top | item 34008605 (no title) bryanh | 3 years ago https://twitter.com/sherwinwu/status/1603522777968832512 appears to include it. discuss order hn newest minimaxir|3 years ago So it does.The code there implies cl100k_base has a vocab size of 100k (I guess it's in the name lol) which means it is more comprehensive than GPT-2's 50k, so fewer tokens will be necessary.
minimaxir|3 years ago So it does.The code there implies cl100k_base has a vocab size of 100k (I guess it's in the name lol) which means it is more comprehensive than GPT-2's 50k, so fewer tokens will be necessary.
minimaxir|3 years ago
The code there implies cl100k_base has a vocab size of 100k (I guess it's in the name lol) which means it is more comprehensive than GPT-2's 50k, so fewer tokens will be necessary.