kth_tokenizer / tokenizer.json
ardauzunoglu's picture
Upload tokenizer
8054815 verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": null,
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"<pad>": 0,
"<s>": 1,
"</s>": 2,
"<unk>": 3,
"A": 4,
"B": 5,
"0": 6,
"1": 7,
"2": 8,
"3": 9,
"4": 10,
"5": 11,
"6": 12,
"7": 13,
"8": 14,
"9": 15,
"K1": 16,
"K2": 17,
"K3": 18,
"K4": 19,
"K5": 20,
"K6": 21,
"K7": 22,
"EQUALS": 23,
"END": 24,
"K8": 25,
"K9": 26,
"K10": 27,
"SELECT": 28,
"SEP": 29
},
"unk_token": "<unk>"
}
}