add tokenizer to main
Browse files- tokenizer.json +57 -0
tokenizer.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [],
|
| 6 |
+
"normalizer": null,
|
| 7 |
+
"pre_tokenizer": {
|
| 8 |
+
"type": "ByteLevel",
|
| 9 |
+
"add_prefix_space": true,
|
| 10 |
+
"trim_offsets": true,
|
| 11 |
+
"use_regex": true
|
| 12 |
+
},
|
| 13 |
+
"post_processor": null,
|
| 14 |
+
"decoder": null,
|
| 15 |
+
"model": {
|
| 16 |
+
"type": "BPE",
|
| 17 |
+
"dropout": null,
|
| 18 |
+
"unk_token": null,
|
| 19 |
+
"continuing_subword_prefix": null,
|
| 20 |
+
"end_of_word_suffix": null,
|
| 21 |
+
"fuse_unk": false,
|
| 22 |
+
"vocab": {
|
| 23 |
+
"<|endoftext|>": 0,
|
| 24 |
+
" A": 1,
|
| 25 |
+
" B": 2,
|
| 26 |
+
" C": 3,
|
| 27 |
+
" D": 4,
|
| 28 |
+
" E": 5,
|
| 29 |
+
" F": 6,
|
| 30 |
+
" G": 7,
|
| 31 |
+
" H": 8,
|
| 32 |
+
" I": 9,
|
| 33 |
+
" J": 10,
|
| 34 |
+
" K": 11,
|
| 35 |
+
" L": 12,
|
| 36 |
+
" M": 13,
|
| 37 |
+
" N": 14,
|
| 38 |
+
" O": 15,
|
| 39 |
+
" P": 16,
|
| 40 |
+
" Q": 17,
|
| 41 |
+
" R": 18,
|
| 42 |
+
" S": 19,
|
| 43 |
+
" T": 20,
|
| 44 |
+
" U": 21,
|
| 45 |
+
" V": 22,
|
| 46 |
+
" W": 23,
|
| 47 |
+
" X": 24,
|
| 48 |
+
" Y": 25,
|
| 49 |
+
" Z": 26,
|
| 50 |
+
" a": 27,
|
| 51 |
+
" b": 28,
|
| 52 |
+
" c": 29,
|
| 53 |
+
" d": 30
|
| 54 |
+
},
|
| 55 |
+
"merges": []
|
| 56 |
+
}
|
| 57 |
+
}
|