google-research-datasets / wit

Related projects: ⓘ

• FreddeFrallan / Multilingual-CLIP
  OpenAI CLIP text encoders for multiple languages!
  ☆746Updated last year
• lucidrains / flamingo-pytorch
  Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch
  ☆1,193Updated last year
• facebookresearch / SLIP
  Code release for SLIP Self-supervision meets Language-Image Pre-training
  ☆743Updated last year
• LAION-AI / CLIP_benchmark
  CLIP-like model evaluation
  ☆584Updated last month
• microsoft / Oscar
  Oscar and VinVL
  ☆1,037Updated last year
• criteo / autofaiss
  Automatically create Faiss knn indices with the most optimal similarity search parameters.
  ☆802Updated 4 months ago
• lucidrains / CoCa-pytorch
  Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch
  ☆1,037Updated 9 months ago
• google-research-datasets / conceptual-12m
  Conceptual 12M is a dataset containing (image-URL, caption) pairs collected for vision-and-language pre-training.
  ☆357Updated last year
• lucidrains / RETRO-pytorch
  Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
  ☆850Updated 10 months ago
• lucidrains / x-clip
  A concise but complete implementation of CLIP with various experimental improvements from recent papers
  ☆678Updated 11 months ago
• Zasder3 / train-CLIP
  A PyTorch Lightning solution to training OpenAI's CLIP from scratch.
  ☆654Updated 2 years ago
• allenai / mmc4
  MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.
  ☆894Updated 3 months ago
• mlfoundations / datacomp
  DataComp: In search of the next generation of multimodal datasets
  ☆637Updated 8 months ago
• kohjingyu / fromage
  🧀 Code and models for the ICML 2023 paper "Grounding Language Models to Images for Multimodal Inputs and Outputs".
  ☆473Updated 10 months ago
• Lightning-Universe / lightning-transformers
  Flexible components pairing 🤗 Transformers with Pytorch Lightning
  ☆610Updated last year
• xplip / pixel
  Research code for pixel-based encoders of language (PIXEL)
  ☆329Updated 6 months ago
• mlfoundations / wise-ft
  Robust fine-tuning of zero-shot models
  ☆629Updated 2 years ago
• OFA-Sys / OFA
  Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence L…
  ☆2,394Updated 4 months ago
• facebookresearch / vilbert-multi-task
  Multi Task Vision and Language
  ☆799Updated 2 years ago
• microsoft / DeBERTa
  The implementation of DeBERTa
  ☆1,966Updated 11 months ago
• google-research / byt5
  ☆480Updated 7 months ago
• google-research / pix2seq
  Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)
  ☆858Updated 10 months ago
• facebookresearch / multimodal
  TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.
  ☆1,423Updated this week
• google-research-datasets / conceptual-captions
  Conceptual Captions is a dataset containing (image-URL, caption) pairs designed for the training and evaluation of machine learned image …
  ☆513Updated 3 years ago
• rom1504 / img2dataset
  Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
  ☆3,602Updated last month
• kakaobrain / coyo-dataset
  COYO-700M: Large-scale Image-Text Pair Dataset
  ☆1,143Updated last year
• yxuansu / MAGIC
  Language Models Can See: Plugging Visual Controls in Text Generation
  ☆251Updated 2 years ago
• rom1504 / clip-retrieval
  Easily compute clip embeddings and build a clip retrieval system with them
  ☆2,355Updated 5 months ago
• ashkamath / mdetr
  ☆963Updated last year
• google / seqio
  Task-based datasets, preprocessing, and evaluation for sequence models.
  ☆552Updated this week