AI2

OLMo

Modeling, training, eval, and inference code for OLMo

open-instruct

ai2thor

An open-source platform for Visual AI.

dolma

Data and tools for generating and inspecting OLMo pre-training data.

objaverse-xl

🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

python-package-template

A template repo for Python packages

reward-bench

RewardBench: the first evaluation tool for reward models.

Holodeck

CVPR 2024: Language Guided Generation of 3D Embodied AI Environments.

allenact

An open source framework for research in Embodied-AI from AI2.

ScienceWorld

ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.

satlas-super-resolution

WildBench

Benchmarking LLMs with Challenging Tasks from Real Users

s2-folks

Public space for the user community of Semantic Scholar APIs to share scripts, report issues, and make suggestions.

SciREX

Data/Code Repository for https://api.semanticscholar.org/CorpusID:218470122

spoc-robot-training

SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World

unified-io-2.pytorch

cached_path

A file utility for accessing both local and remote files through a unified interface.

wildguard

Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

recoma

Reasoning by Communicating with Agents

discoverybench

Discovering Data-driven Hypotheses in the Wild

beaker-gantry

Gantry streamlines running Python experiments in Beaker by managing containers and boilerplate for you

noncompliance

This repository contains data, code and models for contextual noncompliance.

comet-public

A Public repository for the COMeT model

sso

Repository for Skill Set Optimization

safety-eval

A simple evaluation of generative language models and safety classifiers.

beaker-py

A pure-Python Beaker client

objathor

Python package for importing and loading external assets into AI2THOR

inflevel

codenav

CodeNav is an LLM agent that navigates and leverages previously unseen code repositories to solve user queries.

chime

Repository containing dataset, models and code associated with the CHIME project