Upload 4 files
Browse files- adapter_config.json +41 -0
- head_config.json +27 -0
- pytorch_adapter.bin +3 -0
- pytorch_model_head.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"adapter_residual_before_ln": false,
|
| 4 |
+
"cross_adapter": false,
|
| 5 |
+
"dropout": 0.0,
|
| 6 |
+
"factorized_phm_W": true,
|
| 7 |
+
"factorized_phm_rule": false,
|
| 8 |
+
"hypercomplex_nonlinearity": "glorot-uniform",
|
| 9 |
+
"init_weights": "bert",
|
| 10 |
+
"inv_adapter": null,
|
| 11 |
+
"inv_adapter_reduction_factor": null,
|
| 12 |
+
"is_parallel": false,
|
| 13 |
+
"learn_phm": true,
|
| 14 |
+
"leave_out": [],
|
| 15 |
+
"ln_after": false,
|
| 16 |
+
"ln_before": false,
|
| 17 |
+
"mh_adapter": false,
|
| 18 |
+
"non_linearity": "relu",
|
| 19 |
+
"original_ln_after": true,
|
| 20 |
+
"original_ln_before": true,
|
| 21 |
+
"output_adapter": true,
|
| 22 |
+
"phm_bias": true,
|
| 23 |
+
"phm_c_init": "normal",
|
| 24 |
+
"phm_dim": 4,
|
| 25 |
+
"phm_init_range": 0.0001,
|
| 26 |
+
"phm_layer": false,
|
| 27 |
+
"phm_rank": 1,
|
| 28 |
+
"reduction_factor": 16,
|
| 29 |
+
"residual_before_ln": true,
|
| 30 |
+
"scaling": 1.0,
|
| 31 |
+
"shared_W_phm": false,
|
| 32 |
+
"shared_phm_rule": true,
|
| 33 |
+
"use_gating": false
|
| 34 |
+
},
|
| 35 |
+
"hidden_size": 768,
|
| 36 |
+
"model_class": "RobertaAdapterModel",
|
| 37 |
+
"model_name": "roberta-base",
|
| 38 |
+
"model_type": "roberta",
|
| 39 |
+
"name": "moa_classifier",
|
| 40 |
+
"version": "0.2.1"
|
| 41 |
+
}
|
head_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"activation_function": "tanh",
|
| 4 |
+
"bias": true,
|
| 5 |
+
"dropout_prob": null,
|
| 6 |
+
"head_type": "classification",
|
| 7 |
+
"label2id": {
|
| 8 |
+
"cot": 6,
|
| 9 |
+
"exam": 3,
|
| 10 |
+
"finance": 0,
|
| 11 |
+
"gpt4tools": 5,
|
| 12 |
+
"leetcode": 2,
|
| 13 |
+
"medicine": 1,
|
| 14 |
+
"stackoverflow": 7,
|
| 15 |
+
"webgpt": 4
|
| 16 |
+
},
|
| 17 |
+
"layers": 2,
|
| 18 |
+
"num_labels": 8,
|
| 19 |
+
"use_pooler": false
|
| 20 |
+
},
|
| 21 |
+
"hidden_size": 768,
|
| 22 |
+
"model_class": "RobertaAdapterModel",
|
| 23 |
+
"model_name": "roberta-base",
|
| 24 |
+
"model_type": "roberta",
|
| 25 |
+
"name": "moa_classifier",
|
| 26 |
+
"version": "0.2.1"
|
| 27 |
+
}
|
pytorch_adapter.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c589322f7db9609bc86756e4ddf01adf274fe80575a7f8210cca38346133296
|
| 3 |
+
size 3596006
|
pytorch_model_head.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e38ba150536bdadb5cb128890e6c48953e3e8b4d7ac2a0d2278fcc0d3e8431e
|
| 3 |
+
size 2389096
|