Create tokenizer_config.json
Browse files- tokenizer_config.json +13 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_lower_case": true,
|
| 3 |
+
"unk_token": "[UNK]",
|
| 4 |
+
"sep_token": "[SEP]",
|
| 5 |
+
"pad_token": "[PAD]",
|
| 6 |
+
"cls_token": "[CLS]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"tokenize_chinese_chars": true,
|
| 9 |
+
"strip_accents": null,
|
| 10 |
+
"model_max_length": 512,
|
| 11 |
+
"tokenizer_class": "BertTokenizer",
|
| 12 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% elif message['role'] == 'user' %}{{ '### Instruction:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response:\n' + message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### Response:\n' }}{% endif %}"
|
| 13 |
+
}
|