Pinned Repositories
coach
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
curl
CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
distiller
Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
gym
A toolkit for developing and comparing reinforcement learning algorithms.
haq-release
[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision
Megatron-LM
Ongoing research training transformer models at scale
NeMo
NeMo: a toolkit for conversational AI
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
tensorflow
An Open Source Machine Learning Framework for Everyone
guyjacob's Repositories
guyjacob/coach
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
guyjacob/curl
CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
guyjacob/distiller
Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
guyjacob/gym
A toolkit for developing and comparing reinforcement learning algorithms.
guyjacob/haq-release
[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision
guyjacob/Megatron-LM
Ongoing research training transformer models at scale
guyjacob/NeMo
NeMo: a toolkit for conversational AI
guyjacob/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
guyjacob/ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
guyjacob/tensorflow
An Open Source Machine Learning Framework for Everyone
guyjacob/vision
Datasets, Transforms and Models specific to Computer Vision