facebookresearch / dropout
Code release for "Dropout Reduces Underfitting"
☆312Updated last year
Alternatives and similar repositories for dropout:
Users that are interested in dropout are comparing it to the libraries listed below
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆225Updated 5 months ago
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆204Updated last year
- ☆198Updated last year
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆370Updated last year
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆251Updated 2 years ago
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆446Updated 7 months ago
- Probing the representations of Vision Transformers.☆320Updated 2 years ago
- understanding model mistakes with human annotations☆106Updated last year
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆210Updated 2 years ago
- A library to inspect and extract intermediate layers of PyTorch models.☆471Updated 2 years ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆260Updated 9 months ago
- ☆299Updated 7 months ago
- [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"☆309Updated 8 months ago
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆379Updated 8 months ago
- Implementation of Discrete Key / Value Bottleneck, in Pytorch☆87Updated last year
- [NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows …☆127Updated 2 years ago
- Named tensors with first-class dimensions for PyTorch☆321Updated last year
- ☆182Updated last year
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆204Updated last year
- Official implementation of "Active Image Indexing"☆59Updated last year
- A framework for merging models solving different tasks with different initializations into one multi-task model without any additional tr…☆293Updated last year
- Official PyTorch Implementation of "Learning to Learn with Generative Models of Neural Network Checkpoints"☆337Updated 2 years ago
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆405Updated last month
- A concise but complete implementation of CLIP with various experimental improvements from recent papers☆708Updated last year
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆559Updated 2 months ago
- TF/Keras code for DiffStride, a pooling layer with learnable strides.☆124Updated 3 years ago
- Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.☆156Updated 10 months ago
- Masked Siamese Networks for Label-Efficient Learning (https://arxiv.org/abs/2204.07141)☆455Updated 2 years ago
- ☆199Updated 2 years ago
- ☆174Updated 4 months ago