syncdoth / RetNet
Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent, and chunkwise forward.
☆226Updated 6 months ago
Related projects: ⓘ
- A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (http…☆101Updated 9 months ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆278Updated 3 months ago
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆530Updated 4 months ago
- Code repository for Black Mamba☆218Updated 7 months ago
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆391Updated 7 months ago
- PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention…☆271Updated 4 months ago
- PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"☆120Updated last week
- Recurrent Memory Transformer☆148Updated last year
- Official PyTorch implementation of QA-LoRA☆111Updated 6 months ago
- Annotated version of the Mamba paper☆445Updated 6 months ago
- ☆169Updated this week
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆423Updated 5 months ago
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆615Updated this week
- Official implementation of TransNormerLLM: A Faster and Better LLM☆223Updated 7 months ago
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆222Updated 2 weeks ago
- The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction☆361Updated 2 months ago
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆374Updated 3 months ago
- (Unofficial) Implementation of dilated attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens" (https://arxiv.org/abs/2307…☆49Updated last year
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆233Updated 4 months ago
- ☆278Updated 3 weeks ago
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆285Updated this week
- X-LoRA: Mixture of LoRA Experts☆152Updated last month
- NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day☆248Updated 10 months ago
- Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling☆153Updated last week
- Build high-performance AI models with modular building blocks☆377Updated this week
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆452Updated last month
- ☆191Updated 3 months ago
- Transformers with Arbitrarily Large Context☆613Updated last month
- An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"☆1,154Updated 10 months ago
- The repository for the code of the UltraFastBERT paper☆508Updated 5 months ago