Create tokenizer.json
Browse files- tokenizer.json +52 -0
tokenizer.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [],
|
| 6 |
+
"normalizer": null,
|
| 7 |
+
"pre_tokenizer": null,
|
| 8 |
+
"post_processor": null,
|
| 9 |
+
"decoder": null,
|
| 10 |
+
"model": {
|
| 11 |
+
"vocab": {
|
| 12 |
+
"[GO]": 0,
|
| 13 |
+
"[s]": 1,
|
| 14 |
+
"0": 2,
|
| 15 |
+
"1": 3,
|
| 16 |
+
"2": 4,
|
| 17 |
+
"3": 5,
|
| 18 |
+
"4": 6,
|
| 19 |
+
"5": 7,
|
| 20 |
+
"6": 8,
|
| 21 |
+
"7": 9,
|
| 22 |
+
"8": 10,
|
| 23 |
+
"9": 11,
|
| 24 |
+
"a": 12,
|
| 25 |
+
"b": 13,
|
| 26 |
+
"c": 14,
|
| 27 |
+
"d": 15,
|
| 28 |
+
"e": 16,
|
| 29 |
+
"f": 17,
|
| 30 |
+
"g": 18,
|
| 31 |
+
"h": 19,
|
| 32 |
+
"i": 20,
|
| 33 |
+
"j": 21,
|
| 34 |
+
"k": 22,
|
| 35 |
+
"l": 23,
|
| 36 |
+
"m": 24,
|
| 37 |
+
"n": 25,
|
| 38 |
+
"o": 26,
|
| 39 |
+
"p": 27,
|
| 40 |
+
"q": 28,
|
| 41 |
+
"r": 29,
|
| 42 |
+
"s": 30,
|
| 43 |
+
"t": 31,
|
| 44 |
+
"u": 32,
|
| 45 |
+
"v": 33,
|
| 46 |
+
"w": 34,
|
| 47 |
+
"x": 35,
|
| 48 |
+
"y": 36,
|
| 49 |
+
"z": 37
|
| 50 |
+
}
|
| 51 |
+
}
|
| 52 |
+
}
|