wtff / tokenizer.json
Fizzarolli's picture
Upload folder using huggingface_hub
ca76e7c verified
{
"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": "<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
}
],
"normalizer": null,
"pre_tokenizer": null,
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "<s>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "<s>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "<s>",
"type_id": 1
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"<s>": {
"id": "<s>",
"ids": [
1
],
"tokens": [
"<s>"
]
}
}
},
"decoder": null,
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {
"<unk>": 0,
"<s>": 1,
"</s>": 2,
"_tok_3": 3,
"_tok_4": 4,
"_tok_5": 5,
"_tok_6": 6,
"_tok_7": 7,
"_tok_8": 8,
"_tok_9": 9,
"_tok_10": 10,
"_tok_11": 11,
"_tok_12": 12,
"_tok_13": 13,
"_tok_14": 14,
"_tok_15": 15,
"_tok_16": 16,
"_tok_17": 17,
"_tok_18": 18,
"_tok_19": 19,
"_tok_20": 20,
"_tok_21": 21,
"_tok_22": 22,
"_tok_23": 23,
"_tok_24": 24,
"_tok_25": 25,
"_tok_26": 26,
"_tok_27": 27,
"_tok_28": 28,
"_tok_29": 29,
"_tok_30": 30,
"_tok_31": 31,
"_tok_32": 32,
"_tok_33": 33,
"_tok_34": 34,
"_tok_35": 35,
"_tok_36": 36,
"_tok_37": 37,
"_tok_38": 38,
"_tok_39": 39,
"_tok_40": 40,
"_tok_41": 41,
"_tok_42": 42,
"_tok_43": 43,
"_tok_44": 44,
"_tok_45": 45,
"_tok_46": 46,
"_tok_47": 47,
"_tok_48": 48,
"_tok_49": 49,
"_tok_50": 50,
"_tok_51": 51,
"_tok_52": 52,
"_tok_53": 53,
"_tok_54": 54,
"_tok_55": 55,
"_tok_56": 56,
"_tok_57": 57,
"_tok_58": 58,
"_tok_59": 59,
"_tok_60": 60,
"_tok_61": 61,
"_tok_62": 62,
"_tok_63": 63
},
"merges": []
}
}