File size: 1,479 Bytes
6dd7dfe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
{
  "_name_or_path": "markussagen/xlm-roberta-longformer-base-4096",
  "architectures": [
    "XLMRobertaForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "attention_window": [
    512,
    512,
    512,
    512,
    512,
    512,
    512,
    512,
    512,
    512,
    512,
    512
  ],
  "bos_token_id": 0,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "Base32",
    "1": "Base64",
    "2": "Emoji",
    "3": "First_Last_Same",
    "4": "Ignore_Instructions",
    "5": "Languages",
    "6": "Leetspeak",
    "7": "Reverse",
    "8": "ROT13",
    "9": "Word_Order",
    "10": "Not_Evasion"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Base32": 0,
    "Base64": 1,
    "Emoji": 2,
    "First_Last_Same": 3,
    "Ignore_Instructions": 4,
    "Languages": 5,
    "Leetspeak": 6,
    "Not_Evasion": 10,
    "ROT13": 8,
    "Reverse": 7,
    "Word_Order": 9
  },
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 4098,
  "model_type": "xlm-roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "output_past": true,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "problem_type": "multi_label_classification",
  "torch_dtype": "float32",
  "transformers_version": "4.38.2",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 250002
}