facebookresearch / multimodalLinks
TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.
β1,643Updated last week
Alternatives and similar repositories for multimodal
Users that are interested in multimodal are comparing it to the libraries listed below
Sorting:
- Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorchβ1,165Updated last year
- Implementation of 𦩠Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorchβ1,256Updated 2 years ago
- Robust fine-tuning of zero-shot modelsβ728Updated 3 years ago
- Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.β3,078Updated 3 months ago
- Code for ALBEF: a new vision-language pre-training methodβ1,693Updated 2 years ago
- CLIP-like model evaluationβ756Updated last week
- Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"β1,488Updated last year
- Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Lβ¦β2,520Updated last year
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language modelsβ792Updated last year
- Meta-Transformer for Unified Multimodal Learningβ1,622Updated last year
- A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toβ¦β1,050Updated 10 months ago
- [ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decodeβ¦β862Updated 2 years ago
- Awesome list for research on CLIP (Contrastive Language-Image Pre-Training).β1,209Updated last year
- A method to increase the speed and lower the memory footprint of existing vision transformers.β1,083Updated last year
- A PyTorch Lightning solution to training OpenAI's CLIP from scratch.β707Updated 3 years ago
- ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Expertβ¦β1,646Updated last week
- β663Updated 2 weeks ago
- A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''β1,324Updated last year
- EVA Series: Visual Representation Fantasies from BAAIβ2,553Updated last year
- A concise but complete implementation of CLIP with various experimental improvements from recent papersβ712Updated last year
- Grounded Language-Image Pre-trainingβ2,480Updated last year
- A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.β2,766Updated 2 months ago
- iBOT : Image BERT Pre-Training with Online Tokenizer (ICLR 2022)β743Updated 3 years ago
- Hiera: A fast, powerful, and simple hierarchical vision transformer.β1,012Updated last year
- Foundation Architecture for (M)LLMsβ3,099Updated last year
- Simple implementation of OpenAI CLIP model in PyTorch.β700Updated last year
- Code release for SLIP Self-supervision meets Language-Image Pre-trainingβ778Updated 2 years ago
- Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)β921Updated last year
- PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057β1,283Updated 3 years ago
- DataComp: In search of the next generation of multimodal datasetsβ734Updated 3 months ago