facebookresearch / SIMAT
codebase for the SIMAT dataset and evaluation
☆39Updated 3 years ago
Alternatives and similar repositories for SIMAT:
Users that are interested in SIMAT are comparing it to the libraries listed below
- Un-*** 50 billions multimodality dataset☆24Updated 2 years ago
- PyTorch code for "Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention" (WACV 2023)☆33Updated 2 years ago
- Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012☆49Updated 3 years ago
- Command-line tool for downloading and extending the RedCaps dataset.☆46Updated last year
- Repository for the paper "Data Efficient Masked Language Modeling for Vision and Language".☆18Updated 3 years ago
- ☆34Updated last year
- ☆32Updated 3 years ago
- An open source implementation of CLIP.☆32Updated 2 years ago
- ☆50Updated 2 years ago
- ☆46Updated 11 months ago
- Script and models for clustering LAION-400m CLIP embeddings.☆26Updated 3 years ago
- The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns …☆16Updated last year
- ImageNet-12k subset of ImageNet-21k (fall11)☆21Updated last year
- Official code for the paper: "Metadata Archaeology"☆19Updated last year
- ☆64Updated last year
- ☆29Updated 2 years ago
- Code for T-MARS data filtering☆35Updated last year
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆48Updated 3 years ago
- [ECCV2024][ICCV2023] Official PyTorch implementation of SeiT++ and SeiT☆55Updated 8 months ago
- ☆26Updated 3 years ago
- A python library for highly configurable transformers - easing model architecture search and experimentation.☆49Updated 3 years ago
- ☆13Updated 3 years ago
- Large-Scale Bidirectional Training for Zero-Shot Image Captioning☆21Updated 2 years ago
- JAX implementation ViT-VQGAN☆82Updated 2 years ago
- Simple script to compute CLIP-based scores given a DALL-e trained model.☆30Updated 3 years ago
- ☆47Updated 4 years ago
- Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch☆89Updated 3 years ago
- Implementation of "compositional attention" from MILA, a multi-head attention variant that is reframed as a two-step attention process wi…☆50Updated 2 years ago
- ☆29Updated 2 years ago
- Patching open-vocabulary models by interpolating weights☆91Updated last year