Armin Mehrabian commited on
Commit
77c545e
1 Parent(s): e497528

Adding model and tokenizer saved on 0.0.1

Browse files
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nasa-impact/bert-e-base-mlm",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_10": 10,
42
+ "LABEL_11": 11,
43
+ "LABEL_12": 12,
44
+ "LABEL_13": 13,
45
+ "LABEL_14": 14,
46
+ "LABEL_15": 15,
47
+ "LABEL_16": 16,
48
+ "LABEL_17": 17,
49
+ "LABEL_18": 18,
50
+ "LABEL_19": 19,
51
+ "LABEL_2": 2,
52
+ "LABEL_20": 20,
53
+ "LABEL_21": 21,
54
+ "LABEL_22": 22,
55
+ "LABEL_3": 3,
56
+ "LABEL_4": 4,
57
+ "LABEL_5": 5,
58
+ "LABEL_6": 6,
59
+ "LABEL_7": 7,
60
+ "LABEL_8": 8,
61
+ "LABEL_9": 9
62
+ },
63
+ "layer_norm_eps": 1e-12,
64
+ "max_position_embeddings": 512,
65
+ "model_type": "bert",
66
+ "num_attention_heads": 12,
67
+ "num_hidden_layers": 12,
68
+ "pad_token_id": 0,
69
+ "position_embedding_type": "absolute",
70
+ "problem_type": "single_label_classification",
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.27.3",
73
+ "type_vocab_size": 2,
74
+ "use_cache": true,
75
+ "vocab_size": 31116
76
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a56ac18d87035dace3d2d68f2af0e32bf34a24e25cc67f07e4891f245dc7a69
3
+ size 439897269
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff