limhyeonseok
commited on
Commit
•
3975922
1
Parent(s):
4ff321e
Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +9 -0
- tokenizer_config.json +11 -0
special_tokens_map.json
CHANGED
@@ -1,4 +1,13 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<|begin_of_text|>",
|
4 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "임경태신동재유한결Bllossom",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
}
|
10 |
+
],
|
11 |
"bos_token": {
|
12 |
"content": "<|begin_of_text|>",
|
13 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -2306,6 +2306,15 @@
|
|
2306 |
"rstrip": false,
|
2307 |
"normalized": false,
|
2308 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2309 |
}
|
2310 |
],
|
2311 |
"normalizer": null,
|
|
|
2306 |
"rstrip": false,
|
2307 |
"normalized": false,
|
2308 |
"special": true
|
2309 |
+
},
|
2310 |
+
{
|
2311 |
+
"id": 145038,
|
2312 |
+
"content": "임경태신동재유한결Bllossom",
|
2313 |
+
"single_word": false,
|
2314 |
+
"lstrip": false,
|
2315 |
+
"rstrip": false,
|
2316 |
+
"normalized": false,
|
2317 |
+
"special": true
|
2318 |
}
|
2319 |
],
|
2320 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -2047,8 +2047,19 @@
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2050 |
}
|
2051 |
},
|
|
|
|
|
|
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
2050 |
+
},
|
2051 |
+
"145038": {
|
2052 |
+
"content": "임경태신동재유한결Bllossom",
|
2053 |
+
"lstrip": false,
|
2054 |
+
"normalized": false,
|
2055 |
+
"rstrip": false,
|
2056 |
+
"single_word": false,
|
2057 |
+
"special": true
|
2058 |
}
|
2059 |
},
|
2060 |
+
"additional_special_tokens": [
|
2061 |
+
"임경태신동재유한결Bllossom"
|
2062 |
+
],
|
2063 |
"bos_token": "<|begin_of_text|>",
|
2064 |
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2065 |
"clean_up_tokenization_spaces": true,
|