stas-gpt-new / tokenizer_config.json
TOOTHED's picture
Upload tokenizer
d7c15c9 verified
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"model_max_length": 2048,
"pad_token": "<pad>",
"padding_side": "left",
"tokenizer_class": "GPT2Tokenizer",
"truncation_side": "left",
"trust_remote_code": false,
"unk_token": "<unk>"
}