syncdoth / RetNetLinks
Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent, and chunkwise forward.
☆226Updated last year
Alternatives and similar repositories for RetNet
Users that are interested in RetNet are comparing it to the libraries listed below
Sorting:
- A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (http…☆106Updated last year
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆560Updated 9 months ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆362Updated last year
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆464Updated last year
- PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"☆190Updated this week
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆230Updated last year
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆417Updated 9 months ago
- ☆196Updated last month
- Code repository for Black Mamba☆255Updated last year
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆652Updated 9 months ago
- Annotated version of the Mamba paper☆490Updated last year
- Official implementation of TransNormerLLM: A Faster and Better LLM☆247Updated last year
- PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention…☆291Updated last year
- Implementation of the Llama architecture with RLHF + Q-learning☆168Updated 8 months ago
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆382Updated last year
- A repository for log-time feedforward networks☆222Updated last year
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆292Updated 4 months ago
- Recurrent Memory Transformer☆150Updated 2 years ago
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆223Updated last year
- Implementation of MambaByte in "MambaByte: Token-free Selective State Space Model" in Pytorch and Zeta☆123Updated last month
- Some preliminary explorations of Mamba's context scaling.☆217Updated last year
- Official PyTorch implementation of QA-LoRA☆141Updated last year
- Convolutions for Sequence Modeling☆898Updated last year
- ☆293Updated 9 months ago
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆437Updated 4 months ago
- Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with I…☆369Updated last year
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆240Updated 4 months ago
- The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction☆388Updated last year
- Efficient Infinite Context Transformers with Infini-attention Pytorch Implementation + QwenMoE Implementation + Training Script + 1M cont…☆84Updated last year
- Implementation of Block Recurrent Transformer - Pytorch☆221Updated last year