syncdoth / RetNet
Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent, and chunkwise forward.
☆225Updated 11 months ago
Alternatives and similar repositories for RetNet:
Users that are interested in RetNet are comparing it to the libraries listed below
- A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (http…☆104Updated last year
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆443Updated 9 months ago
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆547Updated last month
- ☆217Updated 8 months ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆306Updated 7 months ago
- ☆180Updated this week
- Official implementation of TransNormerLLM: A Faster and Better LLM☆238Updated last year
- Some preliminary explorations of Mamba's context scaling.☆213Updated last year
- Official PyTorch implementation of QA-LoRA☆124Updated 11 months ago
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆403Updated last month
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆636Updated last month
- An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"☆1,173Updated last year
- PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"☆157Updated 2 weeks ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆220Updated 2 months ago
- Implementation of MambaByte in "MambaByte: Token-free Selective State Space Model" in Pytorch and Zeta☆114Updated 2 weeks ago
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆258Updated 9 months ago
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores☆294Updated last month
- (Unofficial) Implementation of dilated attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens" (https://arxiv.org/abs/2307…☆50Updated last year
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆582Updated 11 months ago
- ☆138Updated last year
- Recurrent Memory Transformer☆149Updated last year
- PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention…☆286Updated 9 months ago
- Efficient Infinite Context Transformers with Infini-attention Pytorch Implementation + QwenMoE Implementation + Training Script + 1M cont…☆76Updated 9 months ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆675Updated 6 months ago
- Annotated version of the Mamba paper☆472Updated 11 months ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 4 months ago
- For releasing code related to compression methods for transformers, accompanying our publications☆405Updated 3 weeks ago
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆225Updated 5 months ago
- Large Context Attention☆681Updated 3 weeks ago
- A simple and effective LLM pruning approach.☆709Updated 6 months ago