1
{
2
  "architectures": [
3
    "LongformerForSequenceClassification"
4
  ],
5
  "attention_mode": "longformer",
6
  "attention_probs_dropout_prob": 0.1,
7
  "attention_window": [
8
    512,
9
    512,
10
    512,
11
    512,
12
    512,
13
    512,
14
    512,
15
    512,
16
    512,
17
    512,
18
    512,
19
    512
20
  ],
21
  "bos_token_id": 0,
22
  "eos_token_id": 2,
23
  "finetuning_task": "paraphrase_classification",
24
  "gradient_checkpointing": false,
25
  "hidden_act": "gelu",
26
  "hidden_dropout_prob": 0.1,
27
  "hidden_size": 768,
28
  "ignore_attention_mask": false,
29
  "initializer_range": 0.02,
30
  "intermediate_size": 3072,
31
  "layer_norm_eps": 1e-05,
32
  "max_position_embeddings": 4098,
33
  "model_type": "longformer",
34
  "num_attention_heads": 12,
35
  "num_hidden_layers": 12,
36
  "pad_token_id": 1,
37
  "sep_token_id": 2,
38
  "type_vocab_size": 1,
39
  "vocab_size": 50265,
40
  "id2label": {
41
    "0": "ORIGINAL",
42
    "1": "PLAGIARISM"
43
  }
44
}
45