louijiec commited on
Commit
8192cad
·
verified ·
1 Parent(s): 839777f

Upload tokenizer

Browse files
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 %}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
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
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "extra_special_tokens": {},
36
+ "legacy": false,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": "</s>",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }