update additional_special_tokens (#8)
Browse files- update additional_special_tokens (25c9ed42ae8210cb141143667adfae5c9a52a886)
- add additional_special_tokens in tokenizer cfg (2234bca0e798d28dffe3eec70b8d6f11c6c62419)
Co-authored-by: RangiLyu <RangiLyu@users.noreply.huggingface.co>
- special_tokens_map.json +8 -0
- tokenizer_config.json +8 -0
special_tokens_map.json
CHANGED
@@ -1,4 +1,12 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"eos_token": "</s>",
|
4 |
"pad_token": "</s>",
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|action_start|>",
|
6 |
+
"<|action_end|>",
|
7 |
+
"<|interpreter|>",
|
8 |
+
"<|plugin|>"
|
9 |
+
],
|
10 |
"bos_token": "<s>",
|
11 |
"eos_token": "</s>",
|
12 |
"pad_token": "</s>",
|
tokenizer_config.json
CHANGED
@@ -86,5 +86,13 @@
|
|
86 |
"special": true
|
87 |
}
|
88 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
89 |
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
90 |
}
|
|
|
86 |
"special": true
|
87 |
}
|
88 |
},
|
89 |
+
"additional_special_tokens": [
|
90 |
+
"<|im_start|>",
|
91 |
+
"<|im_end|>",
|
92 |
+
"<|action_start|>",
|
93 |
+
"<|action_end|>",
|
94 |
+
"<|interpreter|>",
|
95 |
+
"<|plugin|>"
|
96 |
+
],
|
97 |
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
98 |
}
|