Upload tokenizer
Browse files- tokenizer.json +8 -1
- tokenizer_config.json +1 -2
tokenizer.json
CHANGED
@@ -1,7 +1,14 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
-
"padding":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
+
"padding": {
|
5 |
+
"strategy": "BatchLongest",
|
6 |
+
"direction": "Right",
|
7 |
+
"pad_to_multiple_of": null,
|
8 |
+
"pad_id": 2,
|
9 |
+
"pad_type_id": 0,
|
10 |
+
"pad_token": "</s>"
|
11 |
+
},
|
12 |
"added_tokens": [
|
13 |
{
|
14 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -28,11 +28,10 @@
|
|
28 |
}
|
29 |
},
|
30 |
"bos_token": "<s>",
|
31 |
-
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": false,
|
35 |
-
"model_max_length":
|
36 |
"pad_token": "</s>",
|
37 |
"padding_side": "right",
|
38 |
"sp_model_kwargs": {},
|
|
|
28 |
}
|
29 |
},
|
30 |
"bos_token": "<s>",
|
|
|
31 |
"clean_up_tokenization_spaces": false,
|
32 |
"eos_token": "</s>",
|
33 |
"legacy": false,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
"pad_token": "</s>",
|
36 |
"padding_side": "right",
|
37 |
"sp_model_kwargs": {},
|