Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +7 -13
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -12
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -1,15 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "
|
| 3 |
-
"cls_token": "
|
| 4 |
-
"eos_token": "
|
| 5 |
-
"mask_token":
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false
|
| 11 |
-
},
|
| 12 |
-
"pad_token": "<pad>",
|
| 13 |
-
"sep_token": "</s>",
|
| 14 |
-
"unk_token": "<unk>"
|
| 15 |
}
|
|
|
|
| 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:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,15 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"bos_token": "<s>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
-
"cls_token": "
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"mask_token": "
|
| 9 |
-
"model_max_length":
|
| 10 |
-
"pad_token": "
|
| 11 |
-
"sep_token": "
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
|
|
|
|
|
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "[CLS]",
|
|
|
|
| 3 |
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"eos_token": "[SEP]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"split_by_punct": false,
|
| 13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 14 |
+
"unk_token": "[UNK]",
|
| 15 |
+
"vocab_type": "spm"
|
| 16 |
}
|