ranpox

metaseq

Repo for external large-scale work

BLIP

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

OpenAgents

[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild

torchscale

Foundation Architecture for (M)LLMs

awesome-phd-advice

Collection of advice for prospective and current PhD students

OSWorld

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

OpenDelta

A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

bigscience

Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.

natural-instructions

Expanding natural instructions

evojax

how-do-vits-work

(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"

aclpubcheck

Tools for checking ACL paper submissions

Lemur

[ICLR 2024] Lemur: Open Foundation Models for Language Agents

gpt_paper_assistant

GPT4 based personalized ArXiv paper assistant bot

magma

MAGMA - a GPT-style multimodal model that can understand any combination of images and language. NOTE: The freely available model from this repo is only a demo. For the latest multimodal and multilingual models from Aleph Alpha check out our website https://app.aleph-alpha.com

CLIP-ViL

[ICLR 2022] code for "How Much Can CLIP Benefit Vision-and-Language Tasks?" https://arxiv.org/abs/2107.06383

METER

METER: A Multimodal End-to-end TransformER Framework

xlang-paper-reading

Paper collection on building and evaluating language model agents via executable language grounding

SEAL

Search Engines with Autoregressive Language models

MetaICL

An original implementation of "MetaICL Learning to Learn In Context" by Sewon Min, Mike Lewis, Luke Zettlemoyer and Hannaneh Hajishirzi

RetrivalLMPapers

Paper collections of retrieval-based (augmented) language model.

EditEval

An instruction-based benchmark for text improvements.

DallEval

DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models (ICCV 2023)

iclr2024-openreview-submissions

ICLR 2024 OpenReivew Submission Data

WorldModelPapers

Paper collections of the continuous effort start from World Models.

icl-selective-annotation

[ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"

ZeroGen

[EMNLP 2022] Code for our paper “ZeroGen: Efficient Zero-shot Learning via Dataset Generation”.

Sparkles

Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models

GPT-4V-API

Self-hosted GPT-4V api

multilingual-conala

[EACL'23] MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages