Update tokenizer files (#15)
Browse files- Update tokenizer files (44c340456b9752b0a2a530ddd5837545e55d5921)
Co-authored-by: Joshua <[email protected]>
- special_tokens_map.json +4 -0
- tokenizer_config.json +4 -0
special_tokens_map.json
CHANGED
@@ -1,4 +1,8 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<bos>",
|
4 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<start_of_turn>",
|
4 |
+
"<end_of_turn>"
|
5 |
+
],
|
6 |
"bos_token": {
|
7 |
"content": "<bos>",
|
8 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -1995,6 +1995,10 @@
|
|
1995 |
"special": false
|
1996 |
}
|
1997 |
},
|
|
|
|
|
|
|
|
|
1998 |
"bos_token": "<bos>",
|
1999 |
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
2000 |
"clean_up_tokenization_spaces": false,
|
|
|
1995 |
"special": false
|
1996 |
}
|
1997 |
},
|
1998 |
+
"additional_special_tokens": [
|
1999 |
+
"<start_of_turn>",
|
2000 |
+
"<end_of_turn>"
|
2001 |
+
],
|
2002 |
"bos_token": "<bos>",
|
2003 |
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
2004 |
"clean_up_tokenization_spaces": false,
|