Piyushi-0

FedLF

speculative-decoding

Explorations into some recent techniques surrounding speculative decoding

unscented-autoencoder

Accompanying code for the ICML'23 paper "Unscented Autoencoder", authored by Faris Janjos, Lars Rosenbaum, Maxim Dolgov, and J. Marius Zoellner.

gpu-optimization-workshop

Slides, notes, and materials for the workshop

the-book-of-secret-knowledge

A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

llm.c

LLM training in simple, raw C/CUDA

DomainLab

modular domain generalization: https://pypi.org/project/domainlab/

plandex

AI driven development in your terminal. Designed for large, real-world tasks.

diffprog.github.io

Website for the book "The Elements of Differentiable Programming".

github2file

VACDB

Variance-aware Contextual Dueling Bandits

sampling_diffusion

Improved sampling via learned diffusions (ICLR2024) and an optimal control perspective on diffusion-based generative modeling (SBM@NeurIPS2022)

dift

[NeurIPS'23] Emergent Correspondence from Image Diffusion

uotod

Unbalanced Optimal Transport: A Unified Framework for Object Detection

simalign

Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)

LLM-Uncertainty-Bench

Benchmarking LLMs via Uncertainty Quantification

Diffusion-Models-Papers-Survey-Taxonomy

Diffusion model papers, survey, and taxonomy

fbde

Code for "Fair Densities via Boosting the Sufficient Statistics of Exponential Families"

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

MoEL

MoEL: Mixture of Empathetic Listeners

mixture-of-experts

Training two separate expert neural networks and one gater that can switch the expert networks.

soft-mixture-of-experts

PyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)

soft-moe

PyTorch implementation of "From Sparse to Soft Mixtures of Experts"

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

tutel

Tutel MoE: An Optimized Mixture-of-Experts Implementation

soft-moe-pytorch

Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch

gait

Code for the paper GAIT: A Geometric Approach to Information Theory

cooper

A general-purpose, deep learning-first library for constrained optimization in PyTorch

gpt-pilot

The first real AI developer