config.json
1.8 KB · 76 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 "BartForConditionalGeneration"
9 ],
10 "attention_dropout": 0.0,
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": 6,
19 "decoder_start_token_id": 2,
20 "dropout": 0.1,
21 "early_stopping": true,
22 "encoder_attention_heads": 16,
23 "encoder_ffn_dim": 4096,
24 "encoder_layerdrop": 0.0,
25 "encoder_layers": 12,
26 "eos_token_id": 2,
27 "extra_pos_embeddings": 2,
28 "force_bos_token_to_be_generated": true,
29 "forced_bos_token_id": 0,
30 "forced_eos_token_id": 2,
31 "gradient_checkpointing": false,
32 "id2label": {
33 "0": "LABEL_0",
34 "1": "LABEL_1",
35 "2": "LABEL_2"
36 },
37 "init_std": 0.02,
38 "is_encoder_decoder": true,
39 "label2id": {
40 "LABEL_0": 0,
41 "LABEL_1": 1,
42 "LABEL_2": 2
43 },
44 "length_penalty": 2.0,
45 "max_length": 142,
46 "max_position_embeddings": 1024,
47 "min_length": 56,
48 "model_type": "bart",
49 "no_repeat_ngram_size": 3,
50 "normalize_before": false,
51 "normalize_embedding": true,
52 "num_beams": 4,
53 "num_hidden_layers": 12,
54 "output_past": true,
55 "pad_token_id": 1,
56 "prefix": " ",
57 "replacing_rate": 0,
58 "scale_embedding": false,
59 "static_position_embeddings": false,
60 "student_decoder_layers": null,
61 "student_encoder_layers": null,
62 "task_specific_params": {
63 "summarization": {
64 "early_stopping": true,
65 "length_penalty": 2.0,
66 "max_length": 142,
67 "min_length": 56,
68 "no_repeat_ngram_size": 3,
69 "num_beams": 4
70 }
71 },
72 "transformers_version": "4.7.0.dev0",
73 "use_cache": true,
74 "vocab_size": 50264
75 }
76