rafaelm47labs commited on
Commit
e6616dd
1 Parent(s): d20f2f8

Files from the iptc english classifier

Browse files
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dbmdz/bert-base-italian-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "arti",
13
+ "1": "culture",
14
+ "2": "economy",
15
+ "3": "environment",
16
+ "4": "finance",
17
+ "5": "health",
18
+ "6": "labour",
19
+ "7": "media",
20
+ "8": "science",
21
+ "9": "society",
22
+ "10": "sport",
23
+ "11": "technology",
24
+ "12": "weather"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "label2id": {
29
+ "arti": 0,
30
+ "culture": 1,
31
+ "economy": 2,
32
+ "environment": 3,
33
+ "finance": 4,
34
+ "health": 5,
35
+ "labour": 6,
36
+ "media": 7,
37
+ "science": 8,
38
+ "society": 9,
39
+ "sport": 10,
40
+ "technology": 11,
41
+ "weather": 12
42
+ },
43
+ "layer_norm_eps": 1e-12,
44
+ "max_position_embeddings": 512,
45
+ "model_type": "bert",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 12,
48
+ "pad_token_id": 0,
49
+ "position_embedding_type": "absolute",
50
+ "transformers_version": "4.8.2",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "vocab_size": 31102
54
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6e3c92467a7c6cdb36211daaac7e78c39f7cbaa326d6a5a8844ef2f8898c3dc
3
+ size 439831981
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, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "dbmdz/bert-base-italian-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