1 {
2 "_name_or_path": "xlm-roberta-large",
3 "architectures": [
4 "XLMRobertaForSequenceClassification"
5 ],
6 "attention_probs_dropout_prob": 0.1,
7 "bos_token_id": 0,
8 "eos_token_id": 2,
9 "gradient_checkpointing": false,
10 "hidden_act": "gelu",
11 "hidden_dropout_prob": 0.1,
12 "hidden_size": 1024,
13 "id2label": {
14 "0": "bad",
15 "1": "same",
16 "2": "rel",
17 "3": "left_right_cause",
18 "4": "right_left_cause",
19 "5": "left_right_refute",
20 "6": "right_left_refute"
21 },
22 "initializer_range": 0.02,
23 "intermediate_size": 4096,
24 "label2id": {
25 "bad": 0,
26 "same": 1,
27 "rel": 2,
28 "left_right_cause": 3,
29 "right_left_cause": 4,
30 "left_right_refute": 5,
31 "right_left_refute": 6
32 },
33 "layer_norm_eps": 1e-05,
34 "max_position_embeddings": 514,
35 "model_type": "xlm-roberta",
36 "num_attention_heads": 16,
37 "num_hidden_layers": 24,
38 "output_past": true,
39 "pad_token_id": 1,
40 "position_embedding_type": "absolute",
41 "problem_type": "single_label_classification",
42 "torch_dtype": "float32",
43 "transformers_version": "4.9.2",
44 "type_vocab_size": 1,
45 "use_cache": true,
46 "vocab_size": 250002
47 }