Ai2

All

480 repositories

dolma
Public
Data and tools for generating and inspecting OLMo pre-training data.
nlp data-processing machile-learning large-language-models llm
Python
•
Apache License 2.0
•108•980•23•9•Updated Nov 9, 2024Nov 9, 2024
OLMo
Public
Modeling, training, eval, and inference code for OLMo
Python
•
Apache License 2.0
•470•4.6k•49•50•Updated Nov 9, 2024Nov 9, 2024
regmixer
Public
Python
•0•0•0•2•Updated Nov 8, 2024Nov 8, 2024
OLMo-core
Public
PyTorch building blocks for OLMo
Python
•
Apache License 2.0
•4•18•0•7•Updated Nov 8, 2024Nov 8, 2024
open-instruct
Public
Python
•
Apache License 2.0
•172•1.3k•10•26•Updated Nov 8, 2024Nov 8, 2024
s2-folks
Public
Public space for the user community of Semantic Scholar APIs to share scripts, report issues, and make suggestions.
Other
•29•178•6•1•Updated Nov 8, 2024Nov 8, 2024
ir_datasets
Public
Provides a common interface to many IR ranking datasets.
information-retrieval ir dataset
Python
•
Apache License 2.0
•42•320•73•9•Updated Nov 8, 2024Nov 8, 2024
rslearn
Public
A tool for developing remote sensing datasets and models.
Python
•
Apache License 2.0
•0•10•11•6•Updated Nov 8, 2024Nov 8, 2024
papermage
Public
library supporting NLP and CV research on scientific papers
python machine-learning natural-language-processing computer-vision scientific-papers multimodal pdf-processing
Python
•
Apache License 2.0
•54•699•27•3•Updated Nov 8, 2024Nov 8, 2024
ai2thor
Public
An open-source platform for Visual AI.
computer-vision physics-engine artificial-intelligence interaction visual-ai
C#
•
Apache License 2.0
•217•1.2k•236•3•Updated Nov 6, 2024Nov 6, 2024
PoliFormer
Public
PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators
rl embodied-ai objectnav corl-2024
Python
•
Other
•0•7•1•0•Updated Nov 6, 2024Nov 6, 2024
oe-eval
Public
Reproducible, flexible LLM evaluations
Python
•
Apache License 2.0
•0•1•0•0•Updated Nov 5, 2024Nov 5, 2024
OLMoE
Public
OLMoE: Open Mixture-of-Experts Language Models
Jupyter Notebook
•
Apache License 2.0
•35•436•5•0•Updated Nov 4, 2024Nov 4, 2024
spoc-robot-training
Public
SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World
Python
•
Other
•7•91•4•5•Updated Nov 4, 2024Nov 4, 2024
SciRIFF
Public
Dataset and evaluation suite enabling LLM instruction-following for scientific literature understanding.
Python
•
Apache License 2.0
•3•26•1•0•Updated Nov 3, 2024Nov 3, 2024
WildBench
Public
Benchmarking LLMs with Challenging Tasks from Real Users
Python
•
Apache License 2.0
•36•194•1•0•Updated Nov 3, 2024Nov 3, 2024
hybrid-preferences
Public
Learning to route instances for Human vs AI Feedback
language-model dpo rlhf reward-modeling
Python
•0•12•0•1•Updated Nov 2, 2024Nov 2, 2024
beaker-py
Public
A pure-Python Beaker client
api-client beaker python
Python
•
Apache License 2.0
•2•12•1•5•Updated Nov 1, 2024Nov 1, 2024
beaker-gantry
Public
Gantry streamlines running Python experiments in Beaker by managing containers and boilerplate for you
python docker cli containers beaker
Python
•
Apache License 2.0
•3•19•1•2•Updated Nov 1, 2024Nov 1, 2024
OLMo-Eval
Public
Evaluation suite for LLMs
Python
•
Apache License 2.0
•38•309•3•10•Updated Oct 30, 2024Oct 30, 2024
OLMo-in-loop-evals
Public
Code for in-loop evaluation tasks used by the OLMo training team
Python
•
Apache License 2.0
•0•0•0•0•Updated Oct 29, 2024Oct 29, 2024
scispacy
Public
A full spaCy pipeline and models for scientific/biomedical documents.
nlp bioinformatics biomedical spacy custom-pipes scientific-documents
Python
•
Apache License 2.0
•229•1.7k•28•2•Updated Oct 28, 2024Oct 28, 2024
llm-research-survey
Public
Python
•
Apache License 2.0
•0•1•0•13•Updated Oct 26, 2024Oct 26, 2024
discoverybench
Public
Discovering Data-driven Hypotheses in the Wild
Python
•7•39•0•0•Updated Oct 25, 2024Oct 25, 2024
wildguard
Public
Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Python
•
Other
•5•37•1•0•Updated Oct 25, 2024Oct 25, 2024
maldives_ecosystem_mapping
Public
Apache License 2.0
•0•2•0•0•Updated Oct 24, 2024Oct 24, 2024
satlaspretrain_models
Public
Jupyter Notebook
•
Apache License 2.0
•12•75•2•1•Updated Oct 24, 2024Oct 24, 2024
reward-bench
Public
RewardBench: the first evaluation tool for reward models.
preference-learning rlhf
Python
•
Apache License 2.0
•50•426•6•3•Updated Oct 23, 2024Oct 23, 2024
peS2o
Public
Pretraining Efficiently on S2ORC!
Python
•
Apache License 2.0
•4•136•3•0•Updated Oct 23, 2024Oct 23, 2024
tinyhost
Public
serverless-less way to host a single page website with datastore for sharing with coworkers
Python
•
Apache License 2.0
•1•1•0•13•Updated Oct 23, 2024Oct 23, 2024