danielhanchen commited on
Commit
9167ff5
1 Parent(s): 16ee1de

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +6 -16
  2. tokenizer_config.json +3 -2
tokenizer.json CHANGED
@@ -31,23 +31,13 @@
31
  "special": true
32
  }
33
  ],
34
- "normalizer": {
35
- "type": "Sequence",
36
- "normalizers": [
37
- {
38
- "type": "Prepend",
39
- "prepend": "▁"
40
- },
41
- {
42
- "type": "Replace",
43
- "pattern": {
44
- "String": " "
45
- },
46
- "content": "▁"
47
- }
48
- ]
49
  },
50
- "pre_tokenizer": null,
51
  "post_processor": {
52
  "type": "TemplateProcessing",
53
  "single": [
 
31
  "special": true
32
  }
33
  ],
34
+ "normalizer": null,
35
+ "pre_tokenizer": {
36
+ "type": "Metaspace",
37
+ "replacement": "▁",
38
+ "prepend_scheme": "first",
39
+ "split": false
 
 
 
 
 
 
 
 
 
40
  },
 
41
  "post_processor": {
42
  "type": "TemplateProcessing",
43
  "single": [
tokenizer_config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
 
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
@@ -29,10 +30,10 @@
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
  "model_max_length": 1000000000000000019884624838656,
37
  "pad_token": "<unk>",
38
  "padding_side": "left",
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "add_prefix_space": null,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",
 
30
  },
31
  "additional_special_tokens": [],
32
  "bos_token": "<s>",
33
+ "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message['role'] == 'user' %}\n {%- if loop.first and system_message is defined %}\n {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n {%- else %}\n {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {{- ' ' + message['content'] + eos_token}}\n {%- else %}\n {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n {%- endif %}\n{%- endfor %}\n",
34
  "clean_up_tokenization_spaces": false,
35
  "eos_token": "</s>",
36
+ "legacy": false,
37
  "model_max_length": 1000000000000000019884624838656,
38
  "pad_token": "<unk>",
39
  "padding_side": "left",