Commit
•
6590e30
1
Parent(s):
e37c875
cusomize vilbert for models
Browse files- bert_base_6layer_6conect.json +30 -0
- config.json +31 -0
- pretrained_model.bin +3 -0
bert_base_6layer_6conect.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_probs_dropout_prob": 0.1,
|
| 3 |
+
"hidden_act": "gelu",
|
| 4 |
+
"hidden_dropout_prob": 0.1,
|
| 5 |
+
"hidden_size": 768,
|
| 6 |
+
"initializer_range": 0.02,
|
| 7 |
+
"intermediate_size": 3072,
|
| 8 |
+
"max_position_embeddings": 512,
|
| 9 |
+
"num_attention_heads": 12,
|
| 10 |
+
"num_hidden_layers": 12,
|
| 11 |
+
"type_vocab_size": 2,
|
| 12 |
+
"vocab_size": 30522,
|
| 13 |
+
"v_feature_size": 2048,
|
| 14 |
+
"v_target_size": 1601,
|
| 15 |
+
"v_hidden_size": 1024,
|
| 16 |
+
"v_num_hidden_layers":6,
|
| 17 |
+
"v_num_attention_heads":8,
|
| 18 |
+
"v_intermediate_size":1024,
|
| 19 |
+
"bi_hidden_size":1024,
|
| 20 |
+
"bi_num_attention_heads":8,
|
| 21 |
+
"bi_intermediate_size": 1024,
|
| 22 |
+
"bi_attention_type":1,
|
| 23 |
+
"v_attention_probs_dropout_prob":0.1,
|
| 24 |
+
"v_hidden_act":"gelu",
|
| 25 |
+
"v_hidden_dropout_prob":0.1,
|
| 26 |
+
"v_initializer_range":0.02,
|
| 27 |
+
"v_biattention_id":[0, 1, 2, 3, 4, 5],
|
| 28 |
+
"t_biattention_id":[6, 7, 8, 9, 10, 11],
|
| 29 |
+
"pooling_method": "mul"
|
| 30 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "vilbert",
|
| 3 |
+
"attention_probs_dropout_prob": 0.1,
|
| 4 |
+
"hidden_act": "gelu",
|
| 5 |
+
"hidden_dropout_prob": 0.1,
|
| 6 |
+
"hidden_size": 768,
|
| 7 |
+
"initializer_range": 0.02,
|
| 8 |
+
"intermediate_size": 3072,
|
| 9 |
+
"max_position_embeddings": 512,
|
| 10 |
+
"num_attention_heads": 12,
|
| 11 |
+
"num_hidden_layers": 12,
|
| 12 |
+
"type_vocab_size": 2,
|
| 13 |
+
"vocab_size": 30522,
|
| 14 |
+
"v_feature_size": 2048,
|
| 15 |
+
"v_target_size": 1601,
|
| 16 |
+
"v_hidden_size": 1024,
|
| 17 |
+
"v_num_hidden_layers":6,
|
| 18 |
+
"v_num_attention_heads":8,
|
| 19 |
+
"v_intermediate_size":1024,
|
| 20 |
+
"bi_hidden_size":1024,
|
| 21 |
+
"bi_num_attention_heads":8,
|
| 22 |
+
"bi_intermediate_size": 1024,
|
| 23 |
+
"bi_attention_type":1,
|
| 24 |
+
"v_attention_probs_dropout_prob":0.1,
|
| 25 |
+
"v_hidden_act":"gelu",
|
| 26 |
+
"v_hidden_dropout_prob":0.1,
|
| 27 |
+
"v_initializer_range":0.02,
|
| 28 |
+
"v_biattention_id":[0, 1, 2, 3, 4, 5],
|
| 29 |
+
"t_biattention_id":[6, 7, 8, 9, 10, 11],
|
| 30 |
+
"pooling_method": "mul"
|
| 31 |
+
}
|
pretrained_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:099f90a9729875d368472e27d37a7ff58f2c2f1a698eaf2143afac4f0e6a251b
|
| 3 |
+
size 1000309647
|