add model
Browse files- adapter_config.json +12 -37
- pytorch_adapter.bin +2 -2
adapter_config.json
CHANGED
@@ -1,43 +1,18 @@
|
|
1 |
{
|
2 |
"config": {
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
7 |
-
|
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 |
-
[
|
15 |
-
6,
|
16 |
-
7,
|
17 |
-
8,
|
18 |
-
9,
|
19 |
-
10,
|
20 |
-
11
|
21 |
-
]
|
22 |
],
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"phm_bias": true,
|
31 |
-
"phm_c_init": "normal",
|
32 |
-
"phm_dim": 4,
|
33 |
-
"phm_init_range": 0.0001,
|
34 |
-
"phm_layer": false,
|
35 |
-
"phm_rank": 1,
|
36 |
-
"reduction_factor": 16,
|
37 |
-
"residual_before_ln": true,
|
38 |
-
"scaling": 1.0,
|
39 |
-
"shared_W_phm": false,
|
40 |
-
"shared_phm_rule": true,
|
41 |
"use_gating": false
|
42 |
},
|
43 |
"hidden_size": 768,
|
|
|
1 |
{
|
2 |
"config": {
|
3 |
+
"alpha": 16,
|
4 |
+
"architecture": "lora",
|
5 |
+
"attn_matrices": [
|
6 |
+
"q",
|
7 |
+
"v"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
],
|
9 |
+
"composition_mode": "add",
|
10 |
+
"dropout": 0.0,
|
11 |
+
"init_weights": "lora",
|
12 |
+
"intermediate_lora": false,
|
13 |
+
"output_lora": false,
|
14 |
+
"r": 8,
|
15 |
+
"selfattn_lora": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"use_gating": false
|
17 |
},
|
18 |
"hidden_size": 768,
|
pytorch_adapter.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b892274670ddf7b7ab6d0c8015893bfbbb71982e6ff71b3b7c5dd9d9168677dc
|
3 |
+
size 1794061
|