gpt2_cx-en_00000-00009_50k / tokenizer_config.json
jonasknobloch's picture
Initial commit
6c17a3a
raw
history blame contribute delete
356 Bytes
{
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "PreTrainedTokenizerFast"
}