Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +13 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"legacy": true,
|
| 9 |
+
"model_max_length": 16384,
|
| 10 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 12 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<｜user｜>' + message['content'] }}{% elif message['role'] == 'assistant' %}{{ '<｜assistant｜>' + message['content'] + '<｜end▁of▁sentence｜>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<｜assistant｜>' }}{% endif %}"
|
| 13 |
+
}
|