isanvicente commited on
Commit
d79f160
1 Parent(s): 0af6929

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/nfs/baliabideLexikalak/wordEmbedings/eu/elhBertEu",
3
+ "architectures": [
4
+ "BertForTokenClassification"
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": "O",
13
+ "1": "B-ORG",
14
+ "2": "B-PER",
15
+ "3": "I-PER",
16
+ "4": "I-ORG",
17
+ "5": "B-LOC",
18
+ "6": "I-LOC",
19
+ "7": "B-MISC",
20
+ "8": "I-MISC"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "B-LOC": 5,
26
+ "B-MISC": 7,
27
+ "B-ORG": 1,
28
+ "B-PER": 2,
29
+ "I-LOC": 6,
30
+ "I-MISC": 8,
31
+ "I-ORG": 4,
32
+ "I-PER": 3,
33
+ "O": 0
34
+ },
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 512,
37
+ "model_type": "bert",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "output_past": true,
41
+ "pad_token_id": 3,
42
+ "position_embedding_type": "absolute",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.11.0",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 50099
48
+ }
labels.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ O
2
+ B-ORG
3
+ B-PER
4
+ I-PER
5
+ I-ORG
6
+ B-LOC
7
+ I-LOC
8
+ B-MISC
9
+ I-MISC
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9eb92295d77f4bca08867bba3dd501947cd27b296348d89658e204f6f46554
3
+ size 495818225
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/mnt/nfs/baliabideLexikalak/wordEmbedings/eu/elhBertEu", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff