jondurbin commited on
Commit
60d0d47
·
verified ·
1 Parent(s): aec86c6

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -1,4 +1,9 @@
1
  {
 
 
 
 
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
  "bos_token": {
8
  "content": "<s>",
9
  "lstrip": false,
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 1024,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
tokenizer_config.json CHANGED
@@ -27,13 +27,17 @@
27
  "special": true
28
  }
29
  },
30
- "additional_special_tokens": [],
 
 
 
 
31
  "bos_token": "<s>",
32
  "chat_template": "{{ bos_token }}{% 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'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
  "clean_up_tokenization_spaces": false,
34
  "eos_token": "</s>",
35
  "legacy": true,
36
- "max_length": 1024,
37
  "model_max_length": 1000000000000000019884624838656,
38
  "pad_token": "<unk>",
39
  "padding_side": "right",
@@ -43,6 +47,8 @@
43
  "tokenizer_class": "LlamaTokenizer",
44
  "truncation_side": "right",
45
  "truncation_strategy": "longest_first",
 
46
  "unk_token": "<unk>",
47
- "use_default_system_prompt": false
 
48
  }
 
27
  "special": true
28
  }
29
  },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
  "bos_token": "<s>",
36
  "chat_template": "{{ bos_token }}{% 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'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
37
  "clean_up_tokenization_spaces": false,
38
  "eos_token": "</s>",
39
  "legacy": true,
40
+ "max_length": 2048,
41
  "model_max_length": 1000000000000000019884624838656,
42
  "pad_token": "<unk>",
43
  "padding_side": "right",
 
47
  "tokenizer_class": "LlamaTokenizer",
48
  "truncation_side": "right",
49
  "truncation_strategy": "longest_first",
50
+ "trust_remote_code": false,
51
  "unk_token": "<unk>",
52
+ "use_default_system_prompt": false,
53
+ "use_fast": true
54
  }