Samuel Cahyawijaya
commited on
Commit
·
f09b6f6
1
Parent(s):
cdb45df
update model & tokenizer meta
Browse files- config.json +1 -1
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
@@ -28,5 +28,5 @@
|
|
28 |
}
|
29 |
},
|
30 |
"tokenizer_class": "IndoNLGTokenizer",
|
31 |
-
"vocab_size":
|
32 |
}
|
|
|
28 |
}
|
29 |
},
|
30 |
"tokenizer_class": "IndoNLGTokenizer",
|
31 |
+
"vocab_size": 40005
|
32 |
}
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["[java]", "[sunda]", "[indonesia]", "<mask>"
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["[java]", "[sunda]", "[indonesia]", "<mask>"]}
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["[java]", "[sunda]", "[indonesia]", "<mask>"
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["[java]", "[sunda]", "[indonesia]", "<mask>"]}
|