Modeling, training, eval, and inference code for OLMo
Python 6.7k 801
Data and tools for generating and inspecting OLMo pre-training data.
Python 1.5k 205
An open-source platform for Visual AI.
C# 1.8k 297
Toolkit for linearizing PDFs for LLM datasets/training
Python 19.7k 1.6k
OLMoE: Open Mixture-of-Experts Language Models
Jupyter Notebook 1.1k 122
AllenAI's post-training codebase
Earth system foundation model data, training, and eval
PyTorch building blocks for the OLMo ecosystem
An end-to-end open ecosystem for robot learning
Data-driven scientific discovery via Bayesian surprise
Deprecated: use https://github.com/allenai/playground
A set resources for Ai2 design
