emrgnt-cmplxty
commited on
Commit
•
20ce201
1
Parent(s):
a128f3c
Update tokenizer_config.json
Browse files- tokenizer_config.json +5 -7
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
@@ -25,11 +27,7 @@
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
28 |
-
"additional_special_tokens": [
|
29 |
-
"<unk>",
|
30 |
-
"<s>",
|
31 |
-
"</s>"
|
32 |
-
],
|
33 |
"bos_token": "<s>",
|
34 |
"clean_up_tokenization_spaces": false,
|
35 |
"eos_token": "</s>",
|
@@ -40,5 +38,5 @@
|
|
40 |
"spaces_between_special_tokens": false,
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
42 |
"unk_token": "<unk>",
|
43 |
-
"use_default_system_prompt":
|
44 |
-
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
27 |
"special": true
|
28 |
}
|
29 |
},
|
30 |
+
"additional_special_tokens": [],
|
|
|
|
|
|
|
|
|
31 |
"bos_token": "<s>",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
|
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
40 |
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|