emalach / LinearLMLinks
Code for the paper: https://arxiv.org/pdf/2309.06979.pdf
☆21Updated last year
Alternatives and similar repositories for LinearLM
Users that are interested in LinearLM are comparing it to the libraries listed below
Sorting:
- Official Code Repository for the paper "Key-value memory in the brain"☆29Updated 8 months ago
- Parallel Associative Scan for Language Models☆17Updated last year
- ☆11Updated 2 years ago
- Efficient PScan implementation in PyTorch☆16Updated last year
- ☆33Updated last year
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated last year
- ☆33Updated last year
- ☆48Updated last year
- ☆31Updated last year
- Experiments on the impact of depth in transformers and SSMs.☆36Updated 11 months ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- Here we will test various linear attention designs.☆61Updated last year
- Expanding linear RNN state-transition matrix eigenvalues to include negatives improves state-tracking tasks and language modeling without…☆17Updated 7 months ago
- ☆20Updated last year
- Stick-breaking attention☆61Updated 3 months ago
- ☆53Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)☆78Updated last year
- Awesome Triton Resources☆36Updated 6 months ago
- Blog post☆17Updated last year
- ☆13Updated 4 months ago
- Using FlexAttention to compute attention with different masking patterns☆47Updated last year
- Implementation of Hyena Hierarchy in JAX☆10Updated 2 years ago
- Mamba support for transformer lens☆18Updated last year
- ☆56Updated last year
- Source-to-Source Debuggable Derivatives in Pure Python☆15Updated last year
- Open-sourcing code associated with the AAAI-25 paper "On the Expressiveness and Length Generalization of Selective State-Space Models on …☆15Updated last month
- ☆22Updated last year
- FlexAttention w/ FlashAttention3 Support☆27Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆84Updated 11 months ago
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆39Updated last year