CodeGen-Indo-350M / tokenizer_config.json
zaenalium's picture
Training in progress, step 2000
b007eb7 verified
raw
history blame contribute delete
537 Bytes
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}