l3cube-pune commited on
Commit
23cb1f8
1 Parent(s): 1f9eba5

Update model files

Browse files
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "l3cube-pune/marathi-mixed-ner-iob",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "B-ED",
14
+ "1": "B-NED",
15
+ "2": "B-NEL",
16
+ "3": "B-NEM",
17
+ "4": "B-NEO",
18
+ "5": "B-NEP",
19
+ "6": "B-NETI",
20
+ "7": "I-ED",
21
+ "8": "I-NED",
22
+ "9": "I-NEL",
23
+ "10": "I-NEM",
24
+ "11": "I-NEO",
25
+ "12": "I-NEP",
26
+ "13": "I-NETI",
27
+ "14": "O"
28
+ },
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
+ "label2id": {
32
+ "B-ED": 0,
33
+ "B-NED": 1,
34
+ "B-NEL": 2,
35
+ "B-NEM": 3,
36
+ "B-NEO": 4,
37
+ "B-NEP": 5,
38
+ "B-NETI": 6,
39
+ "I-ED": 7,
40
+ "I-NED": 8,
41
+ "I-NEL": 9,
42
+ "I-NEM": 10,
43
+ "I-NEO": 11,
44
+ "I-NEP": 12,
45
+ "I-NETI": 13,
46
+ "O": 14
47
+ },
48
+ "layer_norm_eps": 1e-12,
49
+ "max_position_embeddings": 512,
50
+ "model_type": "bert",
51
+ "num_attention_heads": 12,
52
+ "num_hidden_layers": 12,
53
+ "pad_token_id": 0,
54
+ "position_embedding_type": "absolute",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.22.0",
57
+ "type_vocab_size": 2,
58
+ "use_cache": true,
59
+ "vocab_size": 197285
60
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f11361de8ca36c08cb174887d6a29d4eeffc0cd42775f388b6810ecd96579e
3
+ size 947978538
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 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "lowercase": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "name_or_path": "l3cube-pune/marathi-mixed-ner-iob",
10
+ "never_split": null,
11
+ "pad_token": "[PAD]",
12
+ "sep_token": "[SEP]",
13
+ "special_tokens_map_file": "l3cube-pune/marathi-mixed-ner-iob/special_tokens_map.json",
14
+ "strip_accents": false,
15
+ "tokenize_chinese_chars": true,
16
+ "tokenizer_class": "BertTokenizer",
17
+ "unk_token": "[UNK]"
18
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff