tf
Browse files- config.json +24 -16
- tf_model.h5 +2 -2
config.json
CHANGED
@@ -1,22 +1,30 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"BertForMaskedLM"
|
4 |
],
|
5 |
-
"attention_probs_dropout_prob": 0.1,
|
6 |
-
"directionality": "bidi",
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"vocab_size": 21128
|
22 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/data/yechen/bert/bert-base-chinese-jinyong",
|
3 |
"architectures": [
|
4 |
"BertForMaskedLM"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"directionality": "bidi",
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"transformers_version": "4.3.3",
|
27 |
+
"type_vocab_size": 2,
|
28 |
+
"use_cache": true,
|
29 |
"vocab_size": 21128
|
30 |
}
|
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 sha256:4a6165c2a0503dc66f67dc227a59af0174b45f72d0ae730f45ad5298e2cd5695
|
3 |
+
size 476719784
|