Pragformer commited on
Commit
71b6cec
·
1 Parent(s): e1f7d8f

Upload BERT_Arch

Browse files
Files changed (2) hide show
  1. config.json +129 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BERT_Arch"
4
+ ],
5
+ "bert": {
6
+ "_commit_hash": "43cf2d48e8c75d255dccab2a19e40d4774fd8853",
7
+ "_name_or_path": "NTUYG/DeepSCC-RoBERTa",
8
+ "add_cross_attention": false,
9
+ "architectures": [
10
+ "RobertaForSequenceClassification"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": 0,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": null,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 2,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "gradient_checkpointing": false,
30
+ "hidden_act": "gelu",
31
+ "hidden_dropout_prob": 0.1,
32
+ "hidden_size": 768,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1",
36
+ "10": "LABEL_10",
37
+ "11": "LABEL_11",
38
+ "12": "LABEL_12",
39
+ "13": "LABEL_13",
40
+ "14": "LABEL_14",
41
+ "15": "LABEL_15",
42
+ "16": "LABEL_16",
43
+ "17": "LABEL_17",
44
+ "18": "LABEL_18",
45
+ "2": "LABEL_2",
46
+ "3": "LABEL_3",
47
+ "4": "LABEL_4",
48
+ "5": "LABEL_5",
49
+ "6": "LABEL_6",
50
+ "7": "LABEL_7",
51
+ "8": "LABEL_8",
52
+ "9": "LABEL_9"
53
+ },
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 3072,
56
+ "is_decoder": false,
57
+ "is_encoder_decoder": false,
58
+ "label2id": {
59
+ "LABEL_0": 0,
60
+ "LABEL_1": 1,
61
+ "LABEL_10": 10,
62
+ "LABEL_11": 11,
63
+ "LABEL_12": 12,
64
+ "LABEL_13": 13,
65
+ "LABEL_14": 14,
66
+ "LABEL_15": 15,
67
+ "LABEL_16": 16,
68
+ "LABEL_17": 17,
69
+ "LABEL_18": 18,
70
+ "LABEL_2": 2,
71
+ "LABEL_3": 3,
72
+ "LABEL_4": 4,
73
+ "LABEL_5": 5,
74
+ "LABEL_6": 6,
75
+ "LABEL_7": 7,
76
+ "LABEL_8": 8,
77
+ "LABEL_9": 9
78
+ },
79
+ "layer_norm_eps": 1e-05,
80
+ "length_penalty": 1.0,
81
+ "max_length": 20,
82
+ "max_position_embeddings": 514,
83
+ "min_length": 0,
84
+ "model_type": "roberta",
85
+ "no_repeat_ngram_size": 0,
86
+ "num_attention_heads": 12,
87
+ "num_beam_groups": 1,
88
+ "num_beams": 1,
89
+ "num_hidden_layers": 12,
90
+ "num_return_sequences": 1,
91
+ "output_attentions": false,
92
+ "output_hidden_states": false,
93
+ "output_scores": false,
94
+ "pad_token_id": 1,
95
+ "position_embedding_type": "absolute",
96
+ "prefix": null,
97
+ "problem_type": null,
98
+ "pruned_heads": {},
99
+ "remove_invalid_values": false,
100
+ "repetition_penalty": 1.0,
101
+ "return_dict": true,
102
+ "return_dict_in_generate": false,
103
+ "sep_token_id": null,
104
+ "suppress_tokens": null,
105
+ "task_specific_params": null,
106
+ "temperature": 1.0,
107
+ "tf_legacy_loss": false,
108
+ "tie_encoder_decoder": false,
109
+ "tie_word_embeddings": true,
110
+ "tokenizer_class": null,
111
+ "top_k": 50,
112
+ "top_p": 1.0,
113
+ "torch_dtype": null,
114
+ "torchscript": false,
115
+ "transformers_version": "4.2.0",
116
+ "type_vocab_size": 1,
117
+ "typical_p": 1.0,
118
+ "use_bfloat16": false,
119
+ "use_cache": true,
120
+ "vocab_size": 50265
121
+ },
122
+ "dropout": 0.2,
123
+ "fc1": 512,
124
+ "fc2": 2,
125
+ "model_type": "pragformer",
126
+ "softmax_dim": 1,
127
+ "torch_dtype": "float32",
128
+ "transformers_version": "4.25.1"
129
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816862e8a2fc62fac62de92357c9394c6649e27b134f3da267e4dbfedad0e544
3
+ size 500230377