gpt2_1t_1M_256d_8l / tokenizer.json
jumelet's picture
Training in progress, step 1757
9c7b54c
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "<mask>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "<bos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "WhitespaceSplit"
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "<bos>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"<bos>": {
"id": "<bos>",
"ids": [
3
],
"tokens": [
"<bos>"
]
}
}
},
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"<unk>": 0,
"<pad>": 1,
"<mask>": 2,
"<bos>": 3,
"Bible": 4,
"that": 5,
"meant": 6,
"class": 7,
",": 8,
".": 9,
"and": 10,
"Today": 11,
"was": 12,
"Tuesday": 13
},
"unk_token": "<unk>"
}
}