Stars
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Claude Code plugins for power users
Recipes to train reward model for RLHF.
Official codebase for "SelFee: Iterative Self-Revising LLM Empowered by Self-Feedback Generation"
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Text generation using language models with multiple exit heads
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
Painter & SegGPT Series: Vision Foundation Models from BAAI
StableLM: Stability AI Language Models
A custom widget for returning mouse and keyboard events to Python. Documentation:
A set of tools for leveraging pre-trained embeddings, active learning and model explainability for effecient document classification
RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes
Code snippets created for the PyTorch discussion board
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
End-to-end training of sparse deep neural networks with little-to-no performance loss.
A Simple pytorch implementation of GradCAM and GradCAM++
🥧 Savoury implementation of the QUIC transport protocol and HTTP/3
Global Sparse Momentum SGD for pruning very deep neural networks
A curated list of neural network pruning resources.
Lookahead: A Far-sighted Alternative of Magnitude-based Pruning (ICLR 2020)
Pytorch implementation of the paper "SNIP: Single-shot Network Pruning based on Connection Sensitivity" by Lee et al.
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" by Jonathan Frankle and Michael Carbin that can be easily a…
implementation of music transformer with pytorch (ICLR2019)
custom cuda kernel for {2, 3}d relative attention with pytorch wrapper