VictorSanh
commited on
Commit
•
6e9baf5
1
Parent(s):
1cb5729
tiny fix with connector update
Browse files- special_tokens_map.json +0 -7
- tokenizer.json +0 -9
- tokenizer_config.json +1 -10
special_tokens_map.json
CHANGED
@@ -13,13 +13,6 @@
|
|
13 |
"normalized": false,
|
14 |
"rstrip": false,
|
15 |
"single_word": false
|
16 |
-
},
|
17 |
-
{
|
18 |
-
"content": "<end_of_utterance>",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": false,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
}
|
24 |
],
|
25 |
"bos_token": {
|
|
|
13 |
"normalized": false,
|
14 |
"rstrip": false,
|
15 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
}
|
17 |
],
|
18 |
"bos_token": {
|
tokenizer.json
CHANGED
@@ -47,15 +47,6 @@
|
|
47 |
"rstrip": false,
|
48 |
"normalized": false,
|
49 |
"special": true
|
50 |
-
},
|
51 |
-
{
|
52 |
-
"id": 32002,
|
53 |
-
"content": "<end_of_utterance>",
|
54 |
-
"single_word": false,
|
55 |
-
"lstrip": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"normalized": false,
|
58 |
-
"special": true
|
59 |
}
|
60 |
],
|
61 |
"normalizer": {
|
|
|
47 |
"rstrip": false,
|
48 |
"normalized": false,
|
49 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
}
|
51 |
],
|
52 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -41,20 +41,11 @@
|
|
41 |
"rstrip": false,
|
42 |
"single_word": false,
|
43 |
"special": true
|
44 |
-
},
|
45 |
-
"32002": {
|
46 |
-
"content": "<end_of_utterance>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"rstrip": false,
|
50 |
-
"single_word": false,
|
51 |
-
"special": true
|
52 |
}
|
53 |
},
|
54 |
"additional_special_tokens": [
|
55 |
"<fake_token_around_image>",
|
56 |
-
"<image>"
|
57 |
-
"<end_of_utterance>"
|
58 |
],
|
59 |
"bos_token": "<s>",
|
60 |
"clean_up_tokenization_spaces": false,
|
|
|
41 |
"rstrip": false,
|
42 |
"single_word": false,
|
43 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
}
|
45 |
},
|
46 |
"additional_special_tokens": [
|
47 |
"<fake_token_around_image>",
|
48 |
+
"<image>"
|
|
|
49 |
],
|
50 |
"bos_token": "<s>",
|
51 |
"clean_up_tokenization_spaces": false,
|