lucidrains / JEPA-pytorch
☆114Updated this week
Related projects: ⓘ
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)☆184Updated 2 years ago
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆202Updated 3 weeks ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆101Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jax☆86Updated 3 months ago
- Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper☆78Updated 2 years ago
- Implementation of Hierarchical Transformer Memory (HTM) for Pytorch☆73Updated 3 years ago
- Experiments in Joint Embedding Predictive Architectures (JEPAs).☆32Updated 8 months ago
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆203Updated last year
- Explorations into the recently proposed Taylor Series Linear Attention☆85Updated last month
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆94Updated last year
- ☆42Updated this week
- Another attempt at a long-context / efficient transformer by me☆37Updated 2 years ago
- ☆192Updated this week
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆53Updated 4 months ago
- Implementation of Discrete Key / Value Bottleneck, in Pytorch☆87Updated last year
- Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI☆74Updated 2 years ago
- Implementation of 🌻 Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorch☆87Updated 8 months ago
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆45Updated last month
- Implementation of some personal helper functions for Einops, my most favorite tensor manipulation library ❤️☆52Updated last year
- σ-GPT: A New Approach to Autoregressive Models☆53Updated last month
- Implementation of Block Recurrent Transformer - Pytorch☆211Updated 3 weeks ago
- A MAD laboratory to improve AI architecture designs 🧪☆84Updated 4 months ago
- Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE …☆113Updated 6 months ago
- CUDA implementation of autoregressive linear attention, with all the latest research findings☆43Updated last year
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆56Updated 10 months ago
- Implementation of an Attention layer where each head can attend to more than just one token, using coordinate descent to pick topk☆46Updated last year
- ☆23Updated this week
- ☆27Updated this week
- Automatic gradient descent☆206Updated last year
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆82Updated 3 weeks ago