facebookresearch / megaLinks
Sequence modeling with Mega.
☆296Updated 2 years ago
Alternatives and similar repositories for mega
Users that are interested in mega are comparing it to the libraries listed below
Sorting:
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆204Updated last year
- Code for the ALiBi method for transformer language models (ICLR 2022)☆535Updated last year
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆230Updated 9 months ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆225Updated 3 years ago
- ☆163Updated 2 years ago
- FairSeq repo with Apollo optimizer☆114Updated last year
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆100Updated 2 years ago
- Long Range Arena for Benchmarking Efficient Transformers☆757Updated last year
- An implementation of local windowed attention for language modeling☆454Updated 5 months ago
- ☆355Updated last year
- ☆147Updated 2 years ago
- ☆166Updated last year
- [ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention☆193Updated 2 years ago
- Randomized Positional Encodings Boost Length Generalization of Transformers☆81Updated last year
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆214Updated 2 years ago
- Implementation of Linformer for Pytorch☆288Updated last year
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆214Updated 10 months ago
- An implementation of masked language modeling for Pytorch, made as concise and simple as possible☆180Updated last year
- Implementation of Block Recurrent Transformer - Pytorch☆219Updated 10 months ago
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆409Updated 5 months ago
- Recurrent Memory Transformer☆149Updated last year
- Implementation of Memformer, a Memory-augmented Transformer, in Pytorch☆118Updated 4 years ago
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆136Updated last year
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆341Updated last year
- Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method (NeurIPS 2021)☆61Updated 3 years ago
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆379Updated last year
- Fully featured implementation of Routing Transformer☆295Updated 3 years ago
- Memory Efficient Attention (O(sqrt(n)) for Jax and PyTorch☆184Updated 2 years ago
- ☆376Updated last year
- Standalone Product Key Memory module in Pytorch - for augmenting Transformer models☆80Updated 10 months ago