Upload tokenizer
Browse files- tokenizer_config.json +29 -47
tokenizer_config.json
CHANGED
|
@@ -1,48 +1,30 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
"normalized": true,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
-
}
|
| 36 |
-
},
|
| 37 |
-
"bos_token": "ξ",
|
| 38 |
-
"clean_up_tokenization_spaces": false,
|
| 39 |
-
"cls_token": "ξ",
|
| 40 |
-
"eos_token": "ξ",
|
| 41 |
-
"extra_special_tokens": {},
|
| 42 |
-
"mask_token": "ξ",
|
| 43 |
-
"model_max_length": 2048,
|
| 44 |
-
"pad_token": "\u0000",
|
| 45 |
-
"processor_class": "GitProcessor",
|
| 46 |
-
"sep_token": "ξ",
|
| 47 |
-
"tokenizer_class": "CanineTokenizer"
|
| 48 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"char_ords": [
|
| 3 |
+
108,
|
| 4 |
+
35,
|
| 5 |
+
41,
|
| 6 |
+
61,
|
| 7 |
+
51,
|
| 8 |
+
70,
|
| 9 |
+
40,
|
| 10 |
+
93,
|
| 11 |
+
52,
|
| 12 |
+
43,
|
| 13 |
+
79,
|
| 14 |
+
49,
|
| 15 |
+
54,
|
| 16 |
+
78,
|
| 17 |
+
66,
|
| 18 |
+
83,
|
| 19 |
+
46,
|
| 20 |
+
50,
|
| 21 |
+
72,
|
| 22 |
+
45,
|
| 23 |
+
114,
|
| 24 |
+
67,
|
| 25 |
+
80,
|
| 26 |
+
91,
|
| 27 |
+
53
|
| 28 |
+
],
|
| 29 |
+
"model_max_length": 1024
|
| 30 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|