tobiaskatsch / GatedLinearRNN
☆24Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for GatedLinearRNN
- Implementation of Spectral State Space Models☆17Updated 9 months ago
- RWKV model implementation☆38Updated last year
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆36Updated last year
- Latent Diffusion Language Models☆67Updated last year
- ☆46Updated last month
- Implementation of GateLoop Transformer in Pytorch and Jax☆86Updated 5 months ago
- The official code of "Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers"☆16Updated 4 months ago
- sigma-MoE layer☆18Updated 10 months ago
- GoldFinch and other hybrid transformer components☆40Updated 4 months ago
- Codes accompanying the paper "LaProp: a Better Way to Combine Momentum with Adaptive Gradient"☆22Updated 4 years ago
- ☆29Updated 7 months ago
- ☆39Updated 10 months ago
- ☆21Updated last month
- ☆18Updated last month
- ☆36Updated 10 months ago
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆35Updated 11 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆16Updated this week
- BitLinear implementation☆21Updated last month
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆35Updated 4 months ago
- Experiment of using Tangent to autodiff triton☆72Updated 10 months ago
- ☆29Updated this week
- Triton Implementation of HyperAttention Algorithm☆46Updated 11 months ago
- ☆53Updated 10 months ago
- ☆27Updated 4 months ago
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆29Updated 3 weeks ago
- Here we will test various linear attention designs.☆56Updated 6 months ago
- ☆31Updated 2 months ago
- DiCE: The Infinitely Differentiable Monte-Carlo Estimator☆30Updated last year
- RWKV-7: Surpassing GPT☆47Updated last week
- ☆31Updated 10 months ago