jmilic1 commited on
Commit
c726da8
·
1 Parent(s): 8e63c80
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "adapters": {
4
+ "adapters": {
5
+ "emo": "9076f36a74755ac4"
6
+ },
7
+ "config_map": {
8
+ "9076f36a74755ac4": {
9
+ "adapter_residual_before_ln": false,
10
+ "cross_adapter": false,
11
+ "factorized_phm_W": true,
12
+ "factorized_phm_rule": false,
13
+ "hypercomplex_nonlinearity": "glorot-uniform",
14
+ "init_weights": "bert",
15
+ "inv_adapter": null,
16
+ "inv_adapter_reduction_factor": null,
17
+ "is_parallel": false,
18
+ "learn_phm": true,
19
+ "leave_out": [],
20
+ "ln_after": false,
21
+ "ln_before": false,
22
+ "mh_adapter": false,
23
+ "non_linearity": "relu",
24
+ "original_ln_after": true,
25
+ "original_ln_before": true,
26
+ "output_adapter": true,
27
+ "phm_bias": true,
28
+ "phm_c_init": "normal",
29
+ "phm_dim": 4,
30
+ "phm_init_range": 0.0001,
31
+ "phm_layer": false,
32
+ "phm_rank": 1,
33
+ "reduction_factor": 16,
34
+ "residual_before_ln": true,
35
+ "scaling": 1.0,
36
+ "shared_W_phm": false,
37
+ "shared_phm_rule": true
38
+ }
39
+ },
40
+ "fusion_config_map": {},
41
+ "fusions": {}
42
+ },
43
+ "architectures": [
44
+ "RobertaAdapterModel"
45
+ ],
46
+ "attention_probs_dropout_prob": 0.1,
47
+ "bos_token_id": 0,
48
+ "classifier_dropout": null,
49
+ "eos_token_id": 2,
50
+ "hidden_act": "gelu",
51
+ "hidden_dropout_prob": 0.1,
52
+ "hidden_size": 768,
53
+ "id2label": {
54
+ "0": "LABEL_0",
55
+ "1": "LABEL_1",
56
+ "2": "LABEL_2",
57
+ "3": "LABEL_3"
58
+ },
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 3072,
61
+ "label2id": {
62
+ "LABEL_0": 0,
63
+ "LABEL_1": 1,
64
+ "LABEL_2": 2,
65
+ "LABEL_3": 3
66
+ },
67
+ "layer_norm_eps": 1e-05,
68
+ "max_position_embeddings": 514,
69
+ "model_type": "roberta",
70
+ "num_attention_heads": 12,
71
+ "num_hidden_layers": 12,
72
+ "pad_token_id": 1,
73
+ "position_embedding_type": "absolute",
74
+ "prediction_heads": {
75
+ "emo": {
76
+ "activation_function": "tanh",
77
+ "bias": true,
78
+ "head_type": "classification",
79
+ "label2id": {
80
+ "LABEL_0": 0,
81
+ "LABEL_1": 1,
82
+ "LABEL_2": 2,
83
+ "LABEL_3": 3
84
+ },
85
+ "layers": 2,
86
+ "num_labels": 4,
87
+ "use_pooler": false
88
+ }
89
+ },
90
+ "torch_dtype": "float32",
91
+ "transformers_version": "4.17.0",
92
+ "type_vocab_size": 1,
93
+ "use_cache": true,
94
+ "vocab_size": 50265
95
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d47c43dc99d073d130e519538e7b3f573c5eda462398d479737d5c16b28dbb30
3
+ size 504653897
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}}
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-base", "tokenizer_class": "RobertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28e08349fc6fb2abfb14e345d9438ba37b54ab85c1d4af12f7fa896394a3dc55
3
+ size 3119
vocab.json ADDED
The diff for this file is too large to render. See raw diff