Parleatacoeur commited on
Commit
3b9eee0
1 Parent(s): cd99c0a

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -2,14 +2,14 @@
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
5
- "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "</s>",
11
  "lstrip": false,
12
- "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
@@ -17,7 +17,7 @@
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
20
- "normalized": true,
21
  "rstrip": false,
22
  "single_word": false
23
  }
 
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
  },
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
20
+ "normalized": false,
21
  "rstrip": false,
22
  "single_word": false
23
  }
tokenizer.json CHANGED
@@ -18,7 +18,7 @@
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
- "normalized": true,
22
  "special": true
23
  },
24
  {
@@ -27,17 +27,8 @@
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
- "normalized": true,
31
  "special": true
32
- },
33
- {
34
- "id": 32000,
35
- "content": "<pad>",
36
- "single_word": false,
37
- "lstrip": false,
38
- "rstrip": false,
39
- "normalized": true,
40
- "special": false
41
  }
42
  ],
43
  "normalizer": {
 
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": false,
22
  "special": true
23
  },
24
  {
 
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": false,
31
  "special": true
 
 
 
 
 
 
 
 
 
32
  }
33
  ],
34
  "normalizer": {
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,32 +1,42 @@
1
  {
2
- "bos_token": {
3
- "__type": "AddedToken",
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  },
 
 
10
  "clean_up_tokenization_spaces": false,
11
- "eos_token": {
12
- "__type": "AddedToken",
13
- "content": "</s>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
  "legacy": false,
20
  "model_max_length": 1000000000000000019884624838656,
21
- "pad_token": null,
 
22
  "sp_model_kwargs": {},
23
  "tokenizer_class": "LlamaTokenizer",
24
- "unk_token": {
25
- "__type": "AddedToken",
26
- "content": "<unk>",
27
- "lstrip": false,
28
- "normalized": true,
29
- "rstrip": false,
30
- "single_word": false
31
- }
32
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
  },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% 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' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
32
  "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
 
 
 
 
 
 
 
34
  "legacy": false,
35
  "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
  "sp_model_kwargs": {},
39
  "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
 
 
 
 
 
 
42
  }