Update model_config.json
Browse files- model_config.json +18 -21
model_config.json
CHANGED
|
@@ -1,23 +1,20 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
],
|
| 5 |
-
"
|
| 6 |
-
|
| 7 |
-
"fuse": false,
|
| 8 |
-
"hidden_act": "gelu",
|
| 9 |
-
"hidden_dropout_prob": 0.1,
|
| 10 |
-
"hidden_size": 8,
|
| 11 |
-
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size": 8,
|
| 13 |
-
"layer_norm_eps": 1e-12,
|
| 14 |
-
"max_position_embeddings": 512,
|
| 15 |
-
"model_type": "bert",
|
| 16 |
-
"num_attention_heads": 2,
|
| 17 |
-
"num_hidden_layers": 2,
|
| 18 |
-
"pad_token_id": 0,
|
| 19 |
-
"paddlenlp_version": null,
|
| 20 |
-
"pool_act": "tanh",
|
| 21 |
-
"type_vocab_size": 2,
|
| 22 |
-
"vocab_size": 30522
|
| 23 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"init_args": [
|
| 3 |
+
{
|
| 4 |
+
"attention_probs_dropout_prob": 0.1,
|
| 5 |
+
"hidden_act": "relu",
|
| 6 |
+
"hidden_dropout_prob": 0.1,
|
| 7 |
+
"hidden_size": 8,
|
| 8 |
+
"intermediate_size": 8,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"max_position_embeddings": 512,
|
| 11 |
+
"num_attention_heads": 2,
|
| 12 |
+
"num_hidden_layers": 2,
|
| 13 |
+
"type_vocab_size": 2,
|
| 14 |
+
"vocab_size": 30522,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"init_class": "BertModel"
|
| 17 |
+
}
|
| 18 |
],
|
| 19 |
+
"init_class": "BertForMaskedLM"
|
| 20 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|