Replaced pretrained model with English BERT fine-tuned to Javanese corpus
Browse files- config.json +4 -4
- pytorch_model.bin +2 -2
- tf_model.h5 +2 -2
- tokenizer_config.json +1 -1
- vocab.txt +0 -0
config.json
CHANGED
@@ -11,14 +11,14 @@
|
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 3072,
|
13 |
"layer_norm_eps": 1e-12,
|
14 |
-
"max_position_embeddings":
|
15 |
"model_type": "bert",
|
16 |
"num_attention_heads": 12,
|
17 |
-
"num_hidden_layers":
|
18 |
"pad_token_id": 0,
|
19 |
"position_embedding_type": "absolute",
|
20 |
"transformers_version": "4.3.3",
|
21 |
-
"type_vocab_size":
|
22 |
"use_cache": true,
|
23 |
-
"vocab_size":
|
24 |
}
|
|
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 3072,
|
13 |
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
"model_type": "bert",
|
16 |
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
"pad_token_id": 0,
|
19 |
"position_embedding_type": "absolute",
|
20 |
"transformers_version": "4.3.3",
|
21 |
+
"type_vocab_size": 2,
|
22 |
"use_cache": true,
|
23 |
+
"vocab_size": 30522
|
24 |
}
|
pytorch_model.bin
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 sha256:69122da68fd9d0f40c5e9890d5f5f473dc66c4729f3f01f90d8bb5cf45cb30fc
|
3 |
+
size 438147282
|
tf_model.h5
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 sha256:515417145dd960b5b855c688daf8355b5f0db8a7f2b351be56e0d1efbb776c04
|
3 |
+
size 532092720
|
tokenizer_config.json
CHANGED
@@ -1 +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": "./
|
|
|
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": "./java_tokens", "do_basic_tokenize": true, "never_split": null}
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|