emalach / LinearLM
Code for the paper: https://arxiv.org/pdf/2309.06979.pdf
☆19Updated 7 months ago
Alternatives and similar repositories for LinearLM:
Users that are interested in LinearLM are comparing it to the libraries listed below
- Xmixers: A collection of SOTA efficient token/channel mixers☆11Updated 4 months ago
- Here we will test various linear attention designs.☆59Updated 10 months ago
- ☆33Updated last year
- Awesome Triton Resources☆20Updated 3 months ago
- ☆47Updated last year
- Parallel Associative Scan for Language Models☆18Updated last year
- ☆51Updated 9 months ago
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated 9 months ago
- Stick-breaking attention☆48Updated this week
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆25Updated 10 months ago
- ☆30Updated last year
- ☆18Updated 9 months ago
- ☆22Updated last year
- Source-to-Source Debuggable Derivatives in Pure Python☆15Updated last year
- ☆48Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated 9 months ago
- Blog post☆17Updated last year
- ☆11Updated last year
- Experiments on the impact of depth in transformers and SSMs.☆23Updated 4 months ago
- Official Code Repository for the paper "Key-value memory in the brain"☆23Updated 2 weeks ago
- Personal solutions to the Triton Puzzles☆18Updated 7 months ago
- HGRN2: Gated Linear RNNs with State Expansion☆53Updated 6 months ago
- Experiment of using Tangent to autodiff triton☆76Updated last year
- Implementation of Hyena Hierarchy in JAX☆10Updated last year
- ☆19Updated last year
- ☆51Updated 8 months ago
- ☆30Updated 5 months ago
- Code for the note "NF4 Isn't Information Theoretically Optimal (and that's Good)☆18Updated last year