A batched offline inference oriented version of segment-anything
APACHE-2.0 License
Ongoing research training transformer language models at scale, including: BERT & GPT-2
Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds
End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 ...
Seamless analysis of your PyTorch models (RAM usage, FLOPs, MACs, receptive field, etc.)
Train fastai models faster (and other useful tools)
Home of StarCoder: fine-tuning & inference!
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed conf...
Implementation of Open-Set Likelihood Maximization for Few-Shot Learning
Official PyTorch implementation of SegFormer
The simplest, fastest repository for training/finetuning medium-sized GPTs.
[ICCV 2023] Tracking Anything with Decoupled Video Segmentation
Segment Anything in High Quality [NeurIPS 2023]
Home of StarCoder2!
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, bas...
Export Segment Anything Models to ONNX