esceptico / squeezerLinks
Lightweight knowledge distillation pipeline
☆28Updated 4 years ago
Alternatives and similar repositories for squeezer
Users that are interested in squeezer are comparing it to the libraries listed below
Sorting:
- Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012☆49Updated 3 years ago
- Layers, datasets and utilities for PyTorch☆10Updated 2 years ago
- Adam with minor modifications which give significant improvement☆19Updated 4 years ago
- Image data augmentation scheduler for albumentations transforms☆19Updated 4 years ago
- High performance pytorch modules☆18Updated 2 years ago
- PyTorch reimplementation of the paper "HyperMixer: An MLP-based Green AI Alternative to Transformers" [arXiv 2022].☆18Updated 3 years ago
- An open source implementation of CLIP.☆33Updated 3 years ago
- Large dataset storage format for Pytorch☆45Updated 4 years ago
- (unofficial) - customized fork of DETR, optimized for intelligent obj detection on 'real world' custom datasets☆12Updated 5 years ago
- Implementation of Multistream Transformers in Pytorch☆54Updated 4 years ago
- Pytorch based library to rank predicted bounding boxes using text/image user's prompts.☆52Updated 4 years ago
- Re-implementation of local descriptor HardNet training in fasta2+kornia☆21Updated 5 years ago
- graftr: an interactive shell to view and edit PyTorch checkpoints.☆114Updated 5 years ago
- Implementation of Spectral Leakage and Rethinking the Kernel Size in CNNs in Pytorch☆14Updated 4 years ago
- A python library for highly configurable transformers - easing model architecture search and experimentation.☆49Updated 4 years ago
- A deep learning library based on Pytorch focussed on low resource language research and robustness☆70Updated 4 years ago
- ☆55Updated 4 years ago
- Implementation of N-Grammer, augmenting Transformers with latent n-grams, in Pytorch☆76Updated 3 years ago
- Local Attention - Flax module for Jax☆22Updated 4 years ago
- ☆15Updated 3 years ago
- Learning to Initialize Neural Networks for Stable and Efficient Training☆138Updated 3 years ago
- ☆21Updated 6 years ago
- (partial) replication of results from https://arxiv.org/abs/1912.07768☆26Updated 5 years ago
- Re-implementation of 'Grokking: Generalization beyond overfitting on small algorithmic datasets'☆39Updated 4 years ago
- This repository hosts the code to port NumPy model weights of BiT-ResNets to TensorFlow SavedModel format.☆14Updated 4 years ago
- A GPT, made only of MLPs, in Jax☆58Updated 4 years ago
- Implementation of the Remixer Block from the Remixer paper, in Pytorch☆36Updated 4 years ago
- Minimalistic TensorFlow2+ deep metric/similarity learning library with loss functions, miners, and utils as embedding projector.☆38Updated 2 years ago
- Minimal implementation of adaptive gradient clipping (https://arxiv.org/abs/2102.06171) in TensorFlow 2.☆85Updated 4 years ago
- a lightweight transformer library for PyTorch☆72Updated 4 years ago