NathanHundley

llama

Inference code for LLaMA models

18335

18.335 - Introduction to Numerical Methods course

18S191

Course 18.S191 at MIT, Spring 2021 - Introduction to computational thinking with Julia:

bayesian_inference_pymc3

Jupyter Python notebook from conference talk on Bayesian inference with PyMC3.

blog

Public repo for HF blog posts

causal_ml_seminar

datasets

🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools

Deepfake-using-Wave2Lip

A deep learning model to lip-sync a given video with any given audio. It uses GAN architecture to orchestrate loss reconstruction or training.

finetune-gpt2xl

Guide: Finetune GPT2-XL (1.5 Billion Parameters) and GPT-NEO (2.7 B) on a GPU with Huggingface Transformers using DeepSpeed

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

gpt-neox

An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.

gym

A toolkit for developing and comparing reinforcement learning algorithms.

missing-data-workshop

Matt Brems' Missing Data Workshop

ml-workshop-advanced

Network-Analysis-in-Python---Tutorial-ODSCWest20

Slides and code repository for 90 minutes training session held at ODSC West 2020.

node-question-answering

Fast and production-ready question answering in Node.js

notebooks

Notebooks using the Hugging Face libraries 🤗

ODSC

tutorial for converting PyTorch to Lightning

ODSC-East-2021

ODSC-East-AB-Testing-Python-2021

This repo contains the data, code, and slides needed for this workshop

ODSC_text_analysis

Materials for Exploratory Text Analysis with spaCy and textacy

odsceast2021

Code for Modern Machine Learning in R

Onnx_Runtime_Mobile_ODSC_Tutorial

Tutorial for ODSC East 2021, "ML Inference on Mobile Device With Onnx Runtime"

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

open-data-registry

A registry of publicly available datasets on AWS

pytorch-lightning

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

retro

Retro Games in Gym

tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Transformers-Tutorial

Advances in Conversational AI and NLP through Large Scale Language Models such as GPT-3

webdataset