Owner

allenai

已索引 264 个仓库 · 在 GitHub 查看

• olmocr

  Toolkit for linearizing PDFs for LLM datasets/training

  Python · 19468 个 star

• OLMo

  Modeling, training, eval, and inference code for OLMo

  Python · 6677 个 star

• open-instruct

  AllenAI's post-training codebase

  Python · 3864 个 star

• RL4LMs

  A modular RL library to fine-tune language models to human preferences

  Python · 2395 个 star

• longformer

  Longformer: The Long-Document Transformer

  Python · 2207 个 star

• scispacy

  A full spaCy pipeline and models for scientific/biomedical documents.

  Python · 1990 个 star

• ai2thor

  An open-source platform for Visual AI.

  C# · 1791 个 star

• scibert

  A BERT model for scientific text.

  Python · 1715 个 star

• bilm-tf

  Tensorflow implementation of contextualized word representations from bi-directional language models

  Python · 1609 个 star

• bi-att-flow

  Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granul...

  Python · 1546 个 star

• dolma

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

  Python · 1544 个 star

• OLMo-core

  PyTorch building blocks for the OLMo ecosystem

  Python · 1533 个 star

• objaverse-xl

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

  Python · 1359 个 star

• s2orc

  S2ORC: The Semantic Scholar Open Research Corpus: https://www.aclweb.org/anthology/2020.acl-main.447/

  Python · 1087 个 star

• OLMoE

  OLMoE: Open Mixture-of-Experts Language Models

  Jupyter Notebook · 1079 个 star

• natural-instructions

  Expanding natural instructions

  Python · 1048 个 star

• mmc4

  MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

  Python · 954 个 star

• molmo

  Code for the Molmo Vision-Language Model

  Python · 933 个 star

• XNOR-Net

  ImageNet classification using binary Convolutional Neural Networks

  Lua · 872 个 star

• papermage

  library supporting NLP and CV research on scientific papers

  Python · 803 个 star

• 还有 244 个仓库在 在 GitHub 查看