GitLab

For many applications requiring randomized data access, it's easier to cache the tokenized representations than the words. So why not turn this into a warning?

update documentation for gpt-2

Few small nits in GPT-2's README code examples

Update README.md

Update run_openai_gpt.py

typo

fix broken link in readme

Minor README typos corrected

Fix typo in `GPT2Model` code sample

Typo prevented code from running

forgot to add regex to requirements.txt :(

Gpt2