SEO
commited on
Commit
·
bc8845f
1
Parent(s):
198c391
Upload tokenizer files
Browse files- id2binary_mask.json +0 -0
- id2csp_feature.json +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- vocab.json +0 -0
id2binary_mask.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
id2csp_feature.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:ab7bab66288e9b9afef77bf6048cc92e62296284d26e855aa1c87049760404fb
|
3 |
+
size 33699819
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"model": "wordlevel", "vocab_size": 8287, "unk_token": "[UNK]", "special_tokens": ["[PAD]", "[UNK]"]}
|
|
|
1 |
+
{"model": "wordlevel", "vocab_size": 8287, "unk_token": "[UNK]", "pad_token": "[PAD]", "mask_token": "[MASK]", "special_tokens": ["[PAD]", "[UNK]", "[MASK]"]}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|