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆89Updated 2 months ago
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 7 months ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆120Updated 10 months ago
- σ-GPT: A New Approach to Autoregressive Models☆67Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Updated last month
- Implementation of Infini-Transformer in Pytorch☆111Updated 8 months ago
- ☆102Updated last month
- DeMo: Decoupled Momentum Optimization☆190Updated 9 months ago
- ☆53Updated last year
- Griffin MQA + Hawk Linear RNN Hybrid☆89Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated last year
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆68Updated 3 weeks ago
- LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence☆59Updated 3 years ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆53Updated 5 months ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆56Updated last year
- ☆57Updated 11 months ago
- ☆49Updated last year
- Getting crystal-like representations with harmonic loss☆194Updated 5 months ago
- A byte-level decoder architecture that matches the performance of tokenized Transformers.☆65Updated last year
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 4 months ago
- Implementation of 2-simplicial attention proposed by Clift et al. (2019) and the recent attempt to make practical in Fast and Simplex, Ro…☆46Updated last week
- The AdEMAMix Optimizer: Better, Faster, Older.☆186Updated last year