calculator_model_test / tokenizer.json
SirSleepalot's picture
Training in progress, step 500
5fc5c05 verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[EOS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[EOS]",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"[EOS]": {
"id": "[EOS]",
"ids": [
0
],
"tokens": [
"[EOS]"
]
}
}
},
"decoder": null,
"model": {
"type": "BPE",
"dropout": null,
"unk_token": "[UNK]",
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {
"[EOS]": 0,
"[UNK]": 1,
"[CLS]": 2,
"[PAD]": 3,
"+": 4,
"-": 5,
"0": 6,
"1": 7,
"2": 8,
"3": 9,
"4": 10,
"5": 11,
"6": 12,
"7": 13,
"8": 14,
"9": 15,
"=": 16
},
"merges": []
}
}