Upload tokenizer
Browse files- added_tokens.json +27 -0
- special_tokens_map.json +35 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000,
|
| 3 |
+
"[R-0]": 128001,
|
| 4 |
+
"[R-10]": 128011,
|
| 5 |
+
"[R-11]": 128012,
|
| 6 |
+
"[R-12]": 128013,
|
| 7 |
+
"[R-13]": 128014,
|
| 8 |
+
"[R-14]": 128015,
|
| 9 |
+
"[R-15]": 128016,
|
| 10 |
+
"[R-16]": 128017,
|
| 11 |
+
"[R-17]": 128018,
|
| 12 |
+
"[R-18]": 128019,
|
| 13 |
+
"[R-19]": 128020,
|
| 14 |
+
"[R-1]": 128002,
|
| 15 |
+
"[R-20]": 128021,
|
| 16 |
+
"[R-21]": 128022,
|
| 17 |
+
"[R-22]": 128023,
|
| 18 |
+
"[R-23]": 128024,
|
| 19 |
+
"[R-2]": 128003,
|
| 20 |
+
"[R-3]": 128004,
|
| 21 |
+
"[R-4]": 128005,
|
| 22 |
+
"[R-5]": 128006,
|
| 23 |
+
"[R-6]": 128007,
|
| 24 |
+
"[R-7]": 128008,
|
| 25 |
+
"[R-8]": 128009,
|
| 26 |
+
"[R-9]": 128010
|
| 27 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"[R-0]",
|
| 4 |
+
"[R-1]",
|
| 5 |
+
"[R-2]",
|
| 6 |
+
"[R-3]",
|
| 7 |
+
"[R-4]",
|
| 8 |
+
"[R-5]",
|
| 9 |
+
"[R-6]",
|
| 10 |
+
"[R-7]",
|
| 11 |
+
"[R-8]",
|
| 12 |
+
"[R-9]",
|
| 13 |
+
"[R-10]",
|
| 14 |
+
"[R-11]",
|
| 15 |
+
"[R-12]",
|
| 16 |
+
"[R-13]",
|
| 17 |
+
"[R-14]",
|
| 18 |
+
"[R-15]",
|
| 19 |
+
"[R-16]",
|
| 20 |
+
"[R-17]",
|
| 21 |
+
"[R-18]",
|
| 22 |
+
"[R-19]",
|
| 23 |
+
"[R-20]",
|
| 24 |
+
"[R-21]",
|
| 25 |
+
"[R-22]",
|
| 26 |
+
"[R-23]"
|
| 27 |
+
],
|
| 28 |
+
"bos_token": "[CLS]",
|
| 29 |
+
"cls_token": "[CLS]",
|
| 30 |
+
"eos_token": "[SEP]",
|
| 31 |
+
"mask_token": "[MASK]",
|
| 32 |
+
"pad_token": "[PAD]",
|
| 33 |
+
"sep_token": "[SEP]",
|
| 34 |
+
"unk_token": "[UNK]"
|
| 35 |
+
}
|
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
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"additional_special_tokens": [
|
| 4 |
+
"[R-0]",
|
| 5 |
+
"[R-1]",
|
| 6 |
+
"[R-2]",
|
| 7 |
+
"[R-3]",
|
| 8 |
+
"[R-4]",
|
| 9 |
+
"[R-5]",
|
| 10 |
+
"[R-6]",
|
| 11 |
+
"[R-7]",
|
| 12 |
+
"[R-8]",
|
| 13 |
+
"[R-9]",
|
| 14 |
+
"[R-10]",
|
| 15 |
+
"[R-11]",
|
| 16 |
+
"[R-12]",
|
| 17 |
+
"[R-13]",
|
| 18 |
+
"[R-14]",
|
| 19 |
+
"[R-15]",
|
| 20 |
+
"[R-16]",
|
| 21 |
+
"[R-17]",
|
| 22 |
+
"[R-18]",
|
| 23 |
+
"[R-19]",
|
| 24 |
+
"[R-20]",
|
| 25 |
+
"[R-21]",
|
| 26 |
+
"[R-22]",
|
| 27 |
+
"[R-23]"
|
| 28 |
+
],
|
| 29 |
+
"bos_token": "[CLS]",
|
| 30 |
+
"clean_up_tokenization_spaces": true,
|
| 31 |
+
"cls_token": "[CLS]",
|
| 32 |
+
"do_lower_case": false,
|
| 33 |
+
"eos_token": "[SEP]",
|
| 34 |
+
"mask_token": "[MASK]",
|
| 35 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": "[PAD]",
|
| 37 |
+
"sep_token": "[SEP]",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"split_by_punct": false,
|
| 40 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 41 |
+
"unk_token": "[UNK]",
|
| 42 |
+
"vocab_type": "spm"
|
| 43 |
+
}
|