fix: tokenizer fix
Browse files- sentencepiece.bpe.model +2 -2
- special_tokens_map.json +7 -1
- 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 sha256:34e9d938fbab77d2bb4acd48953c66bb7ad2d0b675b4c0911e6ed25caf20acd6
|
| 3 |
+
size 1270564
|
special_tokens_map.json
CHANGED
|
@@ -2,7 +2,13 @@
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"cls_token": "<s>",
|
| 4 |
"eos_token": "</s>",
|
| 5 |
-
"mask_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"pad_token": "<pad>",
|
| 7 |
"sep_token": "</s>",
|
| 8 |
"unk_token": "<unk>"
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"cls_token": "<s>",
|
| 4 |
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
"pad_token": "<pad>",
|
| 13 |
"sep_token": "</s>",
|
| 14 |
"unk_token": "<unk>"
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -11,7 +11,7 @@
|
|
| 11 |
"rstrip": false,
|
| 12 |
"single_word": false
|
| 13 |
},
|
| 14 |
-
"model_max_length":
|
| 15 |
"pad_token": "<pad>",
|
| 16 |
"sep_token": "</s>",
|
| 17 |
"sp_model_kwargs": {},
|
|
|
|
| 11 |
"rstrip": false,
|
| 12 |
"single_word": false
|
| 13 |
},
|
| 14 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 15 |
"pad_token": "<pad>",
|
| 16 |
"sep_token": "</s>",
|
| 17 |
"sp_model_kwargs": {},
|