DjAzDeck

tnt

A lightweight library for PyTorch training tools and utilities

factor-fields

[SIGGRAPH 2023] We provide a unified formula for neural fields (Factor Fields) and a novel dictionary factorization (Dictionary Fields)

hyperbolic-rl

kernel_tuner

Kernel Tuner

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

stanford_alpaca

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

EVA

EVA Series: Visual Representation Fantasies from BAAI

PhySO

Physical Symbolic Optimization

FFCV-SSL

FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.

gptq

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

rl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

HIP-Examples

Examples for HIP

json-schema-for-humans

Quickly generate HTML documentation from a JSON schema

efficient-gnns

Code and resources on scalable and efficient Graph Neural Networks

randomfun

Notebooks and various random fun

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

latentplan

Code release for Efficient Planning in a Compact Latent Action Space (ICLR2023) https://arxiv.org/abs/2208.10291.

GNT

[ICLR 2023] "Is Attention All NeRF Needs?" by Mukund Varma T*, Peihao Wang* , Xuxi Chen, Tianlong Chen, Subhashini Venugopalan, Zhangyang Wang

Prompt4ReasoningPapers

[ACL 2023] Reasoning with Language Model Prompting: A Survey

PaSST

Efficient Training of Audio Transformers with Patchout

PaLM-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

conformal-prediction

Lightweight, useful implementation of conformal prediction on real data.

diplomacy_cicero

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

COSCO

[TPDS'21] COSCO: Container Orchestration using Co-Simulation and Gradient Based Optimization for Fog Computing Environments

tripy

A package for efficient likelihood evaluation and sampling for Multivariate Normal distributions with structured covariance matrices

DESDEO

An open source framework for interactive multiobjective optimization methods

alphatensor

machine-learning-articles

🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.

whisper

Robust Speech Recognition via Large-Scale Weak Supervision