Commit
·
10acddc
1
Parent(s):
c718ad4
Upload tokenizer
Browse files- .gitattributes +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -5
.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
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,18 +1,22 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
"bos_token": "<s>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
"cls_token": "<s>",
|
| 6 |
"eos_token": "</s>",
|
| 7 |
-
"
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"max_length": 512,
|
| 10 |
"model_max_length": 512,
|
| 11 |
"pad_token": "<pad>",
|
| 12 |
"sep_token": "</s>",
|
| 13 |
"stride": 256,
|
| 14 |
-
"tokenizer_class": "
|
| 15 |
-
"trim_offsets": true,
|
| 16 |
"truncation_side": "right",
|
| 17 |
"truncation_strategy": "longest_first",
|
| 18 |
"unk_token": "<unk>"
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"clean_up_tokenization_spaces": true,
|
| 4 |
"cls_token": "<s>",
|
| 5 |
"eos_token": "</s>",
|
| 6 |
+
"mask_token": {
|
| 7 |
+
"__type": "AddedToken",
|
| 8 |
+
"content": "<mask>",
|
| 9 |
+
"lstrip": true,
|
| 10 |
+
"normalized": true,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
"max_length": 512,
|
| 15 |
"model_max_length": 512,
|
| 16 |
"pad_token": "<pad>",
|
| 17 |
"sep_token": "</s>",
|
| 18 |
"stride": 256,
|
| 19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
| 20 |
"truncation_side": "right",
|
| 21 |
"truncation_strategy": "longest_first",
|
| 22 |
"unk_token": "<unk>"
|