Xuechen Li's repositories
private-transformers
A codebase that makes differentially private training of transformers easy.
ml-swissknife
An ML research codebase built with friends :)
accelerate
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
bitsandbytes
8-bit CUDA functions for PyTorch
failure-directions
Distilling Model Failures as Directions in Latent Space
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
imagen-pytorch
Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
jax_privacy
Algorithms for Privacy-Preserving Machine Learning in JAX
latent-diffusion
High-Resolution Image Synthesis with Latent Diffusion Models
opacus
Training PyTorch models with differential privacy
open_flamingo
An open-source framework for training large multimodal models.
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
phc-winner-argon2
The password hash Argon2, winner of PHC
RL4LMs-lxuechen
A modular RL library to fine-tune language models to human preferences
self-instruct
Aligning pretrained language models with instruction data generated by themselves.
shap
A game theoretic approach to explain the output of any machine learning model.
summarize-from-feedback
Code for "Learning to summarize from human feedback"
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
triton
Development repository for the Triton language and compiler
trl-lxuechen
Train transformer language models with reinforcement learning.