anas-awadalla
commited on
Commit
•
5207e67
1
Parent(s):
73aee8c
Model save
Browse files- .gitignore +1 -0
- merges.txt +0 -0
- special_tokens_map.json +1 -0
- 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
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
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 sha256:85fecc69ea33f25ee1eb55528469d3d3b2fdbf44d12f2c9e58a5e7f947eb069d
|
3 |
+
size 25442881
|
squad/pytorch_model_head.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16ee1c02d5f956353820702ec57f663e6fdc059758c9d33347afdcadd76aa767
|
3 |
+
size 9191
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large", "tokenizer_class": "RobertaTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52762482531c7cceb80c911b68e158b27f813de6bb178a934c0e9ec0ae981ace
|
3 |
+
size 3055
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|