lucidrains / pytorch-custom-utilsLinks
Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new AI research
☆126Updated last year
Alternatives and similar repositories for pytorch-custom-utils
Users that are interested in pytorch-custom-utils are comparing it to the libraries listed below
Sorting:
- Implementation of Infini-Transformer in Pytorch☆112Updated last year
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated last year
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆134Updated 3 months ago
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆122Updated last year
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆163Updated 2 weeks ago
- Implementation of the Llama architecture with RLHF + Q-learning☆170Updated last year
- Implementation of Agent Attention in Pytorch☆93Updated last year
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆103Updated last year
- A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch☆126Updated 5 months ago
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆224Updated last year
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆57Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jax☆92Updated last year
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆231Updated last year
- ☆82Updated last year
- Implementation of a Light Recurrent Unit in Pytorch☆49Updated last year
- Implementation of Block Recurrent Transformer - Pytorch☆223Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆59Updated 2 years ago
- Implementation of 🌻 Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorch☆91Updated 2 years ago
- ☆92Updated last year
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆220Updated 2 years ago
- Explorations into whether a transformer with RL can direct a genetic algorithm to converge faster☆71Updated 8 months ago
- Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".☆144Updated 2 months ago
- Implementation of a multimodal diffusion transformer in Pytorch☆107Updated last year
- Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.☆160Updated last year
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆72Updated 2 months ago
- Experimental CUDA kernel framework unifying typed dimensions, NVRTC JIT specialization, and ML‑guided tuning.☆46Updated last week
- A repository for log-time feedforward networks☆224Updated last year
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆134Updated 3 months ago
- supporting pytorch FSDP for optimizers☆84Updated last year