-
Inflection.ai
Highlights
- Pro
Stars
A Python 3 compatible version of goose https://goose3.readthedocs.io/en/latest/index.html
Minimal library to train LLMs on TPU in JAX with pjit().
A high performance and generic framework for distributed DNN training
PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".
Wide and Deep Learning(Wide&ResDNN) for Kaggle Criteo Dataset in tensorflow
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
Bitextor generates translation memories from multilingual websites
Gemini is a modern LaTex beamerposter theme 🖼
Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
shFlags is a port of the Google gflags library for Unix shell.
Joint Source-Target Self Attention with Locality Constraints
Meta-Learning with Differentiable Convex Optimization (CVPR 2019 Oral)
Virtual Adversarial Training (VAT) implementation for PyTorch
source code to ICLR'19, 'A Closer Look at Few-shot Classification'
Implementation of Prototypical Networks for Few Shot Learning (https://arxiv.org/abs/1703.05175) in Pytorch
Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"
A dataset of datasets for learning to learn from few examples
PyTorch implementation of MAML: https://arxiv.org/abs/1703.03400
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
TensorFlow code and pre-trained models for BERT
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Data manipulation and transformation for audio signal processing, powered by PyTorch
Differentiable architecture search for convolutional and recurrent networks