zhichao yang
commited on
Commit
•
ec7b120
1
Parent(s):
5bda3fe
Upload config.json
Browse files- config.json +43 -0
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LongformerForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_mode": "longformer",
|
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 |
+
"eos_token_id": 2,
|
23 |
+
"gradient_checkpointing": false,
|
24 |
+
"hidden_act": "gelu",
|
25 |
+
"hidden_dropout_prob": 0.1,
|
26 |
+
"hidden_size": 768,
|
27 |
+
"ignore_attention_mask": false,
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"layer_norm_eps": 1e-05,
|
31 |
+
"max_position_embeddings": 16386,
|
32 |
+
"model_type": "longformer",
|
33 |
+
"num_attention_heads": 12,
|
34 |
+
"num_hidden_layers": 12,
|
35 |
+
"pad_token_id": 1,
|
36 |
+
"position_embedding_type": "absolute",
|
37 |
+
"sep_token_id": 2,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.8.1",
|
40 |
+
"type_vocab_size": 1,
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 50265
|
43 |
+
}
|