rasbt / b3-basic-batchsize-benchmark
Experiments for the blog post "No, We Don't Have to Choose Batch Sizes As Powers Of 2"
☆19Updated 2 years ago
Alternatives and similar repositories for b3-basic-batchsize-benchmark:
Users that are interested in b3-basic-batchsize-benchmark are comparing it to the libraries listed below
- ☆15Updated 3 years ago
- Unofficially Implements https://arxiv.org/abs/2112.05682 to get Linear Memory Cost on Attention for PyTorch☆12Updated 3 years ago
- bumble bee transformer☆14Updated 3 years ago
- PyTorch implementation of GLOM☆21Updated 2 years ago
- Visual Clustering: Clustering Plotted Data by Image Segmentation☆24Updated 3 weeks ago
- Simplifying parsing of large jsonline files in NLP Workflows☆12Updated 3 years ago
- ☆15Updated 2 years ago
- Bi-Directional Attention Flow for Machine Comprehensions☆9Updated 7 years ago
- Colab notebooks for d2l-book☆11Updated 5 years ago
- ☆31Updated last month
- Implements EvoNorms B0 and S0 as proposed in Evolving Normalization-Activation Layers.☆11Updated 4 years ago
- Implementation of N-Grammer in Flax☆17Updated 2 years ago
- Prabhupadavani: A Code-mixed Speech Translation Data for 25 languages☆13Updated 2 years ago
- Local Attention - Flax module for Jax☆20Updated 3 years ago
- A collection of Models, Datasets, DataModules, Callbacks, Metrics, Losses and Loggers to better integrate pytorch-lightning with transfor…☆47Updated last year
- The collection of bulding blocks building fine-tunable metric learning models☆32Updated 2 months ago
- A dashboard for exploring timm learning rate schedulers☆19Updated 4 months ago
- PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"☆23Updated last week
- Describe the format of image/text datasets☆11Updated 2 years ago
- codes for TokenManipulationGAN☆7Updated 4 years ago
- ☆11Updated 3 months ago
- reproduces experiments from "Grounding inductive biases in natural images: invariance stems from variations in data"☆17Updated 5 months ago
- ☆11Updated 2 years ago
- SMASHED is a toolkit designed to apply transformations to samples in datasets, such as fields extraction, tokenization, prompting, batchi…☆32Updated 10 months ago
- ☆24Updated 3 years ago
- Experiments and tutorials with and for torchaudio☆13Updated 3 years ago
- Official Code for MIMETIC^2☆12Updated 4 months ago
- Directed masked autoencoders☆14Updated 2 years ago
- Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012☆49Updated 2 years ago
- A generative modelling toolkit for PyTorch.☆70Updated 3 years ago