whizzzzkid commited on
Commit
4c4f334
1 Parent(s): 0c38bd0

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -4,14 +4,14 @@
4
  "<end_of_turn>"
5
  ],
6
  "bos_token": {
7
- "content": "<bos>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
11
  "single_word": false
12
  },
13
  "eos_token": {
14
- "content": "<eos>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
 
4
  "<end_of_turn>"
5
  ],
6
  "bos_token": {
7
+ "content": "<s>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
11
  "single_word": false
12
  },
13
  "eos_token": {
14
+ "content": "</s>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f121dcf9b0ee3f768a249f3ad6b547c972b9a90bcd9556ee4aea5ebc7a2179b2
3
- size 17478028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d4d36cf68daf005c4f1558210f0b67a276e0470676dd473888300c32df63e2
3
+ size 17478373
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json CHANGED
@@ -49,16 +49,32 @@
49
  "rstrip": false,
50
  "single_word": false,
51
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  }
53
  },
54
  "additional_special_tokens": [
55
  "<start_of_turn>",
56
  "<end_of_turn>"
57
  ],
58
- "bos_token": "<bos>",
59
  "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 %}",
60
  "clean_up_tokenization_spaces": false,
61
- "eos_token": "<eos>",
62
  "legacy": null,
63
  "max_length": 2048,
64
  "model_max_length": 1000000000000000019884624838656,
 
49
  "rstrip": false,
50
  "single_word": false,
51
  "special": true
52
+ },
53
+ "204": {
54
+ "content": "<s>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "213": {
62
+ "content": "</s>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
  }
69
  },
70
  "additional_special_tokens": [
71
  "<start_of_turn>",
72
  "<end_of_turn>"
73
  ],
74
+ "bos_token": "<s>",
75
  "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 %}",
76
  "clean_up_tokenization_spaces": false,
77
+ "eos_token": "</s>",
78
  "legacy": null,
79
  "max_length": 2048,
80
  "model_max_length": 1000000000000000019884624838656,