Commit
·
d86e03b
1
Parent(s):
19008c7
update model
Browse files- config.json +45 -40
config.json
CHANGED
|
@@ -1,40 +1,45 @@
|
|
| 1 |
-
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
"
|
| 7 |
-
|
| 8 |
-
512,
|
| 9 |
-
512,
|
| 10 |
-
512,
|
| 11 |
-
512,
|
| 12 |
-
512,
|
| 13 |
-
512,
|
| 14 |
-
512,
|
| 15 |
-
512,
|
| 16 |
-
512,
|
| 17 |
-
512,
|
| 18 |
-
512
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
-
"
|
| 27 |
-
"
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "H:\\RA\\longformer_full",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LongformerModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"attention_window": [
|
| 8 |
+
512,
|
| 9 |
+
512,
|
| 10 |
+
512,
|
| 11 |
+
512,
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"bos_token_id": 0,
|
| 22 |
+
"directionality": "bidi",
|
| 23 |
+
"eos_token_id": 2,
|
| 24 |
+
"gradient_checkpointing": false,
|
| 25 |
+
"hidden_act": "gelu",
|
| 26 |
+
"hidden_dropout_prob": 0.1,
|
| 27 |
+
"hidden_size": 768,
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"intermediate_size": 3072,
|
| 30 |
+
"layer_norm_eps": 1e-12,
|
| 31 |
+
"max_position_embeddings": 4096,
|
| 32 |
+
"model_type": "longformer",
|
| 33 |
+
"num_attention_heads": 12,
|
| 34 |
+
"num_hidden_layers": 12,
|
| 35 |
+
"pad_token_id": 0,
|
| 36 |
+
"pooler_fc_size": 768,
|
| 37 |
+
"pooler_num_attention_heads": 12,
|
| 38 |
+
"pooler_num_fc_layers": 3,
|
| 39 |
+
"pooler_size_per_head": 128,
|
| 40 |
+
"pooler_type": "first_token_transform",
|
| 41 |
+
"position_embedding_type": "absolute",
|
| 42 |
+
"sep_token_id": 2,
|
| 43 |
+
"type_vocab_size": 2,
|
| 44 |
+
"vocab_size": 21128
|
| 45 |
+
}
|