Added tool tokens (from original repository) (#2)
Browse files- Added tool tokens (from original repository) (8dfe4029a837116eb6bcc007ac112afa78bc3586)
Co-authored-by: Weird ass rabbit <[email protected]>
- tokenizer_config.json +48 -8
tokenizer_config.json
CHANGED
|
@@ -72,6 +72,46 @@
|
|
| 72 |
"single_word": false,
|
| 73 |
"special": true
|
| 74 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
"163601": {
|
| 76 |
"content": "<|im_middle|>",
|
| 77 |
"lstrip": false,
|
|
@@ -107,12 +147,6 @@
|
|
| 107 |
"<|im_system|>",
|
| 108 |
"<|im_middle|>"
|
| 109 |
],
|
| 110 |
-
"auto_map": {
|
| 111 |
-
"AutoTokenizer": [
|
| 112 |
-
"tokenization_kimi.TikTokenTokenizer",
|
| 113 |
-
null
|
| 114 |
-
]
|
| 115 |
-
},
|
| 116 |
"bos_token": "[BOS]",
|
| 117 |
"clean_up_tokenization_spaces": false,
|
| 118 |
"eos_token": "[EOS]",
|
|
@@ -120,5 +154,11 @@
|
|
| 120 |
"model_max_length": 1000000000000000019884624838656,
|
| 121 |
"pad_token": "[PAD]",
|
| 122 |
"tokenizer_class": "TikTokenTokenizer",
|
| 123 |
-
"unk_token": "[UNK]"
|
| 124 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
"single_word": false,
|
| 73 |
"special": true
|
| 74 |
},
|
| 75 |
+
"163595": {
|
| 76 |
+
"content": "<|tool_calls_section_begin|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"163596": {
|
| 84 |
+
"content": "<|tool_calls_section_end|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"163597": {
|
| 92 |
+
"content": "<|tool_call_begin|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"163598": {
|
| 100 |
+
"content": "<|tool_call_argument_begin|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"163599": {
|
| 108 |
+
"content": "<|tool_call_end|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
"163601": {
|
| 116 |
"content": "<|im_middle|>",
|
| 117 |
"lstrip": false,
|
|
|
|
| 147 |
"<|im_system|>",
|
| 148 |
"<|im_middle|>"
|
| 149 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 150 |
"bos_token": "[BOS]",
|
| 151 |
"clean_up_tokenization_spaces": false,
|
| 152 |
"eos_token": "[EOS]",
|
|
|
|
| 154 |
"model_max_length": 1000000000000000019884624838656,
|
| 155 |
"pad_token": "[PAD]",
|
| 156 |
"tokenizer_class": "TikTokenTokenizer",
|
| 157 |
+
"unk_token": "[UNK]",
|
| 158 |
+
"auto_map": {
|
| 159 |
+
"AutoTokenizer": [
|
| 160 |
+
"tokenization_kimi.TikTokenTokenizer",
|
| 161 |
+
null
|
| 162 |
+
]
|
| 163 |
+
}
|
| 164 |
+
}
|