Upload folder using huggingface_hub
Browse files- README.md +1 -1
- tokenizer.json +1 -1
- vocab.json +91 -91
README.md
CHANGED
|
@@ -46,4 +46,4 @@ tokens = tokenizer.encode("Hello, world!")
|
|
| 46 |
## Sample Encoding
|
| 47 |
| Text | Tokens | Token IDs |
|
| 48 |
|------|--------|-----------|
|
| 49 |
-
| `
|
|
|
|
| 46 |
## Sample Encoding
|
| 47 |
| Text | Tokens | Token IDs |
|
| 48 |
|------|--------|-----------|
|
| 49 |
+
| `123500119 mod 67` | `12, 35, 0, 0, 11, 9, , mod, , 67` | `19, 42, 7, 7, 18, 16, 6, 4, 6, 74` |
|
tokenizer.json
CHANGED
|
@@ -83,7 +83,7 @@
|
|
| 83 |
"type": "ByteLevel",
|
| 84 |
"add_prefix_space": false,
|
| 85 |
"trim_offsets": true,
|
| 86 |
-
"use_regex":
|
| 87 |
}
|
| 88 |
]
|
| 89 |
},
|
|
|
|
| 83 |
"type": "ByteLevel",
|
| 84 |
"add_prefix_space": false,
|
| 85 |
"trim_offsets": true,
|
| 86 |
+
"use_regex": false
|
| 87 |
}
|
| 88 |
]
|
| 89 |
},
|
vocab.json
CHANGED
|
@@ -1,109 +1,109 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"71": 78,
|
| 7 |
-
"18": 25,
|
| 8 |
"0": 7,
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
| 13 |
-
"
|
|
|
|
| 14 |
"32": 39,
|
| 15 |
-
"<s>": 1,
|
| 16 |
-
"30": 37,
|
| 17 |
-
"14": 21,
|
| 18 |
-
"80": 87,
|
| 19 |
-
"73": 80,
|
| 20 |
-
"57": 64,
|
| 21 |
"41": 48,
|
| 22 |
-
"37": 44,
|
| 23 |
-
"2": 9,
|
| 24 |
-
"20": 27,
|
| 25 |
-
"29": 36,
|
| 26 |
-
"26": 33,
|
| 27 |
-
"53": 60,
|
| 28 |
-
"39": 46,
|
| 29 |
-
"40": 47,
|
| 30 |
-
"38": 45,
|
| 31 |
-
"56": 63,
|
| 32 |
-
"64": 71,
|
| 33 |
-
"87": 94,
|
| 34 |
-
"8": 15,
|
| 35 |
-
"23": 30,
|
| 36 |
-
"67": 74,
|
| 37 |
-
"51": 58,
|
| 38 |
-
"63": 70,
|
| 39 |
-
"89": 96,
|
| 40 |
-
"84": 91,
|
| 41 |
-
"=": 5,
|
| 42 |
-
"72": 79,
|
| 43 |
-
"60": 67,
|
| 44 |
-
"59": 66,
|
| 45 |
-
"21": 28,
|
| 46 |
-
"9": 16,
|
| 47 |
-
"82": 89,
|
| 48 |
-
"47": 54,
|
| 49 |
"50": 57,
|
| 50 |
-
"
|
| 51 |
-
"15": 22,
|
| 52 |
-
"19": 26,
|
| 53 |
-
"44": 51,
|
| 54 |
"85": 92,
|
| 55 |
-
"
|
| 56 |
-
"31": 38,
|
| 57 |
-
"88": 95,
|
| 58 |
"25": 32,
|
| 59 |
-
"
|
| 60 |
-
"24": 31,
|
| 61 |
"99": 106,
|
| 62 |
-
"
|
|
|
|
|
|
|
| 63 |
"74": 81,
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"28": 35,
|
| 67 |
-
"3": 10,
|
| 68 |
-
"86": 93,
|
| 69 |
"83": 90,
|
| 70 |
-
"
|
| 71 |
-
"
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
"48": 55,
|
| 75 |
-
"68": 75,
|
| 76 |
-
"58": 65,
|
| 77 |
-
"91": 98,
|
| 78 |
-
"36": 43,
|
| 79 |
-
"34": 41,
|
| 80 |
-
"52": 59,
|
| 81 |
-
"7": 14,
|
| 82 |
-
"78": 85,
|
| 83 |
-
"4": 11,
|
| 84 |
-
"13": 20,
|
| 85 |
-
"10": 17,
|
| 86 |
-
"61": 68,
|
| 87 |
-
"49": 56,
|
| 88 |
-
"97": 104,
|
| 89 |
"75": 82,
|
| 90 |
-
"
|
| 91 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
"33": 40,
|
|
|
|
|
|
|
| 93 |
"43": 50,
|
| 94 |
-
"27": 34,
|
| 95 |
-
"90": 97,
|
| 96 |
-
"mod": 4,
|
| 97 |
-
"1": 8,
|
| 98 |
-
"<pad>": 3,
|
| 99 |
-
"92": 99,
|
| 100 |
"76": 83,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
"55": 62,
|
| 102 |
-
"96": 103,
|
| 103 |
"6": 13,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 104 |
"</s>": 2,
|
| 105 |
-
"
|
| 106 |
-
"
|
| 107 |
-
"
|
| 108 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 109 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"56": 63,
|
| 3 |
+
"93": 100,
|
| 4 |
+
"30": 37,
|
| 5 |
+
"51": 58,
|
|
|
|
|
|
|
| 6 |
"0": 7,
|
| 7 |
+
"79": 86,
|
| 8 |
+
"96": 103,
|
| 9 |
+
"37": 44,
|
| 10 |
+
"92": 99,
|
| 11 |
+
"95": 102,
|
| 12 |
+
"7": 14,
|
| 13 |
"32": 39,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"41": 48,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"50": 57,
|
| 16 |
+
"71": 78,
|
|
|
|
|
|
|
|
|
|
| 17 |
"85": 92,
|
| 18 |
+
"59": 66,
|
|
|
|
|
|
|
| 19 |
"25": 32,
|
| 20 |
+
"11": 18,
|
|
|
|
| 21 |
"99": 106,
|
| 22 |
+
"26": 33,
|
| 23 |
+
"88": 95,
|
| 24 |
+
"1": 8,
|
| 25 |
"74": 81,
|
| 26 |
+
"84": 91,
|
| 27 |
+
"46": 53,
|
|
|
|
|
|
|
|
|
|
| 28 |
"83": 90,
|
| 29 |
+
"64": 71,
|
| 30 |
+
"21": 28,
|
| 31 |
+
"=": 5,
|
| 32 |
+
"69": 76,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
"75": 82,
|
| 34 |
+
"44": 51,
|
| 35 |
+
"mod": 4,
|
| 36 |
+
"40": 47,
|
| 37 |
+
"68": 75,
|
| 38 |
+
"42": 49,
|
| 39 |
+
"28": 35,
|
| 40 |
+
"94": 101,
|
| 41 |
+
"90": 97,
|
| 42 |
+
"65": 72,
|
| 43 |
+
"70": 77,
|
| 44 |
+
"66": 73,
|
| 45 |
+
"22": 29,
|
| 46 |
+
"98": 105,
|
| 47 |
+
"86": 93,
|
| 48 |
"33": 40,
|
| 49 |
+
"<unk>": 0,
|
| 50 |
+
"24": 31,
|
| 51 |
"43": 50,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
"76": 83,
|
| 53 |
+
"38": 45,
|
| 54 |
+
"17": 24,
|
| 55 |
+
"82": 89,
|
| 56 |
+
"47": 54,
|
| 57 |
+
"61": 68,
|
| 58 |
+
"18": 25,
|
| 59 |
+
"73": 80,
|
| 60 |
+
"34": 41,
|
| 61 |
+
"67": 74,
|
| 62 |
+
"97": 104,
|
| 63 |
+
"<s>": 1,
|
| 64 |
+
"49": 56,
|
| 65 |
+
"39": 46,
|
| 66 |
+
"78": 85,
|
| 67 |
+
"29": 36,
|
| 68 |
+
"89": 96,
|
| 69 |
"55": 62,
|
|
|
|
| 70 |
"6": 13,
|
| 71 |
+
"52": 59,
|
| 72 |
+
"45": 52,
|
| 73 |
+
"3": 10,
|
| 74 |
+
"4": 11,
|
| 75 |
+
"54": 61,
|
| 76 |
+
"<pad>": 3,
|
| 77 |
+
"53": 60,
|
| 78 |
+
"19": 26,
|
| 79 |
+
"10": 17,
|
| 80 |
+
"58": 65,
|
| 81 |
+
"27": 34,
|
| 82 |
+
"91": 98,
|
| 83 |
+
"14": 21,
|
| 84 |
+
"23": 30,
|
| 85 |
+
"48": 55,
|
| 86 |
+
"62": 69,
|
| 87 |
+
" ": 6,
|
| 88 |
+
"35": 42,
|
| 89 |
+
"31": 38,
|
| 90 |
+
"2": 9,
|
| 91 |
+
"77": 84,
|
| 92 |
+
"72": 79,
|
| 93 |
+
"36": 43,
|
| 94 |
+
"60": 67,
|
| 95 |
+
"80": 87,
|
| 96 |
+
"16": 23,
|
| 97 |
+
"9": 16,
|
| 98 |
"</s>": 2,
|
| 99 |
+
"63": 70,
|
| 100 |
+
"8": 15,
|
| 101 |
+
"5": 12,
|
| 102 |
+
"81": 88,
|
| 103 |
+
"13": 20,
|
| 104 |
+
"57": 64,
|
| 105 |
+
"87": 94,
|
| 106 |
+
"20": 27,
|
| 107 |
+
"15": 22,
|
| 108 |
+
"12": 19
|
| 109 |
}
|