config.json
1.4 KB · 57 lines · json Raw
1 {
2 "_num_labels": 3,
3 "activation_dropout": 0.0,
4 "activation_function": "gelu",
5 "add_bias_logits": false,
6 "add_final_layer_norm": false,
7 "architectures": [
8 "BartForSequenceClassification"
9 ],
10 "attention_dropout": 0.1,
11 "bos_token_id": 0,
12 "classif_dropout": 0.0,
13 "classifier_dropout": 0.0,
14 "d_model": 1024,
15 "decoder_attention_heads": 16,
16 "decoder_ffn_dim": 4096,
17 "decoder_layerdrop": 0.0,
18 "decoder_layers": 1,
19 "decoder_start_token_id": 2,
20 "dropout": 0.1,
21 "encoder_attention_heads": 16,
22 "encoder_ffn_dim": 4096,
23 "encoder_layerdrop": 0.0,
24 "encoder_layers": 12,
25 "eos_token_id": 2,
26 "extra_pos_embeddings": 2,
27 "finetuning_task": "mnli",
28 "force_bos_token_to_be_generated": false,
29 "forced_eos_token_id": 2,
30 "gradient_checkpointing": false,
31 "id2label": {
32 "0": "contradiction",
33 "1": "neutral",
34 "2": "entailment"
35 },
36 "init_std": 0.02,
37 "is_encoder_decoder": true,
38 "label2id": {
39 "contradiction": 0,
40 "entailment": 2,
41 "neutral": 1
42 },
43 "max_position_embeddings": 1024,
44 "model_type": "bart",
45 "normalize_before": false,
46 "normalize_embedding": true,
47 "num_hidden_layers": 12,
48 "output_past": false,
49 "pad_token_id": 1,
50 "scale_embedding": false,
51 "static_position_embeddings": false,
52 "total_flos": 153130534133111808,
53 "transformers_version": "4.7.0.dev0",
54 "use_cache": true,
55 "vocab_size": 50265
56 }
57