lucidrains / grokfast-pytorch
Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
☆95Updated last month
Alternatives and similar repositories for grokfast-pytorch:
Users that are interested in grokfast-pytorch are comparing it to the libraries listed below
- ☆78Updated 9 months ago
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆66Updated last week
- supporting pytorch FSDP for optimizers☆75Updated last month
- Implementation of a Light Recurrent Unit in Pytorch☆48Updated 3 months ago
- σ-GPT: A New Approach to Autoregressive Models☆61Updated 5 months ago
- ☆53Updated last year
- ☆150Updated last month
- Explorations into the recently proposed Taylor Series Linear Attention☆92Updated 5 months ago
- Collection of autoregressive model implementation☆77Updated 3 weeks ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆87Updated 7 months ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆119Updated 6 months ago
- Implementation of Infini-Transformer in Pytorch☆109Updated 3 weeks ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆115Updated 5 months ago
- Focused on fast experimentation and simplicity☆65Updated last month
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆91Updated 2 months ago
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆101Updated 2 months ago
- Implementation of DreamerV3 in Pytorch☆42Updated 2 months ago
- ☆49Updated 10 months ago
- ☆41Updated last year
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆54Updated 8 months ago
- A State-Space Model with Rational Transfer Function Representation.☆77Updated 8 months ago
- ☆27Updated 6 months ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆113Updated 3 months ago
- ☆70Updated 5 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆18Updated last week
- ☆69Updated last week
- Latent Diffusion Language Models☆68Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆102Updated last month
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆121Updated 9 months ago
- DeMo: Decoupled Momentum Optimization☆172Updated last month