JuIm's picture
Upload tokenizer
7c80180 verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "R",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 1,
"content": "H",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 2,
"content": "K",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 3,
"content": "D",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 4,
"content": "E",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 5,
"content": "S",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 6,
"content": "T",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 7,
"content": "N",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 8,
"content": "Q",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 9,
"content": "C",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 10,
"content": "G",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 11,
"content": "P",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 12,
"content": "A",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 13,
"content": "V",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 14,
"content": "I",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 15,
"content": "L",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 16,
"content": "M",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 17,
"content": "F",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 18,
"content": "Y",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 19,
"content": "W",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 20,
"content": "<bos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 21,
"content": "<eos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 22,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 23,
"content": "<mask>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"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": {},
"merges": []
}
}