Files
simple-100m-instruct-v1/tokenizer_config.json

15 lines
377 B
JSON
Raw Permalink Normal View History

{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"is_local": false,
"model_max_length": 1024,
"model_specific_special_tokens": {},
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}