KPMGhyesukim
commited on
Commit
•
11d9872
1
Parent(s):
3327322
update model config
Browse files- config.json +9 -23
config.json
CHANGED
@@ -1,36 +1,22 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"architectures": [
|
4 |
-
"DebertaV2Model"
|
5 |
-
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"hidden_act": "gelu",
|
8 |
"hidden_dropout_prob": 0.1,
|
9 |
"hidden_size": 768,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 3072,
|
12 |
-
"layer_norm_eps": 1e-07,
|
13 |
"max_position_embeddings": 512,
|
14 |
-
"
|
15 |
-
"
|
16 |
"norm_rel_ebd": "layer_norm",
|
|
|
|
|
|
|
|
|
|
|
17 |
"num_attention_heads": 12,
|
18 |
"num_hidden_layers": 12,
|
19 |
-
"pad_token_id": 0,
|
20 |
-
"padding_idx": 0,
|
21 |
-
"pooler_dropout": 0,
|
22 |
-
"pooler_hidden_act": "gelu",
|
23 |
-
"pooler_hidden_size": 768,
|
24 |
-
"pos_att_type": [
|
25 |
-
"p2c",
|
26 |
-
"c2p"
|
27 |
-
],
|
28 |
-
"position_biased_input": false,
|
29 |
-
"position_buckets": 256,
|
30 |
-
"relative_attention": true,
|
31 |
-
"share_att_key": true,
|
32 |
-
"torch_dtype": "float32",
|
33 |
-
"transformers_version": "4.15.0",
|
34 |
"type_vocab_size": 0,
|
35 |
"vocab_size": 251000
|
36 |
-
}
|
|
|
1 |
{
|
2 |
+
"model_type": "deberta-v2",
|
|
|
|
|
|
|
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 |
+
"relative_attention": true,
|
11 |
+
"position_buckets": 256,
|
12 |
"norm_rel_ebd": "layer_norm",
|
13 |
+
"share_att_key": true,
|
14 |
+
"pos_att_type": "p2c|c2p",
|
15 |
+
"layer_norm_eps": 1e-7,
|
16 |
+
"max_relative_positions": -1,
|
17 |
+
"position_biased_input": false,
|
18 |
"num_attention_heads": 12,
|
19 |
"num_hidden_layers": 12,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"type_vocab_size": 0,
|
21 |
"vocab_size": 251000
|
22 |
+
}
|