Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +22 -22
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"add_eos_token": false,
|
| 4 |
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
-
"
|
| 7 |
"content": "õ",
|
| 8 |
"lstrip": false,
|
| 9 |
"normalized": true,
|
|
@@ -11,7 +11,7 @@
|
|
| 11 |
"single_word": false,
|
| 12 |
"special": false
|
| 13 |
},
|
| 14 |
-
"
|
| 15 |
"content": "÷",
|
| 16 |
"lstrip": false,
|
| 17 |
"normalized": true,
|
|
@@ -19,7 +19,7 @@
|
|
| 19 |
"single_word": false,
|
| 20 |
"special": false
|
| 21 |
},
|
| 22 |
-
"
|
| 23 |
"content": "Á",
|
| 24 |
"lstrip": false,
|
| 25 |
"normalized": true,
|
|
@@ -27,7 +27,7 @@
|
|
| 27 |
"single_word": false,
|
| 28 |
"special": false
|
| 29 |
},
|
| 30 |
-
"
|
| 31 |
"content": "ý",
|
| 32 |
"lstrip": false,
|
| 33 |
"normalized": true,
|
|
@@ -35,7 +35,7 @@
|
|
| 35 |
"single_word": false,
|
| 36 |
"special": false
|
| 37 |
},
|
| 38 |
-
"
|
| 39 |
"content": "À",
|
| 40 |
"lstrip": false,
|
| 41 |
"normalized": true,
|
|
@@ -43,7 +43,7 @@
|
|
| 43 |
"single_word": false,
|
| 44 |
"special": false
|
| 45 |
},
|
| 46 |
-
"
|
| 47 |
"content": "ÿ",
|
| 48 |
"lstrip": false,
|
| 49 |
"normalized": true,
|
|
@@ -51,7 +51,7 @@
|
|
| 51 |
"single_word": false,
|
| 52 |
"special": false
|
| 53 |
},
|
| 54 |
-
"
|
| 55 |
"content": "ø",
|
| 56 |
"lstrip": false,
|
| 57 |
"normalized": true,
|
|
@@ -59,7 +59,7 @@
|
|
| 59 |
"single_word": false,
|
| 60 |
"special": false
|
| 61 |
},
|
| 62 |
-
"
|
| 63 |
"content": "ú",
|
| 64 |
"lstrip": false,
|
| 65 |
"normalized": true,
|
|
@@ -67,7 +67,7 @@
|
|
| 67 |
"single_word": false,
|
| 68 |
"special": false
|
| 69 |
},
|
| 70 |
-
"
|
| 71 |
"content": "þ",
|
| 72 |
"lstrip": false,
|
| 73 |
"normalized": true,
|
|
@@ -75,7 +75,7 @@
|
|
| 75 |
"single_word": false,
|
| 76 |
"special": false
|
| 77 |
},
|
| 78 |
-
"
|
| 79 |
"content": "ü",
|
| 80 |
"lstrip": false,
|
| 81 |
"normalized": true,
|
|
@@ -83,7 +83,7 @@
|
|
| 83 |
"single_word": false,
|
| 84 |
"special": false
|
| 85 |
},
|
| 86 |
-
"
|
| 87 |
"content": "ù",
|
| 88 |
"lstrip": false,
|
| 89 |
"normalized": true,
|
|
@@ -91,7 +91,7 @@
|
|
| 91 |
"single_word": false,
|
| 92 |
"special": false
|
| 93 |
},
|
| 94 |
-
"
|
| 95 |
"content": "ö",
|
| 96 |
"lstrip": false,
|
| 97 |
"normalized": true,
|
|
@@ -99,7 +99,7 @@
|
|
| 99 |
"single_word": false,
|
| 100 |
"special": false
|
| 101 |
},
|
| 102 |
-
"
|
| 103 |
"content": "û",
|
| 104 |
"lstrip": false,
|
| 105 |
"normalized": true,
|
|
@@ -107,7 +107,7 @@
|
|
| 107 |
"single_word": false,
|
| 108 |
"special": false
|
| 109 |
},
|
| 110 |
-
"
|
| 111 |
"content": "<|begin▁of▁sentence|>",
|
| 112 |
"lstrip": false,
|
| 113 |
"normalized": true,
|
|
@@ -115,7 +115,7 @@
|
|
| 115 |
"single_word": false,
|
| 116 |
"special": true
|
| 117 |
},
|
| 118 |
-
"
|
| 119 |
"content": "<|end▁of▁sentence|>",
|
| 120 |
"lstrip": false,
|
| 121 |
"normalized": true,
|
|
@@ -123,7 +123,7 @@
|
|
| 123 |
"single_word": false,
|
| 124 |
"special": true
|
| 125 |
},
|
| 126 |
-
"
|
| 127 |
"content": "<|fim▁hole|>",
|
| 128 |
"lstrip": false,
|
| 129 |
"normalized": true,
|
|
@@ -131,7 +131,7 @@
|
|
| 131 |
"single_word": false,
|
| 132 |
"special": false
|
| 133 |
},
|
| 134 |
-
"
|
| 135 |
"content": "<|fim▁begin|>",
|
| 136 |
"lstrip": false,
|
| 137 |
"normalized": true,
|
|
@@ -139,7 +139,7 @@
|
|
| 139 |
"single_word": false,
|
| 140 |
"special": false
|
| 141 |
},
|
| 142 |
-
"
|
| 143 |
"content": "<|fim▁end|>",
|
| 144 |
"lstrip": false,
|
| 145 |
"normalized": true,
|
|
@@ -147,7 +147,7 @@
|
|
| 147 |
"single_word": false,
|
| 148 |
"special": false
|
| 149 |
},
|
| 150 |
-
"
|
| 151 |
"content": "<pad>",
|
| 152 |
"lstrip": false,
|
| 153 |
"normalized": true,
|
|
@@ -155,7 +155,7 @@
|
|
| 155 |
"single_word": false,
|
| 156 |
"special": false
|
| 157 |
},
|
| 158 |
-
"
|
| 159 |
"content": "<|User|>",
|
| 160 |
"lstrip": false,
|
| 161 |
"normalized": true,
|
|
@@ -163,7 +163,7 @@
|
|
| 163 |
"single_word": false,
|
| 164 |
"special": false
|
| 165 |
},
|
| 166 |
-
"
|
| 167 |
"content": "<|Assistant|>",
|
| 168 |
"lstrip": false,
|
| 169 |
"normalized": true,
|
|
@@ -171,7 +171,7 @@
|
|
| 171 |
"single_word": false,
|
| 172 |
"special": false
|
| 173 |
},
|
| 174 |
-
"
|
| 175 |
"content": "<|EOT|>",
|
| 176 |
"lstrip": false,
|
| 177 |
"normalized": true,
|
|
|
|
| 3 |
"add_eos_token": false,
|
| 4 |
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
+
"39861": {
|
| 7 |
"content": "õ",
|
| 8 |
"lstrip": false,
|
| 9 |
"normalized": true,
|
|
|
|
| 11 |
"single_word": false,
|
| 12 |
"special": false
|
| 13 |
},
|
| 14 |
+
"39862": {
|
| 15 |
"content": "÷",
|
| 16 |
"lstrip": false,
|
| 17 |
"normalized": true,
|
|
|
|
| 19 |
"single_word": false,
|
| 20 |
"special": false
|
| 21 |
},
|
| 22 |
+
"39863": {
|
| 23 |
"content": "Á",
|
| 24 |
"lstrip": false,
|
| 25 |
"normalized": true,
|
|
|
|
| 27 |
"single_word": false,
|
| 28 |
"special": false
|
| 29 |
},
|
| 30 |
+
"39864": {
|
| 31 |
"content": "ý",
|
| 32 |
"lstrip": false,
|
| 33 |
"normalized": true,
|
|
|
|
| 35 |
"single_word": false,
|
| 36 |
"special": false
|
| 37 |
},
|
| 38 |
+
"39865": {
|
| 39 |
"content": "À",
|
| 40 |
"lstrip": false,
|
| 41 |
"normalized": true,
|
|
|
|
| 43 |
"single_word": false,
|
| 44 |
"special": false
|
| 45 |
},
|
| 46 |
+
"39866": {
|
| 47 |
"content": "ÿ",
|
| 48 |
"lstrip": false,
|
| 49 |
"normalized": true,
|
|
|
|
| 51 |
"single_word": false,
|
| 52 |
"special": false
|
| 53 |
},
|
| 54 |
+
"39867": {
|
| 55 |
"content": "ø",
|
| 56 |
"lstrip": false,
|
| 57 |
"normalized": true,
|
|
|
|
| 59 |
"single_word": false,
|
| 60 |
"special": false
|
| 61 |
},
|
| 62 |
+
"39868": {
|
| 63 |
"content": "ú",
|
| 64 |
"lstrip": false,
|
| 65 |
"normalized": true,
|
|
|
|
| 67 |
"single_word": false,
|
| 68 |
"special": false
|
| 69 |
},
|
| 70 |
+
"39869": {
|
| 71 |
"content": "þ",
|
| 72 |
"lstrip": false,
|
| 73 |
"normalized": true,
|
|
|
|
| 75 |
"single_word": false,
|
| 76 |
"special": false
|
| 77 |
},
|
| 78 |
+
"39870": {
|
| 79 |
"content": "ü",
|
| 80 |
"lstrip": false,
|
| 81 |
"normalized": true,
|
|
|
|
| 83 |
"single_word": false,
|
| 84 |
"special": false
|
| 85 |
},
|
| 86 |
+
"39871": {
|
| 87 |
"content": "ù",
|
| 88 |
"lstrip": false,
|
| 89 |
"normalized": true,
|
|
|
|
| 91 |
"single_word": false,
|
| 92 |
"special": false
|
| 93 |
},
|
| 94 |
+
"39872": {
|
| 95 |
"content": "ö",
|
| 96 |
"lstrip": false,
|
| 97 |
"normalized": true,
|
|
|
|
| 99 |
"single_word": false,
|
| 100 |
"special": false
|
| 101 |
},
|
| 102 |
+
"39873": {
|
| 103 |
"content": "û",
|
| 104 |
"lstrip": false,
|
| 105 |
"normalized": true,
|
|
|
|
| 107 |
"single_word": false,
|
| 108 |
"special": false
|
| 109 |
},
|
| 110 |
+
"39874": {
|
| 111 |
"content": "<|begin▁of▁sentence|>",
|
| 112 |
"lstrip": false,
|
| 113 |
"normalized": true,
|
|
|
|
| 115 |
"single_word": false,
|
| 116 |
"special": true
|
| 117 |
},
|
| 118 |
+
"39875": {
|
| 119 |
"content": "<|end▁of▁sentence|>",
|
| 120 |
"lstrip": false,
|
| 121 |
"normalized": true,
|
|
|
|
| 123 |
"single_word": false,
|
| 124 |
"special": true
|
| 125 |
},
|
| 126 |
+
"39876": {
|
| 127 |
"content": "<|fim▁hole|>",
|
| 128 |
"lstrip": false,
|
| 129 |
"normalized": true,
|
|
|
|
| 131 |
"single_word": false,
|
| 132 |
"special": false
|
| 133 |
},
|
| 134 |
+
"39877": {
|
| 135 |
"content": "<|fim▁begin|>",
|
| 136 |
"lstrip": false,
|
| 137 |
"normalized": true,
|
|
|
|
| 139 |
"single_word": false,
|
| 140 |
"special": false
|
| 141 |
},
|
| 142 |
+
"39878": {
|
| 143 |
"content": "<|fim▁end|>",
|
| 144 |
"lstrip": false,
|
| 145 |
"normalized": true,
|
|
|
|
| 147 |
"single_word": false,
|
| 148 |
"special": false
|
| 149 |
},
|
| 150 |
+
"39879": {
|
| 151 |
"content": "<pad>",
|
| 152 |
"lstrip": false,
|
| 153 |
"normalized": true,
|
|
|
|
| 155 |
"single_word": false,
|
| 156 |
"special": false
|
| 157 |
},
|
| 158 |
+
"39880": {
|
| 159 |
"content": "<|User|>",
|
| 160 |
"lstrip": false,
|
| 161 |
"normalized": true,
|
|
|
|
| 163 |
"single_word": false,
|
| 164 |
"special": false
|
| 165 |
},
|
| 166 |
+
"39881": {
|
| 167 |
"content": "<|Assistant|>",
|
| 168 |
"lstrip": false,
|
| 169 |
"normalized": true,
|
|
|
|
| 171 |
"single_word": false,
|
| 172 |
"special": false
|
| 173 |
},
|
| 174 |
+
"39882": {
|
| 175 |
"content": "<|EOT|>",
|
| 176 |
"lstrip": false,
|
| 177 |
"normalized": true,
|