lucidrains / hyper-connectionsView external linksLinks
Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public
☆172Feb 4, 2026Updated last week
Alternatives and similar repositories for hyper-connections
Users that are interested in hyper-connections are comparing it to the libraries listed below
Sorting:
- implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880☆302Updated this week
- Implementation of a holodeck, written in Pytorch☆18Nov 1, 2023Updated 2 years ago
- Utilities for PyTorch distributed☆25Feb 27, 2025Updated 11 months ago
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆135Oct 15, 2025Updated 4 months ago
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆293Jun 3, 2025Updated 8 months ago
- DiffPhase: Generative Diffusion-based STFT Phase Retrieval☆16Sep 21, 2023Updated 2 years ago
- Implementation of the proposed MaskBit from Bytedance AI☆83Nov 12, 2024Updated last year
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"☆182Jun 20, 2024Updated last year
- Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.☆17Apr 22, 2025Updated 9 months ago
- Collection of Acceleration Methods for Generative AI☆29Dec 9, 2025Updated 2 months ago
- Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch☆514Jan 18, 2026Updated 3 weeks ago
- Algorithms for approximate attention in LLMs☆21Apr 14, 2025Updated 10 months ago
- Custom triton kernels for training Karpathy's nanoGPT.☆19Oct 21, 2024Updated last year
- Implementation of the proposed LVMAE, from the paper, Extending Video Masked Autoencoders to 128 frames, in Pytorch☆55Nov 25, 2024Updated last year
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆126Jul 26, 2024Updated last year
- Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in P…☆207Feb 14, 2024Updated 2 years ago
- The 2D discrete wavelet transform for JAX☆45Feb 28, 2023Updated 2 years ago
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Oct 22, 2023Updated 2 years ago
- Standalone Product Key Memory module in Pytorch - for augmenting Transformer models☆87Nov 1, 2025Updated 3 months ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆549May 16, 2025Updated 9 months ago
- Fast, free, easy, and object-agnostic video anonymization☆11Dec 12, 2020Updated 5 years ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆92Jun 18, 2024Updated last year
- A collections of audio codecs with a standardized API☆35May 27, 2025Updated 8 months ago
- ☆23Oct 15, 2024Updated last year
- Implementation of the algorithm detailed in paper "Evolutionary design of molecules based on deep learning and a genetic algorithm"☆24Dec 15, 2023Updated 2 years ago
- ☆13Apr 23, 2025Updated 9 months ago
- Implementation of an Attention layer where each head can attend to more than just one token, using coordinate descent to pick topk☆47Jul 16, 2023Updated 2 years ago
- ☆27May 3, 2024Updated last year
- Focused on fast experimentation and simplicity☆80Dec 24, 2024Updated last year
- Explorations into the recently proposed Taylor Series Linear Attention☆100Aug 18, 2024Updated last year
- GoldFinch and other hybrid transformer components☆12Dec 9, 2025Updated 2 months ago
- ☆14Mar 2, 2025Updated 11 months ago
- recipe for training fully-featured self supervised image jepa models☆12Jun 4, 2025Updated 8 months ago
- My implementation of diffusion (like) models☆11Apr 14, 2023Updated 2 years ago
- Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI☆1,326Jan 27, 2026Updated 2 weeks ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆55Mar 25, 2025Updated 10 months ago
- A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch☆126Aug 25, 2025Updated 5 months ago
- [Oral; Neurips OPT2024 ] μLO: Compute-Efficient Meta-Generalization of Learned Optimizers☆14Mar 18, 2025Updated 10 months ago
- [NeurIPS 2025, Spotlight]: Ambient-o: Training Good models with Bad Data.☆30Jan 21, 2026Updated 3 weeks ago