jopetty / word-problemLinks
Experiments on the impact of depth in transformers and SSMs.
☆34Updated 10 months ago
Alternatives and similar repositories for word-problem
Users that are interested in word-problem are comparing it to the libraries listed below
Sorting:
- ☆53Updated last year
- ☆49Updated last year
- Expanding linear RNN state-transition matrix eigenvalues to include negatives improves state-tracking tasks and language modeling without…☆17Updated 6 months ago
- Efficient PScan implementation in PyTorch☆16Updated last year
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- ☆33Updated last year
- ☆34Updated last year
- Here we will test various linear attention designs.☆62Updated last year
- ☆11Updated last year
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated last year
- Parallel Associative Scan for Language Models☆18Updated last year
- ☆38Updated last year
- Blog post☆17Updated last year
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆66Updated last year
- Stick-breaking attention☆60Updated 3 months ago
- Official Code Repository for the paper "Key-value memory in the brain"☆28Updated 7 months ago
- Simple and efficient pytorch-native transformer training and inference (batched)☆79Updated last year
- ☆56Updated last year
- ☆45Updated last year
- ☆13Updated 4 months ago
- ☆58Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆84Updated 11 months ago
- ☆32Updated last year
- ☆33Updated 11 months ago
- Parallelizing non-linear sequential models over the sequence length☆54Updated 3 months ago
- Code for "Theoretical Foundations of Deep Selective State-Space Models" (NeurIPS 2024)☆15Updated 8 months ago
- ☆34Updated 10 months ago
- ☆19Updated 4 months ago
- Official code for the paper "Attention as a Hypernetwork"☆42Updated last year
- Griffin MQA + Hawk Linear RNN Hybrid☆89Updated last year