Upload tokenizer
Browse files- merges.txt +0 -1
- special_tokens_map.json +5 -3
- tokenizer.json +0 -0
- tokenizer_config.json +35 -25
- vocab.json +0 -0
merges.txt
CHANGED
|
@@ -32483,4 +32483,3 @@ ason ic
|
|
| 32483 |
ple ted
|
| 32484 |
cent ered
|
| 32485 |
ĠCl ose
|
| 32486 |
-
ek t
|
|
|
|
| 32483 |
ple ted
|
| 32484 |
cent ered
|
| 32485 |
ĠCl ose
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "<
|
| 3 |
-
"
|
| 4 |
-
"
|
|
|
|
|
|
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<bos>",
|
| 3 |
+
"cls_token": "<classification>",
|
| 4 |
+
"eos_token": "<eos>",
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
+
"unk_token": "<unk>"
|
| 7 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -34,7 +34,7 @@
|
|
| 34 |
"special": true
|
| 35 |
},
|
| 36 |
"4": {
|
| 37 |
-
"content": "<
|
| 38 |
"lstrip": false,
|
| 39 |
"normalized": false,
|
| 40 |
"rstrip": false,
|
|
@@ -42,7 +42,7 @@
|
|
| 42 |
"special": true
|
| 43 |
},
|
| 44 |
"5": {
|
| 45 |
-
"content": "<
|
| 46 |
"lstrip": false,
|
| 47 |
"normalized": false,
|
| 48 |
"rstrip": false,
|
|
@@ -50,7 +50,7 @@
|
|
| 50 |
"special": true
|
| 51 |
},
|
| 52 |
"6": {
|
| 53 |
-
"content": "<
|
| 54 |
"lstrip": false,
|
| 55 |
"normalized": false,
|
| 56 |
"rstrip": false,
|
|
@@ -58,7 +58,7 @@
|
|
| 58 |
"special": true
|
| 59 |
},
|
| 60 |
"7": {
|
| 61 |
-
"content": "<
|
| 62 |
"lstrip": false,
|
| 63 |
"normalized": false,
|
| 64 |
"rstrip": false,
|
|
@@ -66,7 +66,7 @@
|
|
| 66 |
"special": true
|
| 67 |
},
|
| 68 |
"8": {
|
| 69 |
-
"content": "<
|
| 70 |
"lstrip": false,
|
| 71 |
"normalized": false,
|
| 72 |
"rstrip": false,
|
|
@@ -74,7 +74,7 @@
|
|
| 74 |
"special": true
|
| 75 |
},
|
| 76 |
"9": {
|
| 77 |
-
"content": "<
|
| 78 |
"lstrip": false,
|
| 79 |
"normalized": false,
|
| 80 |
"rstrip": false,
|
|
@@ -82,7 +82,7 @@
|
|
| 82 |
"special": true
|
| 83 |
},
|
| 84 |
"10": {
|
| 85 |
-
"content": "<
|
| 86 |
"lstrip": false,
|
| 87 |
"normalized": false,
|
| 88 |
"rstrip": false,
|
|
@@ -90,7 +90,7 @@
|
|
| 90 |
"special": true
|
| 91 |
},
|
| 92 |
"11": {
|
| 93 |
-
"content": "<
|
| 94 |
"lstrip": false,
|
| 95 |
"normalized": false,
|
| 96 |
"rstrip": false,
|
|
@@ -98,7 +98,7 @@
|
|
| 98 |
"special": true
|
| 99 |
},
|
| 100 |
"12": {
|
| 101 |
-
"content": "<
|
| 102 |
"lstrip": false,
|
| 103 |
"normalized": false,
|
| 104 |
"rstrip": false,
|
|
@@ -106,7 +106,7 @@
|
|
| 106 |
"special": true
|
| 107 |
},
|
| 108 |
"13": {
|
| 109 |
-
"content": "<
|
| 110 |
"lstrip": false,
|
| 111 |
"normalized": false,
|
| 112 |
"rstrip": false,
|
|
@@ -114,7 +114,7 @@
|
|
| 114 |
"special": true
|
| 115 |
},
|
| 116 |
"14": {
|
| 117 |
-
"content": "<
|
| 118 |
"lstrip": false,
|
| 119 |
"normalized": false,
|
| 120 |
"rstrip": false,
|
|
@@ -122,7 +122,7 @@
|
|
| 122 |
"special": true
|
| 123 |
},
|
| 124 |
"15": {
|
| 125 |
-
"content": "<
|
| 126 |
"lstrip": false,
|
| 127 |
"normalized": false,
|
| 128 |
"rstrip": false,
|
|
@@ -130,7 +130,7 @@
|
|
| 130 |
"special": true
|
| 131 |
},
|
| 132 |
"16": {
|
| 133 |
-
"content": "<
|
| 134 |
"lstrip": false,
|
| 135 |
"normalized": false,
|
| 136 |
"rstrip": false,
|
|
@@ -138,7 +138,7 @@
|
|
| 138 |
"special": true
|
| 139 |
},
|
| 140 |
"17": {
|
| 141 |
-
"content": "<
|
| 142 |
"lstrip": false,
|
| 143 |
"normalized": false,
|
| 144 |
"rstrip": false,
|
|
@@ -146,7 +146,7 @@
|
|
| 146 |
"special": true
|
| 147 |
},
|
| 148 |
"18": {
|
| 149 |
-
"content": "<
|
| 150 |
"lstrip": false,
|
| 151 |
"normalized": false,
|
| 152 |
"rstrip": false,
|
|
@@ -154,7 +154,7 @@
|
|
| 154 |
"special": true
|
| 155 |
},
|
| 156 |
"19": {
|
| 157 |
-
"content": "<
|
| 158 |
"lstrip": false,
|
| 159 |
"normalized": false,
|
| 160 |
"rstrip": false,
|
|
@@ -162,7 +162,7 @@
|
|
| 162 |
"special": true
|
| 163 |
},
|
| 164 |
"20": {
|
| 165 |
-
"content": "<
|
| 166 |
"lstrip": false,
|
| 167 |
"normalized": false,
|
| 168 |
"rstrip": false,
|
|
@@ -170,7 +170,7 @@
|
|
| 170 |
"special": true
|
| 171 |
},
|
| 172 |
"21": {
|
| 173 |
-
"content": "<
|
| 174 |
"lstrip": false,
|
| 175 |
"normalized": false,
|
| 176 |
"rstrip": false,
|
|
@@ -178,7 +178,7 @@
|
|
| 178 |
"special": true
|
| 179 |
},
|
| 180 |
"22": {
|
| 181 |
-
"content": "<
|
| 182 |
"lstrip": false,
|
| 183 |
"normalized": false,
|
| 184 |
"rstrip": false,
|
|
@@ -186,7 +186,7 @@
|
|
| 186 |
"special": true
|
| 187 |
},
|
| 188 |
"23": {
|
| 189 |
-
"content": "<
|
| 190 |
"lstrip": false,
|
| 191 |
"normalized": false,
|
| 192 |
"rstrip": false,
|
|
@@ -194,7 +194,7 @@
|
|
| 194 |
"special": true
|
| 195 |
},
|
| 196 |
"24": {
|
| 197 |
-
"content": "<
|
| 198 |
"lstrip": false,
|
| 199 |
"normalized": false,
|
| 200 |
"rstrip": false,
|
|
@@ -202,7 +202,7 @@
|
|
| 202 |
"special": true
|
| 203 |
},
|
| 204 |
"25": {
|
| 205 |
-
"content": "<
|
| 206 |
"lstrip": false,
|
| 207 |
"normalized": false,
|
| 208 |
"rstrip": false,
|
|
@@ -210,6 +210,14 @@
|
|
| 210 |
"special": true
|
| 211 |
},
|
| 212 |
"26": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 213 |
"content": "<reserved15>",
|
| 214 |
"lstrip": false,
|
| 215 |
"normalized": false,
|
|
@@ -226,11 +234,13 @@
|
|
| 226 |
"special": true
|
| 227 |
}
|
| 228 |
},
|
| 229 |
-
"bos_token": "<
|
| 230 |
"clean_up_tokenization_spaces": false,
|
| 231 |
-
"
|
|
|
|
| 232 |
"extra_special_tokens": {},
|
| 233 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 234 |
"tokenizer_class": "GPT2Tokenizer",
|
| 235 |
-
"unk_token": "<
|
| 236 |
}
|
|
|
|
| 34 |
"special": true
|
| 35 |
},
|
| 36 |
"4": {
|
| 37 |
+
"content": "<unk>",
|
| 38 |
"lstrip": false,
|
| 39 |
"normalized": false,
|
| 40 |
"rstrip": false,
|
|
|
|
| 42 |
"special": true
|
| 43 |
},
|
| 44 |
"5": {
|
| 45 |
+
"content": "<mask>",
|
| 46 |
"lstrip": false,
|
| 47 |
"normalized": false,
|
| 48 |
"rstrip": false,
|
|
|
|
| 50 |
"special": true
|
| 51 |
},
|
| 52 |
"6": {
|
| 53 |
+
"content": "<general><semantic_similarity>",
|
| 54 |
"lstrip": false,
|
| 55 |
"normalized": false,
|
| 56 |
"rstrip": false,
|
|
|
|
| 58 |
"special": true
|
| 59 |
},
|
| 60 |
"7": {
|
| 61 |
+
"content": "<classification>",
|
| 62 |
"lstrip": false,
|
| 63 |
"normalized": false,
|
| 64 |
"rstrip": false,
|
|
|
|
| 66 |
"special": true
|
| 67 |
},
|
| 68 |
"8": {
|
| 69 |
+
"content": "<clustering>",
|
| 70 |
"lstrip": false,
|
| 71 |
"normalized": false,
|
| 72 |
"rstrip": false,
|
|
|
|
| 74 |
"special": true
|
| 75 |
},
|
| 76 |
"9": {
|
| 77 |
+
"content": "<retrieval_query>",
|
| 78 |
"lstrip": false,
|
| 79 |
"normalized": false,
|
| 80 |
"rstrip": false,
|
|
|
|
| 82 |
"special": true
|
| 83 |
},
|
| 84 |
"10": {
|
| 85 |
+
"content": "<retrieval_document>",
|
| 86 |
"lstrip": false,
|
| 87 |
"normalized": false,
|
| 88 |
"rstrip": false,
|
|
|
|
| 90 |
"special": true
|
| 91 |
},
|
| 92 |
"11": {
|
| 93 |
+
"content": "<code_retrieval_query>",
|
| 94 |
"lstrip": false,
|
| 95 |
"normalized": false,
|
| 96 |
"rstrip": false,
|
|
|
|
| 98 |
"special": true
|
| 99 |
},
|
| 100 |
"12": {
|
| 101 |
+
"content": "<reserved0>",
|
| 102 |
"lstrip": false,
|
| 103 |
"normalized": false,
|
| 104 |
"rstrip": false,
|
|
|
|
| 106 |
"special": true
|
| 107 |
},
|
| 108 |
"13": {
|
| 109 |
+
"content": "<reserved1>",
|
| 110 |
"lstrip": false,
|
| 111 |
"normalized": false,
|
| 112 |
"rstrip": false,
|
|
|
|
| 114 |
"special": true
|
| 115 |
},
|
| 116 |
"14": {
|
| 117 |
+
"content": "<reserved2>",
|
| 118 |
"lstrip": false,
|
| 119 |
"normalized": false,
|
| 120 |
"rstrip": false,
|
|
|
|
| 122 |
"special": true
|
| 123 |
},
|
| 124 |
"15": {
|
| 125 |
+
"content": "<reserved3>",
|
| 126 |
"lstrip": false,
|
| 127 |
"normalized": false,
|
| 128 |
"rstrip": false,
|
|
|
|
| 130 |
"special": true
|
| 131 |
},
|
| 132 |
"16": {
|
| 133 |
+
"content": "<reserved4>",
|
| 134 |
"lstrip": false,
|
| 135 |
"normalized": false,
|
| 136 |
"rstrip": false,
|
|
|
|
| 138 |
"special": true
|
| 139 |
},
|
| 140 |
"17": {
|
| 141 |
+
"content": "<reserved5>",
|
| 142 |
"lstrip": false,
|
| 143 |
"normalized": false,
|
| 144 |
"rstrip": false,
|
|
|
|
| 146 |
"special": true
|
| 147 |
},
|
| 148 |
"18": {
|
| 149 |
+
"content": "<reserved6>",
|
| 150 |
"lstrip": false,
|
| 151 |
"normalized": false,
|
| 152 |
"rstrip": false,
|
|
|
|
| 154 |
"special": true
|
| 155 |
},
|
| 156 |
"19": {
|
| 157 |
+
"content": "<reserved7>",
|
| 158 |
"lstrip": false,
|
| 159 |
"normalized": false,
|
| 160 |
"rstrip": false,
|
|
|
|
| 162 |
"special": true
|
| 163 |
},
|
| 164 |
"20": {
|
| 165 |
+
"content": "<reserved8>",
|
| 166 |
"lstrip": false,
|
| 167 |
"normalized": false,
|
| 168 |
"rstrip": false,
|
|
|
|
| 170 |
"special": true
|
| 171 |
},
|
| 172 |
"21": {
|
| 173 |
+
"content": "<reserved9>",
|
| 174 |
"lstrip": false,
|
| 175 |
"normalized": false,
|
| 176 |
"rstrip": false,
|
|
|
|
| 178 |
"special": true
|
| 179 |
},
|
| 180 |
"22": {
|
| 181 |
+
"content": "<reserved10>",
|
| 182 |
"lstrip": false,
|
| 183 |
"normalized": false,
|
| 184 |
"rstrip": false,
|
|
|
|
| 186 |
"special": true
|
| 187 |
},
|
| 188 |
"23": {
|
| 189 |
+
"content": "<reserved11>",
|
| 190 |
"lstrip": false,
|
| 191 |
"normalized": false,
|
| 192 |
"rstrip": false,
|
|
|
|
| 194 |
"special": true
|
| 195 |
},
|
| 196 |
"24": {
|
| 197 |
+
"content": "<reserved12>",
|
| 198 |
"lstrip": false,
|
| 199 |
"normalized": false,
|
| 200 |
"rstrip": false,
|
|
|
|
| 202 |
"special": true
|
| 203 |
},
|
| 204 |
"25": {
|
| 205 |
+
"content": "<reserved13>",
|
| 206 |
"lstrip": false,
|
| 207 |
"normalized": false,
|
| 208 |
"rstrip": false,
|
|
|
|
| 210 |
"special": true
|
| 211 |
},
|
| 212 |
"26": {
|
| 213 |
+
"content": "<reserved14>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"27": {
|
| 221 |
"content": "<reserved15>",
|
| 222 |
"lstrip": false,
|
| 223 |
"normalized": false,
|
|
|
|
| 234 |
"special": true
|
| 235 |
}
|
| 236 |
},
|
| 237 |
+
"bos_token": "<bos>",
|
| 238 |
"clean_up_tokenization_spaces": false,
|
| 239 |
+
"cls_token": "<classification>",
|
| 240 |
+
"eos_token": "<eos>",
|
| 241 |
"extra_special_tokens": {},
|
| 242 |
"model_max_length": 1000000000000000019884624838656,
|
| 243 |
+
"pad_token": "<pad>",
|
| 244 |
"tokenizer_class": "GPT2Tokenizer",
|
| 245 |
+
"unk_token": "<unk>"
|
| 246 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|