codestylist
commited on
Commit
•
7e702ad
1
Parent(s):
86bbfd4
Upload tokenizer_config.json
Browse files- tokenizer_config.json +1 -68
tokenizer_config.json
CHANGED
@@ -1,68 +1 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"additional_special_tokens": [
|
4 |
-
"<nl>",
|
5 |
-
"</nl>"
|
6 |
-
],
|
7 |
-
"bos_token": {
|
8 |
-
"__type": "AddedToken",
|
9 |
-
"content": "<s>",
|
10 |
-
"lstrip": false,
|
11 |
-
"normalized": true,
|
12 |
-
"rstrip": false,
|
13 |
-
"single_word": false
|
14 |
-
},
|
15 |
-
"cls_token": {
|
16 |
-
"__type": "AddedToken",
|
17 |
-
"content": "<s>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": true,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"eos_token": {
|
24 |
-
"__type": "AddedToken",
|
25 |
-
"content": "</s>",
|
26 |
-
"lstrip": false,
|
27 |
-
"normalized": true,
|
28 |
-
"rstrip": false,
|
29 |
-
"single_word": false
|
30 |
-
},
|
31 |
-
"errors": "replace",
|
32 |
-
"mask_token": {
|
33 |
-
"__type": "AddedToken",
|
34 |
-
"content": "<mask>",
|
35 |
-
"lstrip": true,
|
36 |
-
"normalized": true,
|
37 |
-
"rstrip": false,
|
38 |
-
"single_word": false
|
39 |
-
},
|
40 |
-
"model_max_length": 512,
|
41 |
-
"name_or_path": "Salesforce/codet5-base",
|
42 |
-
"pad_token": {
|
43 |
-
"__type": "AddedToken",
|
44 |
-
"content": "<pad>",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": true,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false
|
49 |
-
},
|
50 |
-
"sep_token": {
|
51 |
-
"__type": "AddedToken",
|
52 |
-
"content": "</s>",
|
53 |
-
"lstrip": false,
|
54 |
-
"normalized": true,
|
55 |
-
"rstrip": false,
|
56 |
-
"single_word": false
|
57 |
-
},
|
58 |
-
"special_tokens_map_file": "/soe/ksmunson/.cache/huggingface/transformers/5941df5e4315c5ab63b7b2ac791fb0bf0f209744a055c06b43b5274849137cdd.b9905d0575bde443a20834122b6e2d48e853b2e36444ce98ddeb43c38097eb3f",
|
59 |
-
"tokenizer_class": "RobertaTokenizer",
|
60 |
-
"unk_token": {
|
61 |
-
"__type": "AddedToken",
|
62 |
-
"content": "<unk>",
|
63 |
-
"lstrip": false,
|
64 |
-
"normalized": true,
|
65 |
-
"rstrip": false,
|
66 |
-
"single_word": false
|
67 |
-
}
|
68 |
-
}
|
|
|
1 |
+
{"errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 512, "additional_special_tokens": ["<nl>", "</nl>"], "special_tokens_map_file": "/data/users/cting3/.cache/huggingface/transformers/5941df5e4315c5ab63b7b2ac791fb0bf0f209744a055c06b43b5274849137cdd.b9905d0575bde443a20834122b6e2d48e853b2e36444ce98ddeb43c38097eb3f", "name_or_path": "Salesforce/codet5-base", "tokenizer_class": "RobertaTokenizer"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|