Upload tokenizer
Browse files- tokenizer_config.json +4 -1
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
@@ -27,6 +29,7 @@
|
|
27 |
},
|
28 |
"additional_special_tokens": [],
|
29 |
"bos_token": "<s>",
|
|
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
"eos_token": "</s>",
|
32 |
"legacy": true,
|
@@ -37,5 +40,5 @@
|
|
37 |
"spaces_between_special_tokens": false,
|
38 |
"tokenizer_class": "LlamaTokenizer",
|
39 |
"unk_token": "<unk>",
|
40 |
-
"use_default_system_prompt":
|
41 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
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,
|
|
|
40 |
"spaces_between_special_tokens": false,
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
42 |
"unk_token": "<unk>",
|
43 |
+
"use_default_system_prompt": true
|
44 |
}
|