config.json
982 B · 48 lines · json Raw
1 {
2 "_name_or_path": "xlm-roberta-large",
3 "architectures": [
4 "XLMRobertaForTokenClassification"
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": "O",
15 "1": "B-DATE",
16 "2": "I-DATE",
17 "3": "B-PER",
18 "4": "I-PER",
19 "5": "B-ORG",
20 "6": "I-ORG",
21 "7": "B-LOC",
22 "8": "I-LOC"
23 },
24 "initializer_range": 0.02,
25 "intermediate_size": 4096,
26 "label2id": {
27 "B-DATE": 1,
28 "B-LOC": 7,
29 "B-ORG": 5,
30 "B-PER": 3,
31 "I-DATE": 2,
32 "I-LOC": 8,
33 "I-ORG": 6,
34 "I-PER": 4,
35 "O": 0
36 },
37 "layer_norm_eps": 1e-05,
38 "max_position_embeddings": 514,
39 "model_type": "xlm-roberta",
40 "num_attention_heads": 16,
41 "num_hidden_layers": 24,
42 "output_past": true,
43 "pad_token_id": 1,
44 "position_embedding_type": "absolute",
45 "type_vocab_size": 1,
46 "vocab_size": 250002
47 }
48