GuillemGSubies
commited on
Commit
•
3cdea0a
1
Parent(s):
32278fd
Upload the tokenizer
Browse files- .gitattributes +1 -0
- added_tokens.json +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +19 -0
.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
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 250101
|
3 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
|
3 |
+
size 4305025
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e23095eb61ba944c7be3a5d3e8ec19e37ce7ced0daa03550bde03e83c21b3f8a
|
3 |
+
size 16316151
|
tokenizer_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"eos_token": "[SEP]",
|
6 |
+
"keep_accents": true,
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"model_max_len": 512,
|
9 |
+
"model_max_length": 1000000000000000019884624838656,
|
10 |
+
"name_or_path": "microsoft/mdeberta-v3-base-16-4e-05-0.2-meddocan_best",
|
11 |
+
"pad_token": "[PAD]",
|
12 |
+
"sep_token": "[SEP]",
|
13 |
+
"sp_model_kwargs": {},
|
14 |
+
"special_tokens_map_file": null,
|
15 |
+
"split_by_punct": false,
|
16 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
17 |
+
"unk_token": "[UNK]",
|
18 |
+
"vocab_type": "spm"
|
19 |
+
}
|