A MAD laboratory to improve AI architecture designs 🧪
☆138Dec 17, 2024Updated last year
Alternatives and similar repositories for mad-lab
Users that are interested in mad-lab are comparing it to the libraries listed below
Sorting:
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Apr 17, 2024Updated last year
- ☆53May 20, 2024Updated last year
- Understand and test language model architectures on synthetic tasks.☆257Feb 24, 2026Updated last week
- HGRN2: Gated Linear RNNs with State Expansion☆56Aug 20, 2024Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32May 25, 2024Updated last year
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Jun 6, 2024Updated last year
- Here we will test various linear attention designs.☆62Apr 25, 2024Updated last year
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆18Mar 15, 2024Updated last year
- ☆20May 30, 2024Updated last year
- Official PyTorch Implementation of the Longhorn Deep State Space Model☆56Dec 4, 2024Updated last year
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆248Jun 6, 2025Updated 8 months ago
- JAX/Flax implementation of the Hyena Hierarchy☆34Apr 27, 2023Updated 2 years ago
- An annotated implementation of the Hyena Hierarchy paper☆34May 28, 2023Updated 2 years ago
- ☆35Apr 12, 2024Updated last year
- Parallel Associative Scan for Language Models☆18Jan 8, 2024Updated 2 years ago
- ☆11Oct 11, 2023Updated 2 years ago
- ☆33Oct 4, 2024Updated last year
- Accelerated First Order Parallel Associative Scan☆195Jan 7, 2026Updated last month
- ☆19Dec 4, 2025Updated 3 months ago
- AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning (Published in TMLR)☆23Oct 15, 2024Updated last year
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆67Apr 24, 2024Updated last year
- Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021☆29Sep 25, 2021Updated 4 years ago
- ☆36Feb 26, 2024Updated 2 years ago
- Fast modular code to create and train cutting edge LLMs☆68May 16, 2024Updated last year
- ☆27Updated this week
- Code for the paper: https://arxiv.org/pdf/2309.06979.pdf☆21Jul 29, 2024Updated last year
- A repository for research on medium sized language models.☆78May 23, 2024Updated last year
- ☆17Dec 19, 2024Updated last year
- train with kittens!☆63Oct 25, 2024Updated last year
- continous batching and parallel acceleration for RWKV6☆22Jun 28, 2024Updated last year
- ☆24Sep 25, 2024Updated last year
- Expanding linear RNN state-transition matrix eigenvalues to include negatives improves state-tracking tasks and language modeling without…☆21Mar 15, 2025Updated 11 months ago
- ☆62Dec 8, 2023Updated 2 years ago
- Official code for the paper "Attention as a Hypernetwork"☆51Feb 24, 2026Updated last week
- ☆29Jul 9, 2024Updated last year
- RWKV-X is a Linear Complexity Hybrid Language Model based on the RWKV architecture, integrating Sparse Attention to improve the model's l…☆54Jan 12, 2026Updated last month
- APPy (Annotated Parallelism for Python) enables users to annotate loops and tensor expressions in Python with compiler directives akin to…☆30Jan 28, 2026Updated last month
- Convolutions for Sequence Modeling☆913Jun 13, 2024Updated last year
- Some preliminary explorations of Mamba's context scaling.☆218Feb 8, 2024Updated 2 years ago