gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.

Democratizing Reinforcement Learning for LLMs

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

Implementation of CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation

Official Repo for Open-Reasoner-Zero

OLMoE: Open Mixture-of-Experts Language Models

Official Implementation for paper: Negative Token Merging: Image-based Adversarial Feature Guidance

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

Generate textbook-quality synthetic LLM pretraining data

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks (ICML 2024)

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

This repository provides an original implementation of Detecting Pretraining Data from Large Language Models by *Weijia Shi, *Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu , Terra Blevins…

EcoAssistant: using LLM assistant more affordably and accurately

SILO Language Models code repository

Code used for the creation of OBELICS, an open, massive and curated collection of interleaved image-text web documents, containing 141M documents, 115B text tokens and 353M images.

Failure archive for ChatGPT and similar models

Resources for Retrieval Augmentation for Commonsense Reasoning: A Unified Approach. EMNLP 2022.

Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Retrieval augmented diffusion from CompVis.

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

Code and models for the paper "Questions Are All You Need to Train a Dense Passage Retriever (TACL 2023)"

Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

PyTorch + HuggingFace code for RetoMaton: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022), including an implementation of kNN-LM and kNN-MT

Parallel data preprocessing for NLP and ML.

[EMNLP 2022] Training Language Models with Memory Augmentation https://arxiv.org/abs/2205.12674