Upload tokenizer
Browse files- special_tokens_map.json +16 -0
- tokenizer_config.json +2 -2
special_tokens_map.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end_of_text|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
}
|
| 16 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -2050,9 +2050,9 @@
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
-
"chat_template": "{
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
-
"eos_token": "<|
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
|
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"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' %}<|end_of_text|>{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n\n### Assistant\n' }}{% endif %}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|end_of_text|>",
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|