ambroz-soniox
commited on
Commit
•
22a39ee
1
Parent(s):
51dcda7
tokenizer_config fix regarding BOS
Browse files- tokenizer_config.json +2 -2
tokenizer_config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"add_bos_token":
|
3 |
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
@@ -39,5 +39,5 @@
|
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
40 |
"unk_token": "<unk>",
|
41 |
"use_default_system_prompt": false,
|
42 |
-
"chat_template": "[CLS:soniox] {% 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 %}"
|
43 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": false,
|
3 |
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
|
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
40 |
"unk_token": "<unk>",
|
41 |
"use_default_system_prompt": false,
|
42 |
+
"chat_template": "<s>[CLS:soniox] {% 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 %}"
|
43 |
}
|