Pinned Repositories
gpt-neo
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
lm-evaluation-harness
A framework for few-shot evaluation of language models.
pyfra
Python Research Framework
the-pile
commoncrawl_downloader
gpt2-hf-to-tf1
Convert TF 2.x/Pytorch GPT2 model to original OpenAI TF 1.x GPT2 format
htmltotext-benchmark
LLMD-CommonCrawl
lm_dataformat
toy-alignment-notebooks
The goal of this project is to collect beginner friendly notebooks for demonstrating alignment concepts in toy environments and make them feel more tangible.
leogao2's Repositories
leogao2/lm_dataformat
leogao2/commoncrawl_downloader
leogao2/toy-alignment-notebooks
The goal of this project is to collect beginner friendly notebooks for demonstrating alignment concepts in toy environments and make them feel more tangible.
leogao2/gpt2-hf-to-tf1
Convert TF 2.x/Pytorch GPT2 model to original OpenAI TF 1.x GPT2 format
leogao2/LLMD-CommonCrawl
leogao2/apps
APPS: Automated Programming Progress Standard (NeurIPS 2021)
leogao2/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
leogao2/akronomicon
Public rankings of extreme-scale models
leogao2/alignment-research-dataset
A dataset of alignment research and code to reproduce it
leogao2/BIG-bench
Beyond the Imitation Game collaborative benchmark for enormous language models
leogao2/cdict
leogao2/CLIP
Contrastive Language-Image Pretraining
leogao2/dask
Parallel computing with task scheduling
leogao2/ergo
A Python library for integrating model-based and judgmental forecasting
leogao2/gpt-neo
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
leogao2/GPT-Neo-visual-grounding
Visually ground GPT-Neo 1.3b and 2.7b
leogao2/idemlib
leogao2/learn2gradienthack
Uses learn2learn to train a fully connected network that implements the constant function and resists SGD
leogao2/leogao2-site
leogao2/link-randomizer
leogao2/lm-evaluation-harness
leogao2/mesh-transformer-jax
Model parallel transformers in JAX and Haiku
leogao2/publish_perish
Academia sim
leogao2/pythonic-rabbitmq
leogao2/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.
leogao2/research_helper
leogao2/scaling-experiments
Experiments related to scaling laws for language models.
leogao2/tensor2tensor
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
leogao2/The-Pile-FreeLaw
Download, parse, and filter data from Court Listener, part of the FreeLaw projects. Data-ready for The-Pile.
leogao2/transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.