edchengg commited on
Commit
0b65a98
1 Parent(s): 65a05e2

First model version for testing pipeline

Browse files
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</FAC>": 50013,
3
+ "</GPE>": 50005,
4
+ "</LOC>": 50011,
5
+ "</ORG>": 50009,
6
+ "</PER>": 50001,
7
+ "</VEH>": 50003,
8
+ "</WEA>": 50007,
9
+ "<FAC>": 50012,
10
+ "<GPE>": 50004,
11
+ "<LOC>": 50010,
12
+ "<ORG>": 50008,
13
+ "<PER>": 50000,
14
+ "<VEH>": 50002,
15
+ "<WEA>": 50006
16
+ }
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lanwuwei/GigaBERT-v4-Arabic-and-English",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "ORG-AFF",
15
+ "2": "ART",
16
+ "3": "PHYS",
17
+ "4": "PART-WHOLE",
18
+ "5": "GEN-AFF",
19
+ "6": "PER-SOC"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "ART": 2,
25
+ "GEN-AFF": 5,
26
+ "O": 0,
27
+ "ORG-AFF": 1,
28
+ "PART-WHOLE": 4,
29
+ "PER-SOC": 6,
30
+ "PHYS": 3
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "max_position_embeddings": 512,
34
+ "model_type": "bert",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 12,
37
+ "pad_token_id": 0,
38
+ "pooler_fc_size": 768,
39
+ "pooler_num_attention_heads": 12,
40
+ "pooler_num_fc_layers": 3,
41
+ "pooler_size_per_head": 128,
42
+ "pooler_type": "first_token_transform",
43
+ "position_embedding_type": "absolute",
44
+ "problem_type": "single_label_classification",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.20.0.dev0",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 50014
50
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:277f1bc63e56cf1af6265f17764d03c3635d0b30328d16b8c4314186ae561f2a
3
+ size 995776285
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef680d83f86c336d836d13bb5908b09eb0d7a542a93647e1a9585462d4b21a8a
3
+ size 497900909
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d3b30a0b260d72b930e334ec49abd418af536d656456b030135e0d86e26e89
3
+ size 14503
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<PER>",
4
+ "</PER>",
5
+ "<VEH>",
6
+ "</VEH>",
7
+ "<GPE>",
8
+ "</GPE>",
9
+ "<WEA>",
10
+ "</WEA>",
11
+ "<ORG>",
12
+ "</ORG>",
13
+ "<LOC>",
14
+ "</LOC>",
15
+ "<FAC>",
16
+ "</FAC>"
17
+ ],
18
+ "bos_token": "[CLS]",
19
+ "cls_token": "[CLS]",
20
+ "eos_token": "[SEP]",
21
+ "mask_token": "[MASK]",
22
+ "pad_token": "[PAD]",
23
+ "sep_token": "[SEP]",
24
+ "unk_token": "[UNK]"
25
+ }
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
+ "name_or_path": "lanwuwei/GigaBERT-v4-Arabic-and-English",
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": "/srv/share5/ychen3411/huggingface_cache/c8a919731ad7551df88a744a8399190ea80a9961eaf96b8a59f86ef617e5144f.6a644b330fad284f98393c5832f71bce43df6855fa6ac7c9e44ed6271b708170",
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