ohaijen
Follow
Stars
LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
Training Sparse Autoencoders on Language Models
A one-stop repository for large language model (LLM) unlearning. Supports TOFU, MUSE and is an easily extensible framework for new datasets, evaluations, methods, and other benchmarks.
OpenMMLab Pose Estimation Toolbox and Benchmark.
Software design principles for machine learning applications
A simple, extensible Markov chain generator.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Micro Llama is a small Llama based model with 300M parameters trained from scratch with $500 budget
[ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
Yes, it's another chat over documents implementation... but this one is entirely local!
A curated list of Large Language Model (LLM) Interpretability resources.
This repository contains two datasets with multi-turn adversarial conversations generated by human agents interacting with a dialog model and rated for safety by two corresponding diverse rater pools.
Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.
This is a collection of our NAS and Vision Transformer work.
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
MAT: Mask-Aware Transformer for Large Hole Image Inpainting
This repository contains implementations and illustrative code to accompany DeepMind publications
Acceptance rates for the major AI conferences
Efficient PyTorch Hessian eigendecomposition tools!
Implementations and checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX (Flax).
A list of AI Art courses, tools, libraries, people, and places.
Recode of book "Dessins géométriques et artistiques avec votre micro-ordinateur" (1985) with p5js
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
Source code and documentation for "FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data" -- Transaction on Machine Learning Research (TMLR) 2022
DataTables but in TypeScript transpiled to Vanilla JS
(WIP) Implementation of Creative Adversarial Networks https://arxiv.org/pdf/1706.07068.pdf