metadata
license: apache-2.0
datasets:
- EleutherAI/the_pile
language:
- en
This is a tokenizer for the Parva models, based off of the GPT-Neox tokenizers
license: apache-2.0
datasets:
- EleutherAI/the_pile
language:
- en
This is a tokenizer for the Parva models, based off of the GPT-Neox tokenizers