marcosgg commited on
Commit
1c21d42
1 Parent(s): 35325a3

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +56 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +1 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "marcosgg/bert-base-gl-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "eos_token_ids": null,
10
+ "finetuning_task": "ner",
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "B-LOC",
16
+ "1": "B-MISC",
17
+ "2": "B-ORG",
18
+ "3": "B-PER",
19
+ "4": "I-LOC",
20
+ "5": "I-MISC",
21
+ "6": "I-ORG",
22
+ "7": "I-PER",
23
+ "8": "O"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "B-LOC": 0,
29
+ "B-MISC": 1,
30
+ "B-ORG": 2,
31
+ "B-PER": 3,
32
+ "I-LOC": 4,
33
+ "I-MISC": 5,
34
+ "I-ORG": 6,
35
+ "I-PER": 7,
36
+ "O": 8
37
+ },
38
+ "layer_norm_eps": 1e-12,
39
+ "max_position_embeddings": 512,
40
+ "model_type": "bert",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "output_past": true,
44
+ "pad_token_id": 0,
45
+ "pooler_fc_size": 768,
46
+ "pooler_num_attention_heads": 12,
47
+ "pooler_num_fc_layers": 3,
48
+ "pooler_size_per_head": 128,
49
+ "pooler_type": "first_token_transform",
50
+ "position_embedding_type": "absolute",
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.19.4",
53
+ "type_vocab_size": 2,
54
+ "use_cache": true,
55
+ "vocab_size": 119547
56
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eacfd54da6344321da71efdb8d9e4b37770eb1184c8ec47eccce782f502db062
3
+ size 709149489
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": false, "strip_accents": null, "special_tokens_map_file": "/home/marcos/.cache/huggingface/transformers/79d33c7b216b88eb723de0efcf9dd481d11ab6e297ac874fec94b58f7591a636.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "marcosgg/bert-base-gl-cased", "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