Upload generator_config.json
Browse files- generator_config.json +24 -0
generator_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 384,
|
| 7 |
+
"initializer_range": 0.02,
|
| 8 |
+
"intermediate_size": 1536,
|
| 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": 6,
|
| 19 |
+
"num_hidden_layers": 6,
|
| 20 |
+
"z_steps": 2,
|
| 21 |
+
"type_vocab_size": 0,
|
| 22 |
+
"vocab_size": 128000,
|
| 23 |
+
"dtype": "float16"
|
| 24 |
+
}
|