Upload tokenizer
Browse files- added_tokens.json +2 -0
- tokenizer_config.json +17 -2
added_tokens.json
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"</tool_call>": 151658,
|
|
|
|
| 3 |
"<tool_call>": 151657,
|
| 4 |
"<|box_end|>": 151649,
|
| 5 |
"<|box_start|>": 151648,
|
|
|
|
| 1 |
{
|
| 2 |
+
"</think>": 151666,
|
| 3 |
"</tool_call>": 151658,
|
| 4 |
+
"<think>": 151665,
|
| 5 |
"<tool_call>": 151657,
|
| 6 |
"<|box_end|>": 151649,
|
| 7 |
"<|box_start|>": 151648,
|
tokenizer_config.json
CHANGED
|
@@ -177,6 +177,22 @@
|
|
| 177 |
"rstrip": false,
|
| 178 |
"single_word": false,
|
| 179 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 180 |
}
|
| 181 |
},
|
| 182 |
"additional_special_tokens": [
|
|
@@ -200,9 +216,8 @@
|
|
| 200 |
"eos_token": "<|im_end|>",
|
| 201 |
"errors": "replace",
|
| 202 |
"extra_special_tokens": {},
|
| 203 |
-
"model_max_length":
|
| 204 |
"pad_token": "<|endoftext|>",
|
| 205 |
-
"padding_side": "left",
|
| 206 |
"split_special_tokens": false,
|
| 207 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
"unk_token": null
|
|
|
|
| 177 |
"rstrip": false,
|
| 178 |
"single_word": false,
|
| 179 |
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<think>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": true,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</think>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": true,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
}
|
| 197 |
},
|
| 198 |
"additional_special_tokens": [
|
|
|
|
| 216 |
"eos_token": "<|im_end|>",
|
| 217 |
"errors": "replace",
|
| 218 |
"extra_special_tokens": {},
|
| 219 |
+
"model_max_length": 131072,
|
| 220 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 221 |
"split_special_tokens": false,
|
| 222 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 223 |
"unk_token": null
|