albertfgu / awesome-ssm-mlLinks
β12Updated last year
Alternatives and similar repositories for awesome-ssm-ml
Users that are interested in awesome-ssm-ml are comparing it to the libraries listed below
Sorting:
- β31Updated 7 months ago
- A MAD laboratory to improve AI architecture designs π§ͺβ122Updated 6 months ago
- Non official implementation of the Linear Recurrent Unit (LRU, Orvieto et al. 2023)β53Updated 7 months ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAXβ83Updated last year
- Accelerated First Order Parallel Associative Scanβ182Updated 10 months ago
- Maximal Update Parametrization (ΞΌP) with Flax & Optax.β11Updated last year
- β292Updated 5 months ago
- Pytorch implementation of Simplified Structured State-Spaces for Sequence Modeling (S5)β76Updated last year
- β80Updated 7 months ago
- β40Updated last year
- Minimal pretraining script for language modeling in PyTorch. Supporting torch compilation and DDP. It includes a model implementation andβ¦β25Updated last week
- Implementation of GateLoop Transformer in Pytorch and Jaxβ89Updated last year
- Implementations of various linear RNN layers using pytorch and tritonβ53Updated last year
- β37Updated last year
- Minimal but scalable implementation of large language models in JAXβ35Updated 7 months ago
- Implementation of PSGD optimizer in JAXβ33Updated 5 months ago
- β126Updated last month
- Implementation of Soft Actor Critic and some of its improvements in Pytorchβ60Updated 4 months ago
- Accelerated replay buffers in JAXβ41Updated 2 years ago
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]β103Updated last year
- β104Updated 2 weeks ago
- Understand and test language model architectures on synthetic tasks.β218Updated 2 weeks ago
- Accelerated minigrid environments with JAXβ139Updated 2 weeks ago
- Parallelizing non-linear sequential models over the sequence lengthβ52Updated 5 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.β33Updated last year