Upload tokenizer
Browse files- added_tokens.json +0 -0
- special_tokens_map.json +6 -42
- spm.model +3 -0
- tokenizer.json +2 -2
- tokenizer_config.json +0 -4
added_tokens.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,46 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
},
|
| 9 |
-
"cls_token": {
|
| 10 |
-
"content": "[CLS]",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"eos_token": {
|
| 17 |
-
"content": "[SEP]",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
-
"mask_token": {
|
| 24 |
-
"content": "[MASK]",
|
| 25 |
-
"lstrip": false,
|
| 26 |
-
"normalized": false,
|
| 27 |
-
"rstrip": false,
|
| 28 |
-
"single_word": false
|
| 29 |
-
},
|
| 30 |
-
"pad_token": {
|
| 31 |
-
"content": "[PAD]",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": false,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false
|
| 36 |
-
},
|
| 37 |
-
"sep_token": {
|
| 38 |
-
"content": "[SEP]",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false
|
| 43 |
-
},
|
| 44 |
"unk_token": {
|
| 45 |
"content": "[UNK]",
|
| 46 |
"lstrip": false,
|
|
|
|
| 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": {
|
| 9 |
"content": "[UNK]",
|
| 10 |
"lstrip": false,
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1266e0edc0bc19b131866b403edb3cc5db56f83199c2348c5bfb661b24275554
|
| 3 |
+
size 10522807
|
tokenizer_config.json
CHANGED
|
@@ -80240,7 +80240,6 @@
|
|
| 80240 |
"eos_token": "[SEP]",
|
| 80241 |
"is_split_into_words": true,
|
| 80242 |
"mask_token": "[MASK]",
|
| 80243 |
-
"max_length": 512,
|
| 80244 |
"model_max_length": 1000000000000000019884624838656,
|
| 80245 |
"pad_token": "[PAD]",
|
| 80246 |
"padding": true,
|
|
@@ -80248,11 +80247,8 @@
|
|
| 80248 |
"sep_token": "[SEP]",
|
| 80249 |
"sp_model_kwargs": {},
|
| 80250 |
"split_by_punct": false,
|
| 80251 |
-
"stride": 0,
|
| 80252 |
"tokenizer_class": "DebertaV2Tokenizer",
|
| 80253 |
"truncation": true,
|
| 80254 |
-
"truncation_side": "right",
|
| 80255 |
-
"truncation_strategy": "longest_first",
|
| 80256 |
"unk_token": "[UNK]",
|
| 80257 |
"vocab_type": "spm"
|
| 80258 |
}
|
|
|
|
| 80240 |
"eos_token": "[SEP]",
|
| 80241 |
"is_split_into_words": true,
|
| 80242 |
"mask_token": "[MASK]",
|
|
|
|
| 80243 |
"model_max_length": 1000000000000000019884624838656,
|
| 80244 |
"pad_token": "[PAD]",
|
| 80245 |
"padding": true,
|
|
|
|
| 80247 |
"sep_token": "[SEP]",
|
| 80248 |
"sp_model_kwargs": {},
|
| 80249 |
"split_by_punct": false,
|
|
|
|
| 80250 |
"tokenizer_class": "DebertaV2Tokenizer",
|
| 80251 |
"truncation": true,
|
|
|
|
|
|
|
| 80252 |
"unk_token": "[UNK]",
|
| 80253 |
"vocab_type": "spm"
|
| 80254 |
}
|