Upload config.json
Browse files- config.json +26 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ElectraForPreTraining"
|
| 4 |
+
],
|
| 5 |
+
"model_type": "electra",
|
| 6 |
+
"model_name": "base",
|
| 7 |
+
"vocab_size": 30112,
|
| 8 |
+
"embedding_size": 768,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"num_hidden_layers": 12,
|
| 11 |
+
"num_attention_heads": 12,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0.1,
|
| 15 |
+
"attention_probs_dropout_prob": 0.1,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"type_vocab_size": 2,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"summary_type": "first",
|
| 21 |
+
"summary_use_proj": true,
|
| 22 |
+
"summary_activation": "gelu",
|
| 23 |
+
"summary_last_dropout": 0.1,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"position_embedding_type": "absolute"
|
| 26 |
+
}
|