Upload tokenizer
Browse files- sentencepiece.bpe.model +2 -2
- special_tokens_map.json +6 -42
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
sentencepiece.bpe.model
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:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
|
| 3 |
+
size 808767
|
special_tokens_map.json
CHANGED
|
@@ -4,27 +4,9 @@
|
|
| 4 |
"</s>NOTUSED",
|
| 5 |
"<unk>NOTUSED"
|
| 6 |
],
|
| 7 |
-
"bos_token":
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
"normalized": false,
|
| 11 |
-
"rstrip": false,
|
| 12 |
-
"single_word": false
|
| 13 |
-
},
|
| 14 |
-
"cls_token": {
|
| 15 |
-
"content": "<s>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": false,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false
|
| 20 |
-
},
|
| 21 |
-
"eos_token": {
|
| 22 |
-
"content": "</s>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false
|
| 27 |
-
},
|
| 28 |
"mask_token": {
|
| 29 |
"content": "<mask>",
|
| 30 |
"lstrip": true,
|
|
@@ -32,25 +14,7 @@
|
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false
|
| 34 |
},
|
| 35 |
-
"pad_token":
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false
|
| 41 |
-
},
|
| 42 |
-
"sep_token": {
|
| 43 |
-
"content": "</s>",
|
| 44 |
-
"lstrip": false,
|
| 45 |
-
"normalized": false,
|
| 46 |
-
"rstrip": false,
|
| 47 |
-
"single_word": false
|
| 48 |
-
},
|
| 49 |
-
"unk_token": {
|
| 50 |
-
"content": "<unk>",
|
| 51 |
-
"lstrip": false,
|
| 52 |
-
"normalized": false,
|
| 53 |
-
"rstrip": false,
|
| 54 |
-
"single_word": false
|
| 55 |
-
}
|
| 56 |
}
|
|
|
|
| 4 |
"</s>NOTUSED",
|
| 5 |
"<unk>NOTUSED"
|
| 6 |
],
|
| 7 |
+
"bos_token": "<s>",
|
| 8 |
+
"cls_token": "<s>",
|
| 9 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"mask_token": {
|
| 11 |
"content": "<mask>",
|
| 12 |
"lstrip": true,
|
|
|
|
| 14 |
"rstrip": false,
|
| 15 |
"single_word": false
|
| 16 |
},
|
| 17 |
+
"pad_token": "<pad>",
|
| 18 |
+
"sep_token": "</s>",
|
| 19 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -75,7 +75,7 @@
|
|
| 75 |
"cls_token": "<s>",
|
| 76 |
"eos_token": "</s>",
|
| 77 |
"mask_token": "<mask>",
|
| 78 |
-
"model_max_length":
|
| 79 |
"pad_token": "<pad>",
|
| 80 |
"sep_token": "</s>",
|
| 81 |
"sp_model_kwargs": {},
|
|
|
|
| 75 |
"cls_token": "<s>",
|
| 76 |
"eos_token": "</s>",
|
| 77 |
"mask_token": "<mask>",
|
| 78 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 79 |
"pad_token": "<pad>",
|
| 80 |
"sep_token": "</s>",
|
| 81 |
"sp_model_kwargs": {},
|