Commit
•
8c4f939
1
Parent(s):
1dfa574
add albert
Browse files- albert_chinese_base/bert4torch_config.json +27 -0
- albert_chinese_large/bert4torch_config.json +27 -0
- albert_chinese_small/bert4torch_config.json +26 -0
- albert_chinese_tiny/bert4torch_config.json +26 -0
- albert_chinese_xlarge/bert4torch_config.json +27 -0
- albert_chinese_xxlarge/bert4torch_config.json +27 -0
albert_chinese_base/bert4torch_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_probs_dropout_prob": 0,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"classifier_dropout_prob": 0.1,
|
5 |
+
"down_scale_factor": 1,
|
6 |
+
"embedding_size": 128,
|
7 |
+
"eos_token_id": 3,
|
8 |
+
"gap_size": 0,
|
9 |
+
"hidden_act": "relu",
|
10 |
+
"hidden_dropout_prob": 0,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"inner_group_num": 1,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"layers_to_keep": [],
|
17 |
+
"max_position_embeddings": 512,
|
18 |
+
"model": "albert",
|
19 |
+
"net_structure_type": 0,
|
20 |
+
"num_attention_heads": 12,
|
21 |
+
"num_hidden_groups": 1,
|
22 |
+
"num_hidden_layers": 12,
|
23 |
+
"num_memory_blocks": 0,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"vocab_size": 21128
|
27 |
+
}
|
albert_chinese_large/bert4torch_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_probs_dropout_prob": 0,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"classifier_dropout_prob": 0.1,
|
5 |
+
"down_scale_factor": 1,
|
6 |
+
"embedding_size": 128,
|
7 |
+
"eos_token_id": 3,
|
8 |
+
"gap_size": 0,
|
9 |
+
"hidden_act": "relu",
|
10 |
+
"hidden_dropout_prob": 0,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"inner_group_num": 1,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"layers_to_keep": [],
|
17 |
+
"max_position_embeddings": 512,
|
18 |
+
"model": "albert",
|
19 |
+
"net_structure_type": 0,
|
20 |
+
"num_attention_heads": 16,
|
21 |
+
"num_hidden_groups": 1,
|
22 |
+
"num_hidden_layers": 24,
|
23 |
+
"num_memory_blocks": 0,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"vocab_size": 21128
|
27 |
+
}
|
albert_chinese_small/bert4torch_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_probs_dropout_prob": 0.0,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"classifier_dropout_prob": 0.1,
|
5 |
+
"down_scale_factor": 1,
|
6 |
+
"embedding_size": 128,
|
7 |
+
"eos_token_id": 3,
|
8 |
+
"gap_size": 0,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.0,
|
11 |
+
"hidden_size": 384,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"inner_group_num": 1,
|
14 |
+
"intermediate_size": 1536,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model": "albert",
|
18 |
+
"net_structure_type": 0,
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_groups": 1,
|
21 |
+
"num_hidden_layers": 6,
|
22 |
+
"num_memory_blocks": 0,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"vocab_size": 21128
|
26 |
+
}
|
albert_chinese_tiny/bert4torch_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_probs_dropout_prob": 0.0,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"classifier_dropout_prob": 0.1,
|
5 |
+
"down_scale_factor": 1,
|
6 |
+
"embedding_size": 128,
|
7 |
+
"eos_token_id": 3,
|
8 |
+
"gap_size": 0,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.0,
|
11 |
+
"hidden_size": 312,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"inner_group_num": 1,
|
14 |
+
"intermediate_size": 1248,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model": "albert",
|
18 |
+
"net_structure_type": 0,
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_groups": 1,
|
21 |
+
"num_hidden_layers": 4,
|
22 |
+
"num_memory_blocks": 0,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"vocab_size": 21128
|
26 |
+
}
|
albert_chinese_xlarge/bert4torch_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_probs_dropout_prob": 0,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"classifier_dropout_prob": 0.1,
|
5 |
+
"down_scale_factor": 1,
|
6 |
+
"embedding_size": 128,
|
7 |
+
"eos_token_id": 3,
|
8 |
+
"gap_size": 0,
|
9 |
+
"hidden_act": "relu",
|
10 |
+
"hidden_dropout_prob": 0,
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.014,
|
13 |
+
"inner_group_num": 1,
|
14 |
+
"intermediate_size": 8192,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"layers_to_keep": [],
|
17 |
+
"max_position_embeddings": 512,
|
18 |
+
"model": "albert",
|
19 |
+
"net_structure_type": 0,
|
20 |
+
"num_attention_heads": 16,
|
21 |
+
"num_hidden_groups": 1,
|
22 |
+
"num_hidden_layers": 24,
|
23 |
+
"num_memory_blocks": 0,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"vocab_size": 21128
|
27 |
+
}
|
albert_chinese_xxlarge/bert4torch_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_probs_dropout_prob": 0,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"classifier_dropout_prob": 0.1,
|
5 |
+
"down_scale_factor": 1,
|
6 |
+
"embedding_size": 128,
|
7 |
+
"eos_token_id": 3,
|
8 |
+
"gap_size": 0,
|
9 |
+
"hidden_act": "relu",
|
10 |
+
"hidden_dropout_prob": 0,
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.01,
|
13 |
+
"inner_group_num": 1,
|
14 |
+
"intermediate_size": 16384,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"layers_to_keep": [],
|
17 |
+
"max_position_embeddings": 512,
|
18 |
+
"model": "albert",
|
19 |
+
"net_structure_type": 0,
|
20 |
+
"num_attention_heads": 16,
|
21 |
+
"num_hidden_groups": 1,
|
22 |
+
"num_hidden_layers": 12,
|
23 |
+
"num_memory_blocks": 0,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"vocab_size": 21128
|
27 |
+
}
|