affjljoo3581 / deit3-jaxLinks
Jax/Flax implementation of DeiT and DeiT-III (ViT)
โ19Updated last year
Alternatives and similar repositories for deit3-jax
Users that are interested in deit3-jax are comparing it to the libraries listed below
Sorting:
- ๐ฅ12th place solution on G2Net Detecting Continuous Gravitational Waves๐ฅโ14Updated 3 years ago
- ๐งชcategorical tabnet research part๐งชโ13Updated last year
- ์ปค๋ฒ๋ฆฌ์คํธ - ๋ถ ์ปค๋ฒ ์์ฑ AI ์๋น์คโ12Updated 3 years ago
- ๊ด์ด๋ํ๊ต ์ปดํจํฐ ๋น์ AI ๊ฒฝ์ง๋ํ 1๋ฑ ์๋ฃจ์ ์ ๋๋ค.โ15Updated 3 years ago
- TPU์์ ํ๊ตญ์ด์ฉ LLM ์ถ๋ก ์ ์ํ Jax/Flax ๊ตฌํ์ฒด์ ๋๋ค.โ12Updated 2 years ago
- ๐๏ธ 5th place solution in the Google American Sign Language Fingerspelling Recognition Competition๐๏ธโ16Updated 2 years ago
- Reproduction of Vision Transformer in Tensorflow2. Train from scratch and Finetune.โ48Updated 4 years ago
- Optimize RandAugment with differentiable operationsโ25Updated 5 years ago
- KAIST AI605 Deep Learning for NLPโ31Updated 3 years ago
- โ126Updated 3 years ago
- Learning Features with Parameter-Free Layers, ICLR 2022โ84Updated 2 years ago
- The official repository for <Autoencoding Under Normalization Constraints> (Yoon, Noh and Park, ICML 2021).โ44Updated 2 years ago
- read 1 paper everyday (only weekday)โ55Updated 4 years ago
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adamโ85Updated last year
- My collection of machine learning papersโ296Updated 2 years ago
- ๐ฅ LG-AI-Challenge 2022 1์ ์๋ฃจ์ ์ ๋๋ค.โ13Updated 2 years ago
- This project attempts to build neural network training and lightweighting cookbook including three kinds of lightweighting solutions, i.eโฆโ22Updated 3 years ago
- a Jax/Flax inference code of StarCoderโ12Updated 2 years ago
- Official repository for Automated Learning Rate Scheduler for Large-Batch Training (8th ICML Workshop on AutoML)โ40Updated 4 years ago
- Getting GPU Util 99%โ33Updated 5 years ago
- A hackable, simple, and reseach-friendly GRPO Training Framework with high speed weight synchronization in a multinode environment.โ36Updated 5 months ago
- Codes for "Learning bounds for risk-sensitive learning," NeurIPS 2020 (or see arXiv 2006.08138)โ11Updated 5 years ago
- ๐๋ฐ์ด์ฝ AIํด์ปคํค ๋ํ ์ฐ์์ ์๋ฃจ์ ๐โ22Updated last year
- Model Stock: All we need is just a few fine-tuned modelsโ128Updated 5 months ago
- (ICML 2022) Official PyTorch implementation of โBlurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robโฆโ79Updated 3 years ago
- Google's Conceptual Captions Dataset translated into Koreanโ23Updated 3 years ago
- [ICLR 2023] RC-MAEโ53Updated 2 years ago
- A PyTorch Implementation of the Luna: Linear Unified Nested Attentionโ41Updated 4 years ago
- Serving large language model with transformersโ13Updated 3 years ago
- Paper Today I Readโ27Updated this week