Update to new format and include chat template with default system message
#1
by
BramVanroy
- opened
- tokenizer_config.json +31 -24
tokenizer_config.json
CHANGED
@@ -1,33 +1,40 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
},
|
|
|
|
|
10 |
"clean_up_tokenization_spaces": false,
|
11 |
-
"eos_token":
|
12 |
-
"__type": "AddedToken",
|
13 |
-
"content": "</s>",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": false,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false
|
18 |
-
},
|
19 |
"legacy": false,
|
20 |
"model_max_length": 1000000000000000019884624838656,
|
21 |
"pad_token": null,
|
22 |
"padding_side": "right",
|
23 |
"sp_model_kwargs": {},
|
24 |
"tokenizer_class": "LlamaTokenizer",
|
25 |
-
"unk_token":
|
26 |
-
|
27 |
-
|
28 |
-
"lstrip": false,
|
29 |
-
"normalized": false,
|
30 |
-
"rstrip": false,
|
31 |
-
"single_word": false
|
32 |
-
}
|
33 |
-
}
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
},
|
28 |
+
"bos_token": "<s>",
|
29 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{%set system_message = 'Je bent een behulpzame, respectvolle en eerlijke assistent. Antwoord altijd zo behulpzaam mogelijk. Je antwoorden mogen geen schadelijke, onethische, racistische, seksistische, gevaarlijke of illegale inhoud bevatten. Zorg ervoor dat je antwoorden sociaal onbevooroordeeld en positief van aard zijn.\n\nAls een vraag nergens op slaat of feitelijk niet coherent is, leg dan uit waarom in plaats van iets niet correct te antwoorden. Als je het antwoord op een vraag niet weet, deel dan geen onjuiste informatie.' %}{% 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'] == 'system' %}{{ '<<SYS>>\n' + content.strip() + '\n<</SYS>>\n\n' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
"legacy": false,
|
33 |
"model_max_length": 1000000000000000019884624838656,
|
34 |
"pad_token": null,
|
35 |
"padding_side": "right",
|
36 |
"sp_model_kwargs": {},
|
37 |
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": false
|
40 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|