Upload tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +30 -0
- tokenizer_config.json +795 -0
- vocab.json +0 -0
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": true,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": true,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|im_end|>",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": true,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|dummy_87|>",
|
| 18 |
+
"lstrip": true,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": true,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "�",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,795 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"5809": {
|
| 6 |
+
"content": "�",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"100256": {
|
| 14 |
+
"content": "<|dummy_0|>",
|
| 15 |
+
"lstrip": true,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": true,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"100257": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
+
"lstrip": true,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": true,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"100258": {
|
| 30 |
+
"content": "<|fim_prefix|>",
|
| 31 |
+
"lstrip": true,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": true,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"100259": {
|
| 38 |
+
"content": "<|fim_middle|>",
|
| 39 |
+
"lstrip": true,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": true,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"100260": {
|
| 46 |
+
"content": "<|fim_suffix|>",
|
| 47 |
+
"lstrip": true,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": true,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"100261": {
|
| 54 |
+
"content": "<|dummy_1|>",
|
| 55 |
+
"lstrip": true,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": true,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"100262": {
|
| 62 |
+
"content": "<|dummy_2|>",
|
| 63 |
+
"lstrip": true,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": true,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"100263": {
|
| 70 |
+
"content": "<|dummy_3|>",
|
| 71 |
+
"lstrip": true,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": true,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"100264": {
|
| 78 |
+
"content": "<|im_start|>",
|
| 79 |
+
"lstrip": true,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": true,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"100265": {
|
| 86 |
+
"content": "<|im_end|>",
|
| 87 |
+
"lstrip": true,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": true,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"100266": {
|
| 94 |
+
"content": "<|im_sep|>",
|
| 95 |
+
"lstrip": true,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": true,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"100267": {
|
| 102 |
+
"content": "<|dummy_4|>",
|
| 103 |
+
"lstrip": true,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": true,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"100268": {
|
| 110 |
+
"content": "<|dummy_5|>",
|
| 111 |
+
"lstrip": true,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": true,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"100269": {
|
| 118 |
+
"content": "<|dummy_6|>",
|
| 119 |
+
"lstrip": true,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": true,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"100270": {
|
| 126 |
+
"content": "<|dummy_7|>",
|
| 127 |
+
"lstrip": true,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": true,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": true
|
| 132 |
+
},
|
| 133 |
+
"100271": {
|
| 134 |
+
"content": "<|dummy_8|>",
|
| 135 |
+
"lstrip": true,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": true,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
"100272": {
|
| 142 |
+
"content": "<|dummy_9|>",
|
| 143 |
+
"lstrip": true,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": true,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": true
|
| 148 |
+
},
|
| 149 |
+
"100273": {
|
| 150 |
+
"content": "<|dummy_10|>",
|
| 151 |
+
"lstrip": true,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": true,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": true
|
| 156 |
+
},
|
| 157 |
+
"100274": {
|
| 158 |
+
"content": "<|dummy_11|>",
|
| 159 |
+
"lstrip": true,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": true,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": true
|
| 164 |
+
},
|
| 165 |
+
"100275": {
|
| 166 |
+
"content": "<|dummy_12|>",
|
| 167 |
+
"lstrip": true,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": true,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
"100276": {
|
| 174 |
+
"content": "<|endofprompt|>",
|
| 175 |
+
"lstrip": true,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": true,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
},
|
| 181 |
+
"100277": {
|
| 182 |
+
"content": "<|dummy_13|>",
|
| 183 |
+
"lstrip": true,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": true,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"100278": {
|
| 190 |
+
"content": "<|dummy_14|>",
|
| 191 |
+
"lstrip": true,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": true,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"100279": {
|
| 198 |
+
"content": "<|dummy_15|>",
|
| 199 |
+
"lstrip": true,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": true,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"100280": {
|
| 206 |
+
"content": "<|dummy_16|>",
|
| 207 |
+
"lstrip": true,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": true,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
"100281": {
|
| 214 |
+
"content": "<|dummy_17|>",
|
| 215 |
+
"lstrip": true,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": true,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"100282": {
|
| 222 |
+
"content": "<|dummy_18|>",
|
| 223 |
+
"lstrip": true,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": true,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"100283": {
|
| 230 |
+
"content": "<|dummy_19|>",
|
| 231 |
+
"lstrip": true,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": true,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"100284": {
|
| 238 |
+
"content": "<|dummy_20|>",
|
| 239 |
+
"lstrip": true,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": true,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"100285": {
|
| 246 |
+
"content": "<|dummy_21|>",
|
| 247 |
+
"lstrip": true,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": true,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
},
|
| 253 |
+
"100286": {
|
| 254 |
+
"content": "<|dummy_22|>",
|
| 255 |
+
"lstrip": true,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": true,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": true
|
| 260 |
+
},
|
| 261 |
+
"100287": {
|
| 262 |
+
"content": "<|dummy_23|>",
|
| 263 |
+
"lstrip": true,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": true,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": true
|
| 268 |
+
},
|
| 269 |
+
"100288": {
|
| 270 |
+
"content": "<|dummy_24|>",
|
| 271 |
+
"lstrip": true,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": true,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": true
|
| 276 |
+
},
|
| 277 |
+
"100289": {
|
| 278 |
+
"content": "<|dummy_25|>",
|
| 279 |
+
"lstrip": true,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": true,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
"100290": {
|
| 286 |
+
"content": "<|dummy_26|>",
|
| 287 |
+
"lstrip": true,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": true,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": true
|
| 292 |
+
},
|
| 293 |
+
"100291": {
|
| 294 |
+
"content": "<|dummy_27|>",
|
| 295 |
+
"lstrip": true,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": true,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": true
|
| 300 |
+
},
|
| 301 |
+
"100292": {
|
| 302 |
+
"content": "<|dummy_28|>",
|
| 303 |
+
"lstrip": true,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": true,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": true
|
| 308 |
+
},
|
| 309 |
+
"100293": {
|
| 310 |
+
"content": "<|dummy_29|>",
|
| 311 |
+
"lstrip": true,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": true,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": true
|
| 316 |
+
},
|
| 317 |
+
"100294": {
|
| 318 |
+
"content": "<|dummy_30|>",
|
| 319 |
+
"lstrip": true,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": true,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": true
|
| 324 |
+
},
|
| 325 |
+
"100295": {
|
| 326 |
+
"content": "<|dummy_31|>",
|
| 327 |
+
"lstrip": true,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": true,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": true
|
| 332 |
+
},
|
| 333 |
+
"100296": {
|
| 334 |
+
"content": "<|dummy_32|>",
|
| 335 |
+
"lstrip": true,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"rstrip": true,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": true
|
| 340 |
+
},
|
| 341 |
+
"100297": {
|
| 342 |
+
"content": "<|dummy_33|>",
|
| 343 |
+
"lstrip": true,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"rstrip": true,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": true
|
| 348 |
+
},
|
| 349 |
+
"100298": {
|
| 350 |
+
"content": "<|dummy_34|>",
|
| 351 |
+
"lstrip": true,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": true,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": true
|
| 356 |
+
},
|
| 357 |
+
"100299": {
|
| 358 |
+
"content": "<|dummy_35|>",
|
| 359 |
+
"lstrip": true,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": true,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": true
|
| 364 |
+
},
|
| 365 |
+
"100300": {
|
| 366 |
+
"content": "<|dummy_36|>",
|
| 367 |
+
"lstrip": true,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": true,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": true
|
| 372 |
+
},
|
| 373 |
+
"100301": {
|
| 374 |
+
"content": "<|dummy_37|>",
|
| 375 |
+
"lstrip": true,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": true,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": true
|
| 380 |
+
},
|
| 381 |
+
"100302": {
|
| 382 |
+
"content": "<|dummy_38|>",
|
| 383 |
+
"lstrip": true,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": true,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": true
|
| 388 |
+
},
|
| 389 |
+
"100303": {
|
| 390 |
+
"content": "<|dummy_39|>",
|
| 391 |
+
"lstrip": true,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": true,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": true
|
| 396 |
+
},
|
| 397 |
+
"100304": {
|
| 398 |
+
"content": "<|dummy_40|>",
|
| 399 |
+
"lstrip": true,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": true,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": true
|
| 404 |
+
},
|
| 405 |
+
"100305": {
|
| 406 |
+
"content": "<|dummy_41|>",
|
| 407 |
+
"lstrip": true,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": true,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": true
|
| 412 |
+
},
|
| 413 |
+
"100306": {
|
| 414 |
+
"content": "<|dummy_42|>",
|
| 415 |
+
"lstrip": true,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": true,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": true
|
| 420 |
+
},
|
| 421 |
+
"100307": {
|
| 422 |
+
"content": "<|dummy_43|>",
|
| 423 |
+
"lstrip": true,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": true,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": true
|
| 428 |
+
},
|
| 429 |
+
"100308": {
|
| 430 |
+
"content": "<|dummy_44|>",
|
| 431 |
+
"lstrip": true,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": true,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": true
|
| 436 |
+
},
|
| 437 |
+
"100309": {
|
| 438 |
+
"content": "<|dummy_45|>",
|
| 439 |
+
"lstrip": true,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": true,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": true
|
| 444 |
+
},
|
| 445 |
+
"100310": {
|
| 446 |
+
"content": "<|dummy_46|>",
|
| 447 |
+
"lstrip": true,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": true,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": true
|
| 452 |
+
},
|
| 453 |
+
"100311": {
|
| 454 |
+
"content": "<|dummy_47|>",
|
| 455 |
+
"lstrip": true,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": true,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": true
|
| 460 |
+
},
|
| 461 |
+
"100312": {
|
| 462 |
+
"content": "<|dummy_48|>",
|
| 463 |
+
"lstrip": true,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": true,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": true
|
| 468 |
+
},
|
| 469 |
+
"100313": {
|
| 470 |
+
"content": "<|dummy_49|>",
|
| 471 |
+
"lstrip": true,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"rstrip": true,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": true
|
| 476 |
+
},
|
| 477 |
+
"100314": {
|
| 478 |
+
"content": "<|dummy_50|>",
|
| 479 |
+
"lstrip": true,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"rstrip": true,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": true
|
| 484 |
+
},
|
| 485 |
+
"100315": {
|
| 486 |
+
"content": "<|dummy_51|>",
|
| 487 |
+
"lstrip": true,
|
| 488 |
+
"normalized": false,
|
| 489 |
+
"rstrip": true,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": true
|
| 492 |
+
},
|
| 493 |
+
"100316": {
|
| 494 |
+
"content": "<|dummy_52|>",
|
| 495 |
+
"lstrip": true,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"rstrip": true,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": true
|
| 500 |
+
},
|
| 501 |
+
"100317": {
|
| 502 |
+
"content": "<|dummy_53|>",
|
| 503 |
+
"lstrip": true,
|
| 504 |
+
"normalized": false,
|
| 505 |
+
"rstrip": true,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": true
|
| 508 |
+
},
|
| 509 |
+
"100318": {
|
| 510 |
+
"content": "<|dummy_54|>",
|
| 511 |
+
"lstrip": true,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"rstrip": true,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": true
|
| 516 |
+
},
|
| 517 |
+
"100319": {
|
| 518 |
+
"content": "<|dummy_55|>",
|
| 519 |
+
"lstrip": true,
|
| 520 |
+
"normalized": false,
|
| 521 |
+
"rstrip": true,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": true
|
| 524 |
+
},
|
| 525 |
+
"100320": {
|
| 526 |
+
"content": "<|dummy_56|>",
|
| 527 |
+
"lstrip": true,
|
| 528 |
+
"normalized": false,
|
| 529 |
+
"rstrip": true,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": true
|
| 532 |
+
},
|
| 533 |
+
"100321": {
|
| 534 |
+
"content": "<|dummy_57|>",
|
| 535 |
+
"lstrip": true,
|
| 536 |
+
"normalized": false,
|
| 537 |
+
"rstrip": true,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": true
|
| 540 |
+
},
|
| 541 |
+
"100322": {
|
| 542 |
+
"content": "<|dummy_58|>",
|
| 543 |
+
"lstrip": true,
|
| 544 |
+
"normalized": false,
|
| 545 |
+
"rstrip": true,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": true
|
| 548 |
+
},
|
| 549 |
+
"100323": {
|
| 550 |
+
"content": "<|dummy_59|>",
|
| 551 |
+
"lstrip": true,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"rstrip": true,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": true
|
| 556 |
+
},
|
| 557 |
+
"100324": {
|
| 558 |
+
"content": "<|dummy_60|>",
|
| 559 |
+
"lstrip": true,
|
| 560 |
+
"normalized": false,
|
| 561 |
+
"rstrip": true,
|
| 562 |
+
"single_word": false,
|
| 563 |
+
"special": true
|
| 564 |
+
},
|
| 565 |
+
"100325": {
|
| 566 |
+
"content": "<|dummy_61|>",
|
| 567 |
+
"lstrip": true,
|
| 568 |
+
"normalized": false,
|
| 569 |
+
"rstrip": true,
|
| 570 |
+
"single_word": false,
|
| 571 |
+
"special": true
|
| 572 |
+
},
|
| 573 |
+
"100326": {
|
| 574 |
+
"content": "<|dummy_62|>",
|
| 575 |
+
"lstrip": true,
|
| 576 |
+
"normalized": false,
|
| 577 |
+
"rstrip": true,
|
| 578 |
+
"single_word": false,
|
| 579 |
+
"special": true
|
| 580 |
+
},
|
| 581 |
+
"100327": {
|
| 582 |
+
"content": "<|dummy_63|>",
|
| 583 |
+
"lstrip": true,
|
| 584 |
+
"normalized": false,
|
| 585 |
+
"rstrip": true,
|
| 586 |
+
"single_word": false,
|
| 587 |
+
"special": true
|
| 588 |
+
},
|
| 589 |
+
"100328": {
|
| 590 |
+
"content": "<|dummy_64|>",
|
| 591 |
+
"lstrip": true,
|
| 592 |
+
"normalized": false,
|
| 593 |
+
"rstrip": true,
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"special": true
|
| 596 |
+
},
|
| 597 |
+
"100329": {
|
| 598 |
+
"content": "<|dummy_65|>",
|
| 599 |
+
"lstrip": true,
|
| 600 |
+
"normalized": false,
|
| 601 |
+
"rstrip": true,
|
| 602 |
+
"single_word": false,
|
| 603 |
+
"special": true
|
| 604 |
+
},
|
| 605 |
+
"100330": {
|
| 606 |
+
"content": "<|dummy_66|>",
|
| 607 |
+
"lstrip": true,
|
| 608 |
+
"normalized": false,
|
| 609 |
+
"rstrip": true,
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"special": true
|
| 612 |
+
},
|
| 613 |
+
"100331": {
|
| 614 |
+
"content": "<|dummy_67|>",
|
| 615 |
+
"lstrip": true,
|
| 616 |
+
"normalized": false,
|
| 617 |
+
"rstrip": true,
|
| 618 |
+
"single_word": false,
|
| 619 |
+
"special": true
|
| 620 |
+
},
|
| 621 |
+
"100332": {
|
| 622 |
+
"content": "<|dummy_68|>",
|
| 623 |
+
"lstrip": true,
|
| 624 |
+
"normalized": false,
|
| 625 |
+
"rstrip": true,
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"special": true
|
| 628 |
+
},
|
| 629 |
+
"100333": {
|
| 630 |
+
"content": "<|dummy_69|>",
|
| 631 |
+
"lstrip": true,
|
| 632 |
+
"normalized": false,
|
| 633 |
+
"rstrip": true,
|
| 634 |
+
"single_word": false,
|
| 635 |
+
"special": true
|
| 636 |
+
},
|
| 637 |
+
"100334": {
|
| 638 |
+
"content": "<|dummy_70|>",
|
| 639 |
+
"lstrip": true,
|
| 640 |
+
"normalized": false,
|
| 641 |
+
"rstrip": true,
|
| 642 |
+
"single_word": false,
|
| 643 |
+
"special": true
|
| 644 |
+
},
|
| 645 |
+
"100335": {
|
| 646 |
+
"content": "<|dummy_71|>",
|
| 647 |
+
"lstrip": true,
|
| 648 |
+
"normalized": false,
|
| 649 |
+
"rstrip": true,
|
| 650 |
+
"single_word": false,
|
| 651 |
+
"special": true
|
| 652 |
+
},
|
| 653 |
+
"100336": {
|
| 654 |
+
"content": "<|dummy_72|>",
|
| 655 |
+
"lstrip": true,
|
| 656 |
+
"normalized": false,
|
| 657 |
+
"rstrip": true,
|
| 658 |
+
"single_word": false,
|
| 659 |
+
"special": true
|
| 660 |
+
},
|
| 661 |
+
"100337": {
|
| 662 |
+
"content": "<|dummy_73|>",
|
| 663 |
+
"lstrip": true,
|
| 664 |
+
"normalized": false,
|
| 665 |
+
"rstrip": true,
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"special": true
|
| 668 |
+
},
|
| 669 |
+
"100338": {
|
| 670 |
+
"content": "<|dummy_74|>",
|
| 671 |
+
"lstrip": true,
|
| 672 |
+
"normalized": false,
|
| 673 |
+
"rstrip": true,
|
| 674 |
+
"single_word": false,
|
| 675 |
+
"special": true
|
| 676 |
+
},
|
| 677 |
+
"100339": {
|
| 678 |
+
"content": "<|dummy_75|>",
|
| 679 |
+
"lstrip": true,
|
| 680 |
+
"normalized": false,
|
| 681 |
+
"rstrip": true,
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"special": true
|
| 684 |
+
},
|
| 685 |
+
"100340": {
|
| 686 |
+
"content": "<|dummy_76|>",
|
| 687 |
+
"lstrip": true,
|
| 688 |
+
"normalized": false,
|
| 689 |
+
"rstrip": true,
|
| 690 |
+
"single_word": false,
|
| 691 |
+
"special": true
|
| 692 |
+
},
|
| 693 |
+
"100341": {
|
| 694 |
+
"content": "<|dummy_77|>",
|
| 695 |
+
"lstrip": true,
|
| 696 |
+
"normalized": false,
|
| 697 |
+
"rstrip": true,
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"special": true
|
| 700 |
+
},
|
| 701 |
+
"100342": {
|
| 702 |
+
"content": "<|dummy_78|>",
|
| 703 |
+
"lstrip": true,
|
| 704 |
+
"normalized": false,
|
| 705 |
+
"rstrip": true,
|
| 706 |
+
"single_word": false,
|
| 707 |
+
"special": true
|
| 708 |
+
},
|
| 709 |
+
"100343": {
|
| 710 |
+
"content": "<|dummy_79|>",
|
| 711 |
+
"lstrip": true,
|
| 712 |
+
"normalized": false,
|
| 713 |
+
"rstrip": true,
|
| 714 |
+
"single_word": false,
|
| 715 |
+
"special": true
|
| 716 |
+
},
|
| 717 |
+
"100344": {
|
| 718 |
+
"content": "<|dummy_80|>",
|
| 719 |
+
"lstrip": true,
|
| 720 |
+
"normalized": false,
|
| 721 |
+
"rstrip": true,
|
| 722 |
+
"single_word": false,
|
| 723 |
+
"special": true
|
| 724 |
+
},
|
| 725 |
+
"100345": {
|
| 726 |
+
"content": "<|dummy_81|>",
|
| 727 |
+
"lstrip": true,
|
| 728 |
+
"normalized": false,
|
| 729 |
+
"rstrip": true,
|
| 730 |
+
"single_word": false,
|
| 731 |
+
"special": true
|
| 732 |
+
},
|
| 733 |
+
"100346": {
|
| 734 |
+
"content": "<|dummy_82|>",
|
| 735 |
+
"lstrip": true,
|
| 736 |
+
"normalized": false,
|
| 737 |
+
"rstrip": true,
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"special": true
|
| 740 |
+
},
|
| 741 |
+
"100347": {
|
| 742 |
+
"content": "<|dummy_83|>",
|
| 743 |
+
"lstrip": true,
|
| 744 |
+
"normalized": false,
|
| 745 |
+
"rstrip": true,
|
| 746 |
+
"single_word": false,
|
| 747 |
+
"special": true
|
| 748 |
+
},
|
| 749 |
+
"100348": {
|
| 750 |
+
"content": "<|dummy_84|>",
|
| 751 |
+
"lstrip": true,
|
| 752 |
+
"normalized": false,
|
| 753 |
+
"rstrip": true,
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"special": true
|
| 756 |
+
},
|
| 757 |
+
"100349": {
|
| 758 |
+
"content": "<|dummy_85|>",
|
| 759 |
+
"lstrip": true,
|
| 760 |
+
"normalized": false,
|
| 761 |
+
"rstrip": true,
|
| 762 |
+
"single_word": false,
|
| 763 |
+
"special": true
|
| 764 |
+
},
|
| 765 |
+
"100350": {
|
| 766 |
+
"content": "<|dummy_86|>",
|
| 767 |
+
"lstrip": true,
|
| 768 |
+
"normalized": false,
|
| 769 |
+
"rstrip": true,
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"special": true
|
| 772 |
+
},
|
| 773 |
+
"100351": {
|
| 774 |
+
"content": "<|dummy_87|>",
|
| 775 |
+
"lstrip": true,
|
| 776 |
+
"normalized": false,
|
| 777 |
+
"rstrip": true,
|
| 778 |
+
"single_word": false,
|
| 779 |
+
"special": true
|
| 780 |
+
}
|
| 781 |
+
},
|
| 782 |
+
"bos_token": "<|endoftext|>",
|
| 783 |
+
"chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
|
| 784 |
+
"clean_up_tokenization_spaces": false,
|
| 785 |
+
"eos_token": "<|im_end|>",
|
| 786 |
+
"errors": "replace",
|
| 787 |
+
"extra_special_tokens": {},
|
| 788 |
+
"from_slow": true,
|
| 789 |
+
"legacy": false,
|
| 790 |
+
"model_max_length": 16384,
|
| 791 |
+
"pad_token": "<|dummy_87|>",
|
| 792 |
+
"padding_side": "left",
|
| 793 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 794 |
+
"unk_token": "�"
|
| 795 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|