anas-awadalla
commited on
Commit
•
64b5586
1
Parent(s):
e565779
Model save
Browse files- squad/adapter_config.json +40 -0
- squad/head_config.json +14 -0
- squad/pytorch_adapter.bin +3 -0
- squad/pytorch_model_head.bin +3 -0
- training_args.bin +1 -1
squad/adapter_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": {
|
3 |
+
"adapter_residual_before_ln": false,
|
4 |
+
"cross_adapter": false,
|
5 |
+
"factorized_phm_W": true,
|
6 |
+
"factorized_phm_rule": false,
|
7 |
+
"hypercomplex_nonlinearity": "glorot-uniform",
|
8 |
+
"init_weights": "bert",
|
9 |
+
"inv_adapter": null,
|
10 |
+
"inv_adapter_reduction_factor": null,
|
11 |
+
"is_parallel": false,
|
12 |
+
"learn_phm": true,
|
13 |
+
"leave_out": [],
|
14 |
+
"ln_after": false,
|
15 |
+
"ln_before": false,
|
16 |
+
"mh_adapter": true,
|
17 |
+
"non_linearity": "swish",
|
18 |
+
"original_ln_after": true,
|
19 |
+
"original_ln_before": false,
|
20 |
+
"output_adapter": true,
|
21 |
+
"phm_bias": true,
|
22 |
+
"phm_c_init": "normal",
|
23 |
+
"phm_dim": 4,
|
24 |
+
"phm_init_range": 0.0001,
|
25 |
+
"phm_layer": false,
|
26 |
+
"phm_rank": 1,
|
27 |
+
"reduction_factor": 16,
|
28 |
+
"residual_before_ln": true,
|
29 |
+
"scaling": 1.0,
|
30 |
+
"shared_W_phm": false,
|
31 |
+
"shared_phm_rule": true
|
32 |
+
},
|
33 |
+
"config_id": "b1017368d7a97b11",
|
34 |
+
"hidden_size": 1024,
|
35 |
+
"model_class": "RobertaForQuestionAnswering",
|
36 |
+
"model_name": "roberta-large",
|
37 |
+
"model_type": "roberta",
|
38 |
+
"name": "squad",
|
39 |
+
"version": "3.0.0"
|
40 |
+
}
|
squad/head_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": null,
|
3 |
+
"hidden_size": 1024,
|
4 |
+
"label2id": {
|
5 |
+
"LABEL_0": 0,
|
6 |
+
"LABEL_1": 1
|
7 |
+
},
|
8 |
+
"model_class": "RobertaForQuestionAnswering",
|
9 |
+
"model_name": "roberta-large",
|
10 |
+
"model_type": "roberta",
|
11 |
+
"name": null,
|
12 |
+
"num_labels": 2,
|
13 |
+
"version": "3.0.0"
|
14 |
+
}
|
squad/pytorch_adapter.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0e12e43f8f7580d23722e09d739179bb6209144561962f5727bf0b4c555ae45
|
3 |
+
size 25442881
|
squad/pytorch_model_head.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93bfab5b3c7ad7ed44a9edc8bf3be020ed2703ce394a0c63d64689236f6d59fc
|
3 |
+
size 9191
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3055
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb76498c427d3ae8a3425998bb6e6146a8f0ce3b8414eba77ba0aaa3b31b23fa
|
3 |
size 3055
|