Commit
•
98cf8e8
1
Parent(s):
1d9420a
Upload tokenizer
Browse files- .gitattributes +1 -0
- sentencepiece.bpe.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +6 -7
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip 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
|
|
|
|
|
|
| 33 |
*.zip 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
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"0": {
|
| 5 |
"content": "<s>",
|
| 6 |
"lstrip": false,
|
| 7 |
-
"normalized":
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
|
@@ -12,7 +12,7 @@
|
|
| 12 |
"1": {
|
| 13 |
"content": "<pad>",
|
| 14 |
"lstrip": false,
|
| 15 |
-
"normalized":
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
|
@@ -20,7 +20,7 @@
|
|
| 20 |
"2": {
|
| 21 |
"content": "</s>",
|
| 22 |
"lstrip": false,
|
| 23 |
-
"normalized":
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
|
@@ -28,12 +28,12 @@
|
|
| 28 |
"3": {
|
| 29 |
"content": "<unk>",
|
| 30 |
"lstrip": false,
|
| 31 |
-
"normalized":
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false,
|
| 34 |
"special": true
|
| 35 |
},
|
| 36 |
-
"
|
| 37 |
"content": "<mask>",
|
| 38 |
"lstrip": true,
|
| 39 |
"normalized": false,
|
|
@@ -46,12 +46,11 @@
|
|
| 46 |
"clean_up_tokenization_spaces": true,
|
| 47 |
"cls_token": "<s>",
|
| 48 |
"eos_token": "</s>",
|
| 49 |
-
"errors": "replace",
|
| 50 |
"mask_token": "<mask>",
|
| 51 |
"model_max_length": 512,
|
| 52 |
"pad_token": "<pad>",
|
| 53 |
"sep_token": "</s>",
|
| 54 |
-
"tokenizer_class": "
|
| 55 |
"trim_offsets": true,
|
| 56 |
"unk_token": "<unk>"
|
| 57 |
}
|
|
|
|
| 4 |
"0": {
|
| 5 |
"content": "<s>",
|
| 6 |
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
|
|
|
| 12 |
"1": {
|
| 13 |
"content": "<pad>",
|
| 14 |
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
|
|
|
| 20 |
"2": {
|
| 21 |
"content": "</s>",
|
| 22 |
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
|
|
|
| 28 |
"3": {
|
| 29 |
"content": "<unk>",
|
| 30 |
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false,
|
| 34 |
"special": true
|
| 35 |
},
|
| 36 |
+
"250001": {
|
| 37 |
"content": "<mask>",
|
| 38 |
"lstrip": true,
|
| 39 |
"normalized": false,
|
|
|
|
| 46 |
"clean_up_tokenization_spaces": true,
|
| 47 |
"cls_token": "<s>",
|
| 48 |
"eos_token": "</s>",
|
|
|
|
| 49 |
"mask_token": "<mask>",
|
| 50 |
"model_max_length": 512,
|
| 51 |
"pad_token": "<pad>",
|
| 52 |
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 54 |
"trim_offsets": true,
|
| 55 |
"unk_token": "<unk>"
|
| 56 |
}
|