John's repositories
InformalToFormalDataset
Informal to formal dataset mask MLM
ChatGPT-Prompts
ChatGPT prompt curation to use ChatGPT better.
detecting-fake-text
Giant Language Model Test Room, outdated
election-vis
An interactive, draggable d3.js visualization showing turnout and party margins for the 2004-2020 elections.
gpt2-business
GPT API for service
gpt2-cover-letter
generate cover-letter sentence based fine-tuned gpt2 model
gpt2_debate
This GPT2-debate model generates debate writing text. When you enter text for the beginning of the script, the model gives you the rest of the script as long as you want.
gpt2_story
This GPT2-story model generates genre story text. When you enter text at the beginning of the story, the model gives you the rest of the story as long as you want.
Homework-helper
Automatically search for quizlet answer on highlighted text.
NLP-Dashboard
A language model example using GPT2 (sentence completion) and BERT (fill in the blanks)
TabTab-Mini
TabTab tutorial
ToTTo
ToTTo is an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a one-sentence description. We hope it can serve as a useful research benchmark for high-precision conditional text generation.
transformers
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.