rafaelm47labs
commited on
Commit
•
e9fc9a2
1
Parent(s):
1d957a6
first commit
Browse files- config.json +63 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dbmdz/bert-base-italian-xxl-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
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": "arts/culture/entertainment and media",
|
13 |
+
"1": "conflict/war and peace",
|
14 |
+
"2": "crime/law and justice",
|
15 |
+
"3": "disaster/accident and emergency incident",
|
16 |
+
"4": "economy/business and finance",
|
17 |
+
"5": "education",
|
18 |
+
"6": "environment",
|
19 |
+
"7": "health",
|
20 |
+
"8": "human interest",
|
21 |
+
"9": "labour",
|
22 |
+
"10": "lifestyle and leisure",
|
23 |
+
"11": "politics",
|
24 |
+
"12": "religion and belief",
|
25 |
+
"13": "science and technology",
|
26 |
+
"14": "society",
|
27 |
+
"15": "sport",
|
28 |
+
"16": "weather"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"arts/culture/entertainment and media": 0,
|
34 |
+
"conflict/war and peace": 1,
|
35 |
+
"crime/law and justice": 2,
|
36 |
+
"disaster/accident and emergency incident": 3,
|
37 |
+
"economy/business and finance": 4,
|
38 |
+
"education": 5,
|
39 |
+
"environment": 6,
|
40 |
+
"health": 7,
|
41 |
+
"human interest": 8,
|
42 |
+
"labour": 9,
|
43 |
+
"lifestyle and leisure": 10,
|
44 |
+
"politics": 11,
|
45 |
+
"religion and belief": 12,
|
46 |
+
"science and technology": 13,
|
47 |
+
"society": 14,
|
48 |
+
"sport": 15,
|
49 |
+
"weather": 16
|
50 |
+
},
|
51 |
+
"layer_norm_eps": 1e-12,
|
52 |
+
"max_position_embeddings": 512,
|
53 |
+
"model_type": "bert",
|
54 |
+
"num_attention_heads": 12,
|
55 |
+
"num_hidden_layers": 12,
|
56 |
+
"pad_token_id": 0,
|
57 |
+
"position_embedding_type": "absolute",
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.11.3",
|
60 |
+
"type_vocab_size": 2,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 32102
|
63 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de81d4de6392121583b9d25a6830287c1e47ffa665ba125d9695e54b8520ae35
|
3 |
+
size 442919149
|
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": true, "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-xxl-uncased", "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
|
|