Upload tokenizer
Browse files- .gitattributes +1 -0
- tokenizer_config.json +8 -2
- unigram.json +3 -0
.gitattributes
CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
unigram.json filter=lfs diff=lfs merge=lfs -text
|
tokenizer_config.json
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
"bos_token": "<s>",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"cls_token": "<s>",
|
|
|
5 |
"eos_token": "</s>",
|
6 |
"mask_token": {
|
7 |
"__type": "AddedToken",
|
@@ -11,12 +12,17 @@
|
|
11 |
"rstrip": false,
|
12 |
"single_word": false
|
13 |
},
|
14 |
-
"max_length":
|
15 |
"model_max_length": 512,
|
|
|
16 |
"pad_token": "<pad>",
|
|
|
|
|
17 |
"sep_token": "</s>",
|
18 |
"stride": 0,
|
19 |
-
"
|
|
|
|
|
20 |
"truncation_side": "right",
|
21 |
"truncation_strategy": "longest_first",
|
22 |
"unk_token": "<unk>"
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"cls_token": "<s>",
|
5 |
+
"do_lower_case": true,
|
6 |
"eos_token": "</s>",
|
7 |
"mask_token": {
|
8 |
"__type": "AddedToken",
|
|
|
12 |
"rstrip": false,
|
13 |
"single_word": false
|
14 |
},
|
15 |
+
"max_length": 128,
|
16 |
"model_max_length": 512,
|
17 |
+
"pad_to_multiple_of": null,
|
18 |
"pad_token": "<pad>",
|
19 |
+
"pad_token_type_id": 0,
|
20 |
+
"padding_side": "right",
|
21 |
"sep_token": "</s>",
|
22 |
"stride": 0,
|
23 |
+
"strip_accents": null,
|
24 |
+
"tokenize_chinese_chars": true,
|
25 |
+
"tokenizer_class": "BertTokenizer",
|
26 |
"truncation_side": "right",
|
27 |
"truncation_strategy": "longest_first",
|
28 |
"unk_token": "<unk>"
|
unigram.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71b44701d7efd054205115acfa6ef126c5d2f84bd3affe0c59e48163674d19a6
|
3 |
+
size 14763234
|