Upload tokenizer
Browse files- special_tokens_map.json +3 -3
- tokenizer.json +0 -0
- tokenizer_config.json +22 -74
special_tokens_map.json
CHANGED
|
@@ -1,20 +1,20 @@
|
|
| 1 |
{
|
| 2 |
"eos_token": {
|
| 3 |
-
"content": "<|
|
| 4 |
"lstrip": false,
|
| 5 |
"normalized": false,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"pad_token": {
|
| 10 |
-
"content": "<|
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"unk_token": {
|
| 17 |
-
"content": "<|
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
"eos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
"lstrip": false,
|
| 5 |
"normalized": false,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"pad_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"unk_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,38 +1,32 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
-
"
|
| 4 |
-
"content": "<|
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"32001": {
|
| 12 |
-
"content": "<|im_end|>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
-
"content": "<|
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
-
"
|
| 28 |
-
"content": "<|
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
-
"
|
| 36 |
"content": "<tool_call>",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
|
@@ -40,7 +34,7 @@
|
|
| 40 |
"single_word": false,
|
| 41 |
"special": false
|
| 42 |
},
|
| 43 |
-
"
|
| 44 |
"content": "</tool_call>",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
|
@@ -48,7 +42,7 @@
|
|
| 48 |
"single_word": false,
|
| 49 |
"special": false
|
| 50 |
},
|
| 51 |
-
"
|
| 52 |
"content": "<think>",
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": false,
|
|
@@ -56,7 +50,7 @@
|
|
| 56 |
"single_word": false,
|
| 57 |
"special": false
|
| 58 |
},
|
| 59 |
-
"
|
| 60 |
"content": "</think>",
|
| 61 |
"lstrip": false,
|
| 62 |
"normalized": false,
|
|
@@ -64,7 +58,7 @@
|
|
| 64 |
"single_word": false,
|
| 65 |
"special": false
|
| 66 |
},
|
| 67 |
-
"
|
| 68 |
"content": "<|unused_special_token_0|>",
|
| 69 |
"lstrip": false,
|
| 70 |
"normalized": false,
|
|
@@ -72,7 +66,7 @@
|
|
| 72 |
"single_word": false,
|
| 73 |
"special": true
|
| 74 |
},
|
| 75 |
-
"
|
| 76 |
"content": "<|unused_special_token_1|>",
|
| 77 |
"lstrip": false,
|
| 78 |
"normalized": false,
|
|
@@ -80,7 +74,7 @@
|
|
| 80 |
"single_word": false,
|
| 81 |
"special": true
|
| 82 |
},
|
| 83 |
-
"
|
| 84 |
"content": "<|unused_special_token_2|>",
|
| 85 |
"lstrip": false,
|
| 86 |
"normalized": false,
|
|
@@ -88,68 +82,22 @@
|
|
| 88 |
"single_word": false,
|
| 89 |
"special": true
|
| 90 |
},
|
| 91 |
-
"
|
| 92 |
"content": "<|unused_special_token_3|>",
|
| 93 |
"lstrip": false,
|
| 94 |
"normalized": false,
|
| 95 |
"rstrip": false,
|
| 96 |
"single_word": false,
|
| 97 |
"special": true
|
| 98 |
-
},
|
| 99 |
-
"32012": {
|
| 100 |
-
"content": "<|unused_special_token_4|>",
|
| 101 |
-
"lstrip": false,
|
| 102 |
-
"normalized": false,
|
| 103 |
-
"rstrip": false,
|
| 104 |
-
"single_word": false,
|
| 105 |
-
"special": true
|
| 106 |
-
},
|
| 107 |
-
"32013": {
|
| 108 |
-
"content": "<|unused_special_token_5|>",
|
| 109 |
-
"lstrip": false,
|
| 110 |
-
"normalized": false,
|
| 111 |
-
"rstrip": false,
|
| 112 |
-
"single_word": false,
|
| 113 |
-
"special": true
|
| 114 |
-
},
|
| 115 |
-
"32014": {
|
| 116 |
-
"content": "<|unused_special_token_6|>",
|
| 117 |
-
"lstrip": false,
|
| 118 |
-
"normalized": false,
|
| 119 |
-
"rstrip": false,
|
| 120 |
-
"single_word": false,
|
| 121 |
-
"special": true
|
| 122 |
-
},
|
| 123 |
-
"32015": {
|
| 124 |
-
"content": "<|unused_special_token_7|>",
|
| 125 |
-
"lstrip": false,
|
| 126 |
-
"normalized": false,
|
| 127 |
-
"rstrip": false,
|
| 128 |
-
"single_word": false,
|
| 129 |
-
"special": true
|
| 130 |
-
},
|
| 131 |
-
"32016": {
|
| 132 |
-
"content": "<|unused_special_token_8|>",
|
| 133 |
-
"lstrip": false,
|
| 134 |
-
"normalized": false,
|
| 135 |
-
"rstrip": false,
|
| 136 |
-
"single_word": false,
|
| 137 |
-
"special": true
|
| 138 |
-
},
|
| 139 |
-
"32017": {
|
| 140 |
-
"content": "<|unused_special_token_9|>",
|
| 141 |
-
"lstrip": false,
|
| 142 |
-
"normalized": false,
|
| 143 |
-
"rstrip": false,
|
| 144 |
-
"single_word": false,
|
| 145 |
-
"special": true
|
| 146 |
}
|
| 147 |
},
|
|
|
|
| 148 |
"clean_up_tokenization_spaces": false,
|
| 149 |
-
"eos_token": "<|
|
| 150 |
"extra_special_tokens": {},
|
| 151 |
"model_max_length": 2048,
|
| 152 |
-
"pad_token": "<|
|
| 153 |
-
"
|
| 154 |
-
"
|
|
|
|
| 155 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"lstrip": false,
|
| 8 |
"normalized": false,
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false,
|
| 11 |
"special": true
|
| 12 |
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
"lstrip": false,
|
| 16 |
"normalized": false,
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false,
|
| 19 |
"special": true
|
| 20 |
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
"lstrip": false,
|
| 24 |
"normalized": false,
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
},
|
| 29 |
+
"31992": {
|
| 30 |
"content": "<tool_call>",
|
| 31 |
"lstrip": false,
|
| 32 |
"normalized": false,
|
|
|
|
| 34 |
"single_word": false,
|
| 35 |
"special": false
|
| 36 |
},
|
| 37 |
+
"31993": {
|
| 38 |
"content": "</tool_call>",
|
| 39 |
"lstrip": false,
|
| 40 |
"normalized": false,
|
|
|
|
| 42 |
"single_word": false,
|
| 43 |
"special": false
|
| 44 |
},
|
| 45 |
+
"31994": {
|
| 46 |
"content": "<think>",
|
| 47 |
"lstrip": false,
|
| 48 |
"normalized": false,
|
|
|
|
| 50 |
"single_word": false,
|
| 51 |
"special": false
|
| 52 |
},
|
| 53 |
+
"31995": {
|
| 54 |
"content": "</think>",
|
| 55 |
"lstrip": false,
|
| 56 |
"normalized": false,
|
|
|
|
| 58 |
"single_word": false,
|
| 59 |
"special": false
|
| 60 |
},
|
| 61 |
+
"31996": {
|
| 62 |
"content": "<|unused_special_token_0|>",
|
| 63 |
"lstrip": false,
|
| 64 |
"normalized": false,
|
|
|
|
| 66 |
"single_word": false,
|
| 67 |
"special": true
|
| 68 |
},
|
| 69 |
+
"31997": {
|
| 70 |
"content": "<|unused_special_token_1|>",
|
| 71 |
"lstrip": false,
|
| 72 |
"normalized": false,
|
|
|
|
| 74 |
"single_word": false,
|
| 75 |
"special": true
|
| 76 |
},
|
| 77 |
+
"31998": {
|
| 78 |
"content": "<|unused_special_token_2|>",
|
| 79 |
"lstrip": false,
|
| 80 |
"normalized": false,
|
|
|
|
| 82 |
"single_word": false,
|
| 83 |
"special": true
|
| 84 |
},
|
| 85 |
+
"31999": {
|
| 86 |
"content": "<|unused_special_token_3|>",
|
| 87 |
"lstrip": false,
|
| 88 |
"normalized": false,
|
| 89 |
"rstrip": false,
|
| 90 |
"single_word": false,
|
| 91 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
}
|
| 93 |
},
|
| 94 |
+
"bos_token": null,
|
| 95 |
"clean_up_tokenization_spaces": false,
|
| 96 |
+
"eos_token": "<|endoftext|>",
|
| 97 |
"extra_special_tokens": {},
|
| 98 |
"model_max_length": 2048,
|
| 99 |
+
"pad_token": "<|endoftext|>",
|
| 100 |
+
"split_special_tokens": false,
|
| 101 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 102 |
+
"unk_token": "<|endoftext|>"
|
| 103 |
}
|