Commit
•
9b6343b
1
Parent(s):
8c4f939
nezha
Browse files
nezha-base-wwm/bert4torch_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_probs_dropout_prob": 0.1,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"classifier_dropout": 0.1,
|
| 5 |
+
"embedding_size": 128,
|
| 6 |
+
"eos_token_id": 3,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"inner_group_num": 1,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"max_relative_position": 64,
|
| 16 |
+
"model": "nezha",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_groups": 1,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"use_relative_position": true,
|
| 25 |
+
"vocab_size": 21128
|
| 26 |
+
}
|
nezha-cn-base/bert4torch_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"max_relative_position": 64,
|
| 10 |
+
"num_attention_heads": 12,
|
| 11 |
+
"num_hidden_layers": 12,
|
| 12 |
+
"type_vocab_size": 2,
|
| 13 |
+
"vocab_size": 21128,
|
| 14 |
+
"use_relative_position": true,
|
| 15 |
+
"model": "nezha"
|
| 16 |
+
}
|
nezha-cn-large/bert4torch_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_probs_dropout_prob": 0.1,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"classifier_dropout": 0.1,
|
| 5 |
+
"embedding_size": 128,
|
| 6 |
+
"eos_token_id": 3,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 1024,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 4096,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_position": 64,
|
| 15 |
+
"model": "nezha",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"torch_dtype": "float32",
|
| 20 |
+
"type_vocab_size": 2,
|
| 21 |
+
"use_cache": true,
|
| 22 |
+
"use_relative_position": true,
|
| 23 |
+
"vocab_size": 21128
|
| 24 |
+
}
|
nezha-large-wwm/bert4torch_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_probs_dropout_prob": 0.1,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"classifier_dropout": 0.1,
|
| 5 |
+
"embedding_size": 128,
|
| 6 |
+
"eos_token_id": 3,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 1024,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 4096,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_position": 64,
|
| 15 |
+
"model": "nezha",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"torch_dtype": "float32",
|
| 20 |
+
"type_vocab_size": 2,
|
| 21 |
+
"use_cache": true,
|
| 22 |
+
"use_relative_position": true,
|
| 23 |
+
"vocab_size": 21128
|
| 24 |
+
}
|