facebookresearch / capi
Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
☆95Updated last week
Alternatives and similar repositories for capi:
Users that are interested in capi are comparing it to the libraries listed below
- WIP☆93Updated 8 months ago
- ☆25Updated last year
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆156Updated last month
- ☆19Updated 6 months ago
- supporting pytorch FSDP for optimizers☆80Updated 4 months ago
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"☆170Updated 10 months ago
- ☆31Updated 3 months ago
- Train VAE like a boss☆274Updated 6 months ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆229Updated last month
- ☆77Updated 9 months ago
- Focused on fast experimentation and simplicity☆71Updated 3 months ago
- ☆50Updated last year
- An implementation of PSGD Kron second-order optimizer for PyTorch☆89Updated 3 weeks ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆123Updated last year
- 🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic…☆73Updated 4 months ago
- ☆65Updated 6 months ago
- Implementation of the proposed Spline-Based Transformer from Disney Research☆88Updated 5 months ago
- FlexTok: Resampling Images into 1D Token Sequences of Flexible Length☆104Updated 2 weeks ago
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆58Updated 2 months ago
- My take on Flow Matching☆50Updated 3 months ago
- This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"☆133Updated 2 months ago
- ☆264Updated 2 months ago
- ☆150Updated 8 months ago
- VIT inference in triton because, why not?☆27Updated 10 months ago
- research impl of Native Sparse Attention (2502.11089)☆53Updated 2 months ago
- When it comes to optimizers, it's always better to be safe than sorry☆217Updated 3 weeks ago
- ☆39Updated 2 weeks ago
- Scaling Vision Pre-Training to 4K Resolution☆124Updated 3 weeks ago
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆127Updated 2 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆105Updated 5 months ago