Mechinterp-old-Model / tokenizer.json
Manoj-kanur's picture
Training in progress, step 500
3f1394e verified
Raw
History Blame Contribute Delete
2.41 kB
{
"version": "1.0",
"truncation": null,
"padding": {
"strategy": "BatchLongest",
"direction": "Left",
"pad_to_multiple_of": null,
"pad_id": 0,
"pad_type_id": 0,
"pad_token": "<pad>"
},
"added_tokens": [
{
"id": 0,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<bos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "<eos>",
"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": "Split",
"pattern": {
"Regex": "[\\s\\S]"
},
"behavior": "Isolated",
"invert": false
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {}
},
"decoder": {
"type": "Fuse"
},
"model": {
"type": "WordLevel",
"vocab": {
"<pad>": 0,
"<bos>": 1,
"<eos>": 2,
"<unk>": 3,
"\n": 4,
"+": 5,
"0": 6,
"1": 7,
"2": 8,
"3": 9,
"4": 10,
"5": 11,
"6": 12,
"7": 13,
"8": 14,
"9": 15,
"=": 16,
"٠": 17,
"١": 18,
"٢": 19,
"٣": 20,
"٤": 21,
"٥": 22,
"٦": 23,
"٧": 24,
"٨": 25,
"٩": 26,
"०": 27,
"१": 28,
"२": 29,
"३": 30,
"४": 31,
"५": 32,
"६": 33,
"७": 34,
"८": 35,
"९": 36,
"一": 37,
"七": 38,
"三": 39,
"九": 40,
"二": 41,
"五": 42,
"八": 43,
"六": 44,
"四": 45,
"零": 46
},
"unk_token": "<unk>"
}
}