Replaced pretrained model with English BERT fine-tuned to Javanese corpus

config.json

@@ -11,14 +11,14 @@
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 514,
+  "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "transformers_version": "4.3.3",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 52000
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:734a01ef999f6e039c7ebfedb0dbd55c5cf51ff0e1143eadf2cf22c8a28dcf4c
-size 334067058
+oid sha256:69122da68fd9d0f40c5e9890d5f5f473dc66c4729f3f01f90d8bb5cf45cb30fc
+size 438147282

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e03dfbd7b08471b29960a6bb07a2a04fb1d8b49d85e1ecba8d8ba0de5ccce6f
-size 493911936
+oid sha256:515417145dd960b5b855c688daf8355b5f0db8a7f2b351be56e0d1efbb776c04
+size 532092720

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "./JavaneseBERT", "do_basic_tokenize": true, "never_split": null}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "./java_tokens", "do_basic_tokenize": true, "never_split": null}