unspecialed
Browse files- tokenizer.json +15 -15
- tokenizer_config.json +14 -14
tokenizer.json
CHANGED
|
@@ -10,7 +10,7 @@
|
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
-
"special":
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 100257,
|
|
@@ -55,7 +55,7 @@
|
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
"normalized": false,
|
| 58 |
-
"special":
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 100262,
|
|
@@ -64,7 +64,7 @@
|
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
"normalized": false,
|
| 67 |
-
"special":
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 100263,
|
|
@@ -73,7 +73,7 @@
|
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
| 75 |
"normalized": false,
|
| 76 |
-
"special":
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 100264,
|
|
@@ -100,7 +100,7 @@
|
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
| 102 |
"normalized": false,
|
| 103 |
-
"special":
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 100267,
|
|
@@ -109,7 +109,7 @@
|
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
| 111 |
"normalized": false,
|
| 112 |
-
"special":
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 100268,
|
|
@@ -118,7 +118,7 @@
|
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
| 120 |
"normalized": false,
|
| 121 |
-
"special":
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 100269,
|
|
@@ -127,7 +127,7 @@
|
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
| 129 |
"normalized": false,
|
| 130 |
-
"special":
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 100270,
|
|
@@ -136,7 +136,7 @@
|
|
| 136 |
"lstrip": false,
|
| 137 |
"rstrip": false,
|
| 138 |
"normalized": false,
|
| 139 |
-
"special":
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 100271,
|
|
@@ -145,7 +145,7 @@
|
|
| 145 |
"lstrip": false,
|
| 146 |
"rstrip": false,
|
| 147 |
"normalized": false,
|
| 148 |
-
"special":
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 100272,
|
|
@@ -154,7 +154,7 @@
|
|
| 154 |
"lstrip": false,
|
| 155 |
"rstrip": false,
|
| 156 |
"normalized": false,
|
| 157 |
-
"special":
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 100273,
|
|
@@ -163,7 +163,7 @@
|
|
| 163 |
"lstrip": false,
|
| 164 |
"rstrip": false,
|
| 165 |
"normalized": false,
|
| 166 |
-
"special":
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 100274,
|
|
@@ -172,7 +172,7 @@
|
|
| 172 |
"lstrip": false,
|
| 173 |
"rstrip": false,
|
| 174 |
"normalized": false,
|
| 175 |
-
"special":
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 100275,
|
|
@@ -181,7 +181,7 @@
|
|
| 181 |
"lstrip": false,
|
| 182 |
"rstrip": false,
|
| 183 |
"normalized": false,
|
| 184 |
-
"special":
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 100276,
|
|
@@ -200521,4 +200521,4 @@
|
|
| 200521 |
"ĠCon veyor"
|
| 200522 |
]
|
| 200523 |
}
|
| 200524 |
-
}
|
|
|
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
+
"special": false
|
| 14 |
},
|
| 15 |
{
|
| 16 |
"id": 100257,
|
|
|
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
"normalized": false,
|
| 58 |
+
"special": false
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 100262,
|
|
|
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
"normalized": false,
|
| 67 |
+
"special": false
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 100263,
|
|
|
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
| 75 |
"normalized": false,
|
| 76 |
+
"special": false
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 100264,
|
|
|
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
| 102 |
"normalized": false,
|
| 103 |
+
"special": false
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 100267,
|
|
|
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
| 111 |
"normalized": false,
|
| 112 |
+
"special": false
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 100268,
|
|
|
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
| 120 |
"normalized": false,
|
| 121 |
+
"special": false
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 100269,
|
|
|
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
| 129 |
"normalized": false,
|
| 130 |
+
"special": false
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 100270,
|
|
|
|
| 136 |
"lstrip": false,
|
| 137 |
"rstrip": false,
|
| 138 |
"normalized": false,
|
| 139 |
+
"special": false
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 100271,
|
|
|
|
| 145 |
"lstrip": false,
|
| 146 |
"rstrip": false,
|
| 147 |
"normalized": false,
|
| 148 |
+
"special": false
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 100272,
|
|
|
|
| 154 |
"lstrip": false,
|
| 155 |
"rstrip": false,
|
| 156 |
"normalized": false,
|
| 157 |
+
"special": false
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 100273,
|
|
|
|
| 163 |
"lstrip": false,
|
| 164 |
"rstrip": false,
|
| 165 |
"normalized": false,
|
| 166 |
+
"special": false
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 100274,
|
|
|
|
| 172 |
"lstrip": false,
|
| 173 |
"rstrip": false,
|
| 174 |
"normalized": false,
|
| 175 |
+
"special": false
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 100275,
|
|
|
|
| 181 |
"lstrip": false,
|
| 182 |
"rstrip": false,
|
| 183 |
"normalized": false,
|
| 184 |
+
"special": false
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 100276,
|
|
|
|
| 200521 |
"ĠCon veyor"
|
| 200522 |
]
|
| 200523 |
}
|
| 200524 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"normalized": false,
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
-
"special":
|
| 11 |
},
|
| 12 |
"100257": {
|
| 13 |
"content": "<|endoftext|>",
|
|
@@ -47,7 +47,7 @@
|
|
| 47 |
"normalized": false,
|
| 48 |
"rstrip": false,
|
| 49 |
"single_word": false,
|
| 50 |
-
"special":
|
| 51 |
},
|
| 52 |
"100262": {
|
| 53 |
"content": "|||EMAIL_ADDRESS|||",
|
|
@@ -55,7 +55,7 @@
|
|
| 55 |
"normalized": false,
|
| 56 |
"rstrip": false,
|
| 57 |
"single_word": false,
|
| 58 |
-
"special":
|
| 59 |
},
|
| 60 |
"100263": {
|
| 61 |
"content": "|||IP_ADDRESS|||",
|
|
@@ -63,7 +63,7 @@
|
|
| 63 |
"normalized": false,
|
| 64 |
"rstrip": false,
|
| 65 |
"single_word": false,
|
| 66 |
-
"special":
|
| 67 |
},
|
| 68 |
"100264": {
|
| 69 |
"content": "<|im_start|>",
|
|
@@ -87,7 +87,7 @@
|
|
| 87 |
"normalized": false,
|
| 88 |
"rstrip": false,
|
| 89 |
"single_word": false,
|
| 90 |
-
"special":
|
| 91 |
},
|
| 92 |
"100267": {
|
| 93 |
"content": "<|extra_id_2|>",
|
|
@@ -95,7 +95,7 @@
|
|
| 95 |
"normalized": false,
|
| 96 |
"rstrip": false,
|
| 97 |
"single_word": false,
|
| 98 |
-
"special":
|
| 99 |
},
|
| 100 |
"100268": {
|
| 101 |
"content": "<|extra_id_3|>",
|
|
@@ -103,7 +103,7 @@
|
|
| 103 |
"normalized": false,
|
| 104 |
"rstrip": false,
|
| 105 |
"single_word": false,
|
| 106 |
-
"special":
|
| 107 |
},
|
| 108 |
"100269": {
|
| 109 |
"content": "<|extra_id_4|>",
|
|
@@ -111,7 +111,7 @@
|
|
| 111 |
"normalized": false,
|
| 112 |
"rstrip": false,
|
| 113 |
"single_word": false,
|
| 114 |
-
"special":
|
| 115 |
},
|
| 116 |
"100270": {
|
| 117 |
"content": "<|extra_id_5|>",
|
|
@@ -119,7 +119,7 @@
|
|
| 119 |
"normalized": false,
|
| 120 |
"rstrip": false,
|
| 121 |
"single_word": false,
|
| 122 |
-
"special":
|
| 123 |
},
|
| 124 |
"100271": {
|
| 125 |
"content": "<|extra_id_6|>",
|
|
@@ -127,7 +127,7 @@
|
|
| 127 |
"normalized": false,
|
| 128 |
"rstrip": false,
|
| 129 |
"single_word": false,
|
| 130 |
-
"special":
|
| 131 |
},
|
| 132 |
"100272": {
|
| 133 |
"content": "<|extra_id_7|>",
|
|
@@ -135,7 +135,7 @@
|
|
| 135 |
"normalized": false,
|
| 136 |
"rstrip": false,
|
| 137 |
"single_word": false,
|
| 138 |
-
"special":
|
| 139 |
},
|
| 140 |
"100273": {
|
| 141 |
"content": "<|extra_id_8|>",
|
|
@@ -143,7 +143,7 @@
|
|
| 143 |
"normalized": false,
|
| 144 |
"rstrip": false,
|
| 145 |
"single_word": false,
|
| 146 |
-
"special":
|
| 147 |
},
|
| 148 |
"100274": {
|
| 149 |
"content": "<|extra_id_9|>",
|
|
@@ -151,7 +151,7 @@
|
|
| 151 |
"normalized": false,
|
| 152 |
"rstrip": false,
|
| 153 |
"single_word": false,
|
| 154 |
-
"special":
|
| 155 |
},
|
| 156 |
"100275": {
|
| 157 |
"content": "<|extra_id_10|>",
|
|
@@ -159,7 +159,7 @@
|
|
| 159 |
"normalized": false,
|
| 160 |
"rstrip": false,
|
| 161 |
"single_word": false,
|
| 162 |
-
"special":
|
| 163 |
},
|
| 164 |
"100276": {
|
| 165 |
"content": "<|endofprompt|>",
|
|
|
|
| 7 |
"normalized": false,
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
+
"special": false
|
| 11 |
},
|
| 12 |
"100257": {
|
| 13 |
"content": "<|endoftext|>",
|
|
|
|
| 47 |
"normalized": false,
|
| 48 |
"rstrip": false,
|
| 49 |
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
},
|
| 52 |
"100262": {
|
| 53 |
"content": "|||EMAIL_ADDRESS|||",
|
|
|
|
| 55 |
"normalized": false,
|
| 56 |
"rstrip": false,
|
| 57 |
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
},
|
| 60 |
"100263": {
|
| 61 |
"content": "|||IP_ADDRESS|||",
|
|
|
|
| 63 |
"normalized": false,
|
| 64 |
"rstrip": false,
|
| 65 |
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
},
|
| 68 |
"100264": {
|
| 69 |
"content": "<|im_start|>",
|
|
|
|
| 87 |
"normalized": false,
|
| 88 |
"rstrip": false,
|
| 89 |
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
},
|
| 92 |
"100267": {
|
| 93 |
"content": "<|extra_id_2|>",
|
|
|
|
| 95 |
"normalized": false,
|
| 96 |
"rstrip": false,
|
| 97 |
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
},
|
| 100 |
"100268": {
|
| 101 |
"content": "<|extra_id_3|>",
|
|
|
|
| 103 |
"normalized": false,
|
| 104 |
"rstrip": false,
|
| 105 |
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
},
|
| 108 |
"100269": {
|
| 109 |
"content": "<|extra_id_4|>",
|
|
|
|
| 111 |
"normalized": false,
|
| 112 |
"rstrip": false,
|
| 113 |
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
},
|
| 116 |
"100270": {
|
| 117 |
"content": "<|extra_id_5|>",
|
|
|
|
| 119 |
"normalized": false,
|
| 120 |
"rstrip": false,
|
| 121 |
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
},
|
| 124 |
"100271": {
|
| 125 |
"content": "<|extra_id_6|>",
|
|
|
|
| 127 |
"normalized": false,
|
| 128 |
"rstrip": false,
|
| 129 |
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
},
|
| 132 |
"100272": {
|
| 133 |
"content": "<|extra_id_7|>",
|
|
|
|
| 135 |
"normalized": false,
|
| 136 |
"rstrip": false,
|
| 137 |
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
},
|
| 140 |
"100273": {
|
| 141 |
"content": "<|extra_id_8|>",
|
|
|
|
| 143 |
"normalized": false,
|
| 144 |
"rstrip": false,
|
| 145 |
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
},
|
| 148 |
"100274": {
|
| 149 |
"content": "<|extra_id_9|>",
|
|
|
|
| 151 |
"normalized": false,
|
| 152 |
"rstrip": false,
|
| 153 |
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
},
|
| 156 |
"100275": {
|
| 157 |
"content": "<|extra_id_10|>",
|
|
|
|
| 159 |
"normalized": false,
|
| 160 |
"rstrip": false,
|
| 161 |
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
},
|
| 164 |
"100276": {
|
| 165 |
"content": "<|endofprompt|>",
|