tiny-edu-166m / tokenizer_config.json
SlitherCode's picture
TiktokenTokenizer: upload tokenizer_config.json
99b5878 verified
raw
history blame contribute delete
632 Bytes
{
"added_tokens_decoder": {
"100257": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"backend": "custom",
"bos_token": "<|endoftext|>",
"encoding_name": "cl100k_base",
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|endoftext|>",
"tokenizer_class": "TiktokenTokenizer",
"unk_token": "<|endoftext|>",
"auto_map": {
"AutoTokenizer": [
null,
"tokenization_parchment.TiktokenTokenizer"
]
}
}