Upload tokenizer matching best CV model
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +5 -43
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:a43a63895b18495744e1f257fa161958c578612ec67b8e0b20d24d93cbcc56b9
|
| 3 |
+
size 16014625
|
tokenizer_config.json
CHANGED
|
@@ -1,52 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
"content": "[PAD]",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
-
"content": "[CLS]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "[SEP]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "[UNK]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": true,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"250101": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
"bos_token": "[CLS]",
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
"cls_token": "[CLS]",
|
| 47 |
"do_lower_case": false,
|
| 48 |
"eos_token": "[SEP]",
|
| 49 |
-
"
|
|
|
|
| 50 |
"mask_token": "[MASK]",
|
| 51 |
"model_max_length": 512,
|
| 52 |
"pad_token": "[PAD]",
|
|
@@ -54,6 +15,7 @@
|
|
| 54 |
"sp_model_kwargs": {},
|
| 55 |
"split_by_punct": false,
|
| 56 |
"tokenizer_class": "DebertaV2Tokenizer",
|
|
|
|
| 57 |
"unk_token": "[UNK]",
|
| 58 |
"vocab_type": "spm"
|
| 59 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"bos_token": "[CLS]",
|
| 5 |
"clean_up_tokenization_spaces": true,
|
| 6 |
"cls_token": "[CLS]",
|
| 7 |
"do_lower_case": false,
|
| 8 |
"eos_token": "[SEP]",
|
| 9 |
+
"is_local": true,
|
| 10 |
+
"local_files_only": false,
|
| 11 |
"mask_token": "[MASK]",
|
| 12 |
"model_max_length": 512,
|
| 13 |
"pad_token": "[PAD]",
|
|
|
|
| 15 |
"sp_model_kwargs": {},
|
| 16 |
"split_by_punct": false,
|
| 17 |
"tokenizer_class": "DebertaV2Tokenizer",
|
| 18 |
+
"unk_id": 3,
|
| 19 |
"unk_token": "[UNK]",
|
| 20 |
"vocab_type": "spm"
|
| 21 |
}
|