A unified inference and post-training framework for accelerated video generation.

A framework for efficient model inference with omni-modality models

LightlyStudio - The Unified Data Platform for Multimodal ML

A profiling and performance analysis tool for machine learning

A Lightweight LLM Post-Training Library

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms

Di♪♪Rhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion

Code for 'Applying language models to algebraic topology: generating simplicial cycles using multi-labeling in Wu's formula'

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

LLMs represent numbers on a helix and manipulate that helix to do addition.

Fully open reproduction of DeepSeek-R1

Content of Online Encyclopedia of Integer Sequences (OEIS)

Recipes to train reward model for RLHF.

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

A flexible framework powered by ComfyUI for generating personalized Nobel Prize images.

The official repository of our survey paper: "Towards a Unified View of Preference Learning for Large Language Models: A Survey"

Robust recipes to align language models with human and AI preferences

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

A simple pip-installable Python tool to generate your HTML citation world map from your Google Scholar ID.

FFCV: Fast Forward Computer Vision (and other ML workloads!)

A one stop repository for generative AI research updates, interview resources, notebooks and much more!

Harness LLMs with Multi-Agent Programming

Using Langroid's Multi-Agent Framework to Build LLM Apps

Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using coresets and data selection.

[BMVC2023] Official code for TEMI: Exploring the Limits of Deep Image Clustering using Pretrained Models

Hysteria is a powerful, lightning fast and censorship resistant proxy.

A curated list of awesome Go frameworks, libraries and software

An implementation of the BADGE batch active learning algorithm.