shawntan / SUTLinks
Repository for Sparse Universal Transformers
☆20Updated 2 years ago
Alternatives and similar repositories for SUT
Users that are interested in SUT are comparing it to the libraries listed below
Sorting:
- ☆61Updated last year
- Official code for the paper "Attention as a Hypernetwork"☆46Updated last year
- Experiments on the impact of depth in transformers and SSMs.☆38Updated last month
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- ☆45Updated 2 years ago
- ☆53Updated last year
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 5 months ago
- HGRN2: Gated Linear RNNs with State Expansion☆55Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆85Updated last year
- Official Code Repository for the paper "Key-value memory in the brain"☆29Updated 9 months ago
- Here we will test various linear attention designs.☆62Updated last year
- Stick-breaking attention☆61Updated 5 months ago
- ☆34Updated last year
- ☆89Updated last year
- ☆50Updated last year
- Parallelizing non-linear sequential models over the sequence length☆56Updated 5 months ago
- ☆33Updated last year
- Source code for the paper "Positional Attention: Expressivity and Learnability of Algorithmic Computation"☆14Updated 6 months ago
- ☆35Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated 2 years ago
- ☆83Updated 2 years ago
- Efficient PScan implementation in PyTorch☆17Updated last year
- Official implementation of the transformer (TF) architecture suggested in a paper entitled "Looped Transformers as Programmable Computers…☆29Updated 2 years ago
- Parallel Associative Scan for Language Models☆18Updated last year
- ☆16Updated last year
- Griffin MQA + Hawk Linear RNN Hybrid☆89Updated last year
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated last year
- ☆23Updated last year
- The Energy Transformer block, in JAX☆62Updated last year
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆40Updated 2 years ago