Upload tokenizer
Browse files- README.md +3 -3
- special_tokens_map.json +21 -3
- tokenizer_config.json +5 -1
README.md
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
---
|
2 |
language:
|
3 |
-
|
4 |
-
|
|
|
5 |
library_name: transformers
|
6 |
pipeline_tag: text-generation
|
7 |
model_type: mistral
|
8 |
-
license: apache-2.0
|
9 |
---
|
10 |
|
11 |
# Swallow-MS-7b-v0.1
|
|
|
1 |
---
|
2 |
language:
|
3 |
+
- en
|
4 |
+
- ja
|
5 |
+
license: apache-2.0
|
6 |
library_name: transformers
|
7 |
pipeline_tag: text-generation
|
8 |
model_type: mistral
|
|
|
9 |
---
|
10 |
|
11 |
# Swallow-MS-7b-v0.1
|
special_tokens_map.json
CHANGED
@@ -1,5 +1,23 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
}
|
tokenizer_config.json
CHANGED
@@ -27,17 +27,21 @@
|
|
27 |
"special": true
|
28 |
}
|
29 |
},
|
30 |
-
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true and not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{{ bos_token }}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + content.strip() + ' [/INST] ' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + content.strip() + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ '' + content.strip() + '' + eos_token }}{% endif %}{% endfor %}",
|
31 |
"additional_special_tokens": [],
|
32 |
"bos_token": "<s>",
|
|
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
"legacy": true,
|
|
|
36 |
"model_max_length": 1000000000000000019884624838656,
|
37 |
"pad_token": null,
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
|
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
41 |
"unk_token": "<unk>",
|
42 |
"use_default_system_prompt": false
|
43 |
}
|
|
|
27 |
"special": true
|
28 |
}
|
29 |
},
|
|
|
30 |
"additional_special_tokens": [],
|
31 |
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}\n{% set loop_messages = messages[1:] %}\n{% set system_message = messages[0]['content'] %}\n{% elif false == true and not '<<SYS>>' in messages[0]['content'] %}\n{% set loop_messages = messages %}\n{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}\n{% else %}\n{% set loop_messages = messages %}\n{% set system_message = false %}\n{% endif %}\n{{ bos_token }}\n{% for message in loop_messages %}\n{% if (message['role'] == 'user') != ((loop.index0 + messages[0]['role'] == 'assistant') % 2 == 0) %}\n{{ raise_exception('Conversation roles must alternate starting from the first role.') }}\n{% endif %}\n{% if loop.index0 == 0 and system_message != false %}\n{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}\n{% else %}\n{% set content = message['content'] %}\n{% endif %}\n{% if message['role'] == 'user' %}\n{{ '[INST] ' + content.strip() + ' [/INST] ' }}\n{% elif message['role'] == 'system' %}\n{{ '<<SYS>>\n' + content.strip() + '\n<</SYS>>\n\n' }}\n{% elif message['role'] == 'assistant' %}\n{{ '' + content.strip() + '' + eos_token }}\n{% endif %}\n{% endfor %}\n",
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
"legacy": true,
|
36 |
+
"max_length": 4096,
|
37 |
"model_max_length": 1000000000000000019884624838656,
|
38 |
"pad_token": null,
|
39 |
"sp_model_kwargs": {},
|
40 |
"spaces_between_special_tokens": false,
|
41 |
+
"stride": 0,
|
42 |
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"truncation_side": "right",
|
44 |
+
"truncation_strategy": "longest_first",
|
45 |
"unk_token": "<unk>",
|
46 |
"use_default_system_prompt": false
|
47 |
}
|