gLM2_650M_embed / tokenizer_config.json
andrecornman's picture
Upload tokenizer
d850aa6 verified
raw
history blame
1.75 kB
{
"added_tokens_decoder": {
"0": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"33": {
"content": "<+>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"34": {
"content": "<->",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"35": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"36": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"auto_map": {
"AutoTokenizer": [
"glm_tokenizer.gLM2Tokenizer",
null
]
},
"clean_up_tokenization_spaces": true,
"cls_token": "<cls>",
"eos_token": "<eos>",
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sep_token": "<sep>",
"tokenizer_class": "gLM2Tokenizer",
"unk_token": "<unk>"
}