NextTerm-47M / tokenizer.json
N8Programs's picture
Upload 7 files
ac593f9 verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 12,
"content": "<bos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 13,
"content": "<eos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 14,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Replace",
"pattern": {
"Regex": "[^0-9,-]+"
},
"content": ""
},
{
"type": "Replace",
"pattern": {
"Regex": ",+"
},
"content": ","
},
{
"type": "Strip",
"strip_left": true,
"strip_right": true
},
{
"type": "Replace",
"pattern": {
"Regex": "^,+"
},
"content": ""
},
{ "type": "Replace", "pattern": { "Regex": ",{2,}$" }, "content": "," }
]
},
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": ""
},
"behavior": "Isolated",
"invert": false
},
"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": [
12
],
"tokens": [
"<bos>"
]
}
}
},
"decoder": {
"type": "Sequence",
"decoders": [
{
"type": "Replace",
"pattern": {
"String": " "
},
"content": ""
}
]
},
"model": {
"type": "WordLevel",
"vocab": {
"0": 0,
"1": 1,
"2": 2,
"3": 3,
"4": 4,
"5": 5,
"6": 6,
"7": 7,
"8": 8,
"9": 9,
"-": 10,
",": 11,
"<bos>": 12,
"<eos>": 13,
"<pad>": 14
},
"unk_token": "<pad>"
}
}