Commit
•
724d7f5
1
Parent(s):
77805e0
Upload tokenizer
Browse files- tokenizer.json +1 -6
- tokenizer_config.json +1 -0
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 20480,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
tokenizer_config.json
CHANGED
|
@@ -40,6 +40,7 @@
|
|
| 40 |
"<unk>"
|
| 41 |
],
|
| 42 |
"bos_token": "<s>",
|
|
|
|
| 43 |
"clean_up_tokenization_spaces": true,
|
| 44 |
"eos_token": "</s>",
|
| 45 |
"max_length": 20480,
|
|
|
|
| 40 |
"<unk>"
|
| 41 |
],
|
| 42 |
"bos_token": "<s>",
|
| 43 |
+
"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 %}",
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"eos_token": "</s>",
|
| 46 |
"max_length": 20480,
|