Sky-T1: Train your own O1 preview model within $450

BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature

A generative world for general-purpose robotics & embodied AI learning.

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

XQ-GAN🚀: An Open-source Image Tokenization Framework for Autoregressive Generation

A suite of image and video neural tokenizers

Statistical plotting recipes for Plots.jl

Source code for the crAssphage project

List of papers on Self-Correction of LLMs.

[NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Align Anything: Training All-modality Model with Feedback

A bibliography and survey of the papers surrounding o1

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

PyTorch building blocks for OLMo

Composable building blocks to build Llama Apps

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

Chai-1, SOTA model for biomolecular structure prediction

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

Yet another redundant workflow engine

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838