Upload tokenizer
Browse files- special_tokens_map.json +23 -0
- tokenizer_config.json +1 -1
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin▁of▁sentence|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|end▁of▁sentence|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -133,7 +133,7 @@
|
|
| 133 |
}
|
| 134 |
},
|
| 135 |
"bos_token": "<|begin▁of▁sentence|>",
|
| 136 |
-
"chat_template": "{%
|
| 137 |
"clean_up_tokenization_spaces": false,
|
| 138 |
"eos_token": "<|EOT|>",
|
| 139 |
"legacy": true,
|
|
|
|
| 133 |
}
|
| 134 |
},
|
| 135 |
"bos_token": "<|begin▁of▁sentence|>",
|
| 136 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% if message['role'] == 'system' %}{% set content = '\n### System\n' + message['content'] | trim + '\n' %}{% elif message['role'] == 'user' %}{% set content = '\n### User\n' + message['content'] | trim %}{% else %}{% set content = '\n\n### Assistant\n' + message['content'] | trim %}{% endif %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% if message['role'] == 'assistant' %}<|EOT|>{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n\n### Assistant\n' }}{% endif %}",
|
| 137 |
"clean_up_tokenization_spaces": false,
|
| 138 |
"eos_token": "<|EOT|>",
|
| 139 |
"legacy": true,
|