config.json
1.6 KB · 70 lines · json Raw
1 {
2 "_name_or_path": "facebook/bart-large-cnn",
3 "_num_labels": 3,
4 "activation_dropout": 0.0,
5 "activation_function": "gelu",
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": 12,
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 "force_bos_token_to_be_generated": true,
28 "forced_bos_token_id": 0,
29 "forced_eos_token_id": 2,
30 "gradient_checkpointing": false,
31 "id2label": {
32 "0": "LABEL_0",
33 "1": "LABEL_1",
34 "2": "LABEL_2"
35 },
36 "init_std": 0.02,
37 "is_encoder_decoder": true,
38 "label2id": {
39 "LABEL_0": 0,
40 "LABEL_1": 1,
41 "LABEL_2": 2
42 },
43 "length_penalty": 2.0,
44 "max_length": 142,
45 "max_position_embeddings": 1024,
46 "min_length": 56,
47 "model_type": "bart",
48 "no_repeat_ngram_size": 3,
49 "normalize_before": false,
50 "num_beams": 4,
51 "num_hidden_layers": 12,
52 "output_past": true,
53 "pad_token_id": 1,
54 "prefix": " ",
55 "scale_embedding": false,
56 "task_specific_params": {
57 "summarization": {
58 "early_stopping": true,
59 "length_penalty": 2.0,
60 "max_length": 142,
61 "min_length": 56,
62 "no_repeat_ngram_size": 3,
63 "num_beams": 4
64 }
65 },
66 "transformers_version": "4.4.2",
67 "use_cache": true,
68 "vocab_size": 50264
69 }
70