qgallouedec HF Staff commited on
Commit
8e9a852
·
verified ·
1 Parent(s): 67a3878

Upload tokenizer

Browse files
Files changed (2) hide show
  1. chat_template.jinja +24 -0
  2. tokenizer_config.json +0 -1
chat_template.jinja ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if messages[0]['role'] == 'system' %}
2
+ {%- set system_message = messages[0]['content'] %}
3
+ {%- set loop_messages = messages[1:] %}
4
+ {%- else %}
5
+ {%- set loop_messages = messages %}
6
+ {%- endif %}
7
+
8
+ {{- bos_token }}
9
+ {%- for message in loop_messages %}
10
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}
11
+ {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}
12
+ {%- endif %}
13
+ {%- if message['role'] == 'user' %}
14
+ {%- if loop.first and system_message is defined %}
15
+ {{- ' [INST] ' + system_message + '\n\n' + message['content'] + ' [/INST]' }}
16
+ {%- else %}
17
+ {{- ' [INST] ' + message['content'] + ' [/INST]' }}
18
+ {%- endif %}
19
+ {%- elif message['role'] == 'assistant' %}
20
+ {{- ' ' + message['content'] + eos_token}}
21
+ {%- else %}
22
+ {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}
23
+ {%- endif %}
24
+ {%- endfor %}
tokenizer_config.json CHANGED
@@ -30,7 +30,6 @@
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
  "extra_special_tokens": {},
 
30
  },
31
  "additional_special_tokens": [],
32
  "bos_token": "<s>",
 
33
  "clean_up_tokenization_spaces": false,
34
  "eos_token": "</s>",
35
  "extra_special_tokens": {},