Pinned Repositories
ai2thor
An open-source platform for Visual AI.
allennlp
An open-source NLP research library, built on PyTorch.
bi-att-flow
Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization.
bilm-tf
Tensorflow implementation of contextualized word representations from bi-directional language models
dolma
Data and tools for generating and inspecting OLMo pre-training data.
longformer
Longformer: The Long-Document Transformer
OLMo
Modeling, training, eval, and inference code for OLMo
RL4LMs
A modular RL library to fine-tune language models to human preferences
scibert
A BERT model for scientific text.
scispacy
A full spaCy pipeline and models for scientific/biomedical documents.
AI2's Repositories
allenai/OLMo
Modeling, training, eval, and inference code for OLMo
allenai/ai2thor
An open-source platform for Visual AI.
allenai/open-instruct
allenai/dolma
Data and tools for generating and inspecting OLMo pre-training data.
allenai/visprog
Official code for VisProg (CVPR 2023 Best Paper!)
allenai/science-parse
Science Parse parses scientific papers (in PDF form) and returns them in structured form.
allenai/tango
Organize your experiments into discrete steps that can be cached and reused throughout the lifetime of your research project.
allenai/ir_datasets
Provides a common interface to many IR ranking datasets.
allenai/Holodeck
CVPR 2024: Language Guided Generation of 3D Embodied AI Environments.
allenai/OLMo-Eval
Evaluation suite for LLMs
allenai/fm-cheatsheet
Website for hosting the Open Foundation Models Cheat Sheet.
allenai/reward-bench
RewardBench: the first evaluation tool for reward models.
allenai/ScienceWorld
ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.
allenai/satlas-super-resolution
allenai/mmda
multimodal document analysis
allenai/s2-folks
Public space for the user community of Semantic Scholar APIs to share scripts, report issues, and make suggestions.
allenai/catwalk
This project studies the performance and robustness of language models and task-adaptation methods.
allenai/WildBench
Benchmarking LLMs with Challenging Tasks from Real Users
allenai/SPECTER2
allenai/scirepeval
SciRepEval benchmark training and evaluation scripts
allenai/smashed
SMASHED is a toolkit designed to apply transformations to samples in datasets, such as fields extraction, tokenization, prompting, batching, and more. Supports datasets from Huggingface, torchdata iterables, or simple lists of dictionaries.
allenai/cached_path
A file utility for accessing both local and remote files through a unified interface.
allenai/spoc-robot-training
SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World
allenai/recoma
Reasoning by Communicating with Agents
allenai/beaker-gantry
Gantry streamlines running Python experiments in Beaker by managing containers and boilerplate for you
allenai/vessel-detection-viirs
Model and service code for streaming vessel detections from VIIRS satellite imagery
allenai/sso
Repository for Skill Set Optimization
allenai/beaker-py
A pure-Python Beaker client
allenai/OLMo-core
PyTorch building blocks for OLMo
allenai/discoverybench
Discovering Data-driven Hypotheses in the Wild