Update tokenizer_config.json
#1
by pdelobelle - opened
- tokenizer_config.json +5 -5
tokenizer_config.json
CHANGED
|
@@ -59,10 +59,10 @@
|
|
| 59 |
"65494": {
|
| 60 |
"content": "</think>",
|
| 61 |
"lstrip": false,
|
| 62 |
-
"normalized":
|
| 63 |
"rstrip": false,
|
| 64 |
-
"single_word":
|
| 65 |
-
"special":
|
| 66 |
},
|
| 67 |
"65495": {
|
| 68 |
"content": "source_1",
|
|
@@ -397,7 +397,6 @@
|
|
| 397 |
"<|im_start|>",
|
| 398 |
"<|im_end|>",
|
| 399 |
"<think>",
|
| 400 |
-
"</think>",
|
| 401 |
"source_1",
|
| 402 |
"source_2",
|
| 403 |
"source_3",
|
|
@@ -443,5 +442,6 @@
|
|
| 443 |
"clean_up_tokenization_spaces": true,
|
| 444 |
"extra_special_tokens": {},
|
| 445 |
"model_max_length": 1000000000000000019884624838656,
|
| 446 |
-
"tokenizer_class": "PreTrainedTokenizer"
|
|
|
|
| 447 |
}
|
|
|
|
| 59 |
"65494": {
|
| 60 |
"content": "</think>",
|
| 61 |
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
"rstrip": false,
|
| 64 |
+
"single_word": true,
|
| 65 |
+
"special": false
|
| 66 |
},
|
| 67 |
"65495": {
|
| 68 |
"content": "source_1",
|
|
|
|
| 397 |
"<|im_start|>",
|
| 398 |
"<|im_end|>",
|
| 399 |
"<think>",
|
|
|
|
| 400 |
"source_1",
|
| 401 |
"source_2",
|
| 402 |
"source_3",
|
|
|
|
| 442 |
"clean_up_tokenization_spaces": true,
|
| 443 |
"extra_special_tokens": {},
|
| 444 |
"model_max_length": 1000000000000000019884624838656,
|
| 445 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
| 446 |
+
"chat_template": "{% for m in messages %}<|im_start|>{{ m['role'] }}\n{{ m['content'] }}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n<think>\n{% endif %}"
|
| 447 |
}
|