lxuechen

torchsde

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

BDMC

PyTorch implementation of Bidirectional Monte Carlo, Annealed Importance Sampling, and Hamiltonian Monte Carlo.

Differentially-Private-Fine-tuning-of-Language-Models

Code for ICLR 2022 submission "Differentially Private Fine-tuning of Language Models".

inference-suboptimality

Code for "Inference Suboptimality in Variational Autoencoders"

latent_ode

Code for "Latent ODEs for Irregularly-Sampled Time Series" paper

ml-swissknife

An ML research codebase built with friends :)

private-transformers

A codebase that makes differentially private training of transformers easy.

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

alpaca_farm

A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

lxuechen/ml-swissknife

An ML research codebase built with friends :)

lxuechen/LLM-Training-Puzzles

What would you do with 1000 H100s...

lxuechen/minRLHF

A minimal PyTorch re-implementation of RLHF

lxuechen/accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

lxuechen/awesome-ai-agents

A list of AI autonomous agents

lxuechen/bitsandbytes

8-bit CUDA functions for PyTorch

lxuechen/build-your-own-x

Master programming by recreating your favorite technologies from scratch.

lxuechen/codegpt

VSCode extension that allows you to use GPT3 inside the IDE

lxuechen/evals

lxuechen/FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

lxuechen/flash-attention

Fast and memory-efficient exact attention

lxuechen/label-studio-ml-backend

Configs and boilerplates for Label Studio's Machine Learning backend

lxuechen/levanter

Legibile, Scalable, Reproducible Foundation Models with Named Tensors and Jax

lxuechen/lxuechen

lxuechen/Megatron-LM

Ongoing research training transformer models at scale

lxuechen/open_flamingo

An open-source framework for training large multimodal models.

lxuechen/peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

lxuechen/Quark

lxuechen/RL4LMs-lxuechen

A modular RL library to fine-tune language models to human preferences

lxuechen/self-instruct

Aligning pretrained language models with instruction data generated by themselves.

lxuechen/sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

lxuechen/shap

A game theoretic approach to explain the output of any machine learning model.

lxuechen/shortcuts_public

lxuechen/summarize-from-feedback

Code for "Learning to summarize from human feedback"

lxuechen/tensor_parallel

Automatically split your PyTorch models on multiple GPUs for training & inference

lxuechen/thesis

my thesis

lxuechen/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

lxuechen/trl-lxuechen

Train transformer language models with reinforcement learning.

lxuechen/trlx-lxuechen

lxuechen/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs