fkodom / yet-another-retnetLinks
A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (https://arxiv.org/pdf/2307.08621.pdf)
☆106Updated last year
Alternatives and similar repositories for yet-another-retnet
Users that are interested in yet-another-retnet are comparing it to the libraries listed below
Sorting:
- Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent,…☆226Updated last year
- Implementation of Infini-Transformer in Pytorch☆113Updated 9 months ago
- Implementation of Agent Attention in Pytorch☆91Updated last year
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆230Updated last year
- Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆56Updated this week
- PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"☆192Updated 3 weeks ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆119Updated last year
- Implementation of Block Recurrent Transformer - Pytorch☆221Updated last year
- ☆292Updated 10 months ago
- Griffin MQA + Hawk Linear RNN Hybrid☆89Updated last year
- Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"☆161Updated 8 months ago
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆132Updated last week
- A repository for DenseSSMs☆89Updated last year
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆331Updated 6 months ago
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆222Updated last year
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆99Updated last year
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆91Updated 4 months ago
- Official PyTorch Implementation of "The Hidden Attention of Mamba Models"☆228Updated last week
- Implementation of the Llama architecture with RLHF + Q-learning☆167Updated 8 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆99Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jax☆90Updated last year
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆123Updated last year
- ☆105Updated last year
- Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling☆207Updated last week
- Implementation of MoE Mamba from the paper: "MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts" in Pytorch and Ze…☆112Updated this week
- ☆302Updated 6 months ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆363Updated last year
- Randomized Positional Encodings Boost Length Generalization of Transformers☆82Updated last year
- Pytorch Implementation of the sparse attention from the paper: "Generating Long Sequences with Sparse Transformers"☆89Updated this week
- (Unofficial) Implementation of dilated attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens" (https://arxiv.org/abs/2307…☆53Updated 2 years ago