config.json
1.5 KB · 69 lines · json Raw
1 {
2 "_num_labels": 3,
3 "activation_dropout": 0.0,
4 "activation_function": "gelu",
5 "add_final_layer_norm": false,
6 "architectures": [
7 "BartForConditionalGeneration"
8 ],
9 "attention_dropout": 0.0,
10 "bos_token_id": 0,
11 "classif_dropout": 0.0,
12 "classifier_dropout": 0.0,
13 "d_model": 1024,
14 "decoder_attention_heads": 16,
15 "decoder_ffn_dim": 4096,
16 "decoder_layerdrop": 0.0,
17 "decoder_layers": 12,
18 "decoder_start_token_id": 2,
19 "dropout": 0.1,
20 "early_stopping": true,
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 "force_bos_token_to_be_generated": true,
27 "forced_bos_token_id": 0,
28 "forced_eos_token_id": 2,
29 "gradient_checkpointing": false,
30 "id2label": {
31 "0": "LABEL_0",
32 "1": "LABEL_1",
33 "2": "LABEL_2"
34 },
35 "init_std": 0.02,
36 "is_encoder_decoder": true,
37 "label2id": {
38 "LABEL_0": 0,
39 "LABEL_1": 1,
40 "LABEL_2": 2
41 },
42 "length_penalty": 2.0,
43 "max_length": 142,
44 "max_position_embeddings": 1024,
45 "min_length": 56,
46 "model_type": "bart",
47 "no_repeat_ngram_size": 3,
48 "normalize_before": false,
49 "num_beams": 4,
50 "num_hidden_layers": 12,
51 "output_past": true,
52 "pad_token_id": 1,
53 "prefix": " ",
54 "scale_embedding": false,
55 "task_specific_params": {
56 "summarization": {
57 "early_stopping": true,
58 "length_penalty": 2.0,
59 "max_length": 142,
60 "min_length": 56,
61 "no_repeat_ngram_size": 3,
62 "num_beams": 4
63 }
64 },
65 "transformers_version": "4.7.0.dev0",
66 "use_cache": true,
67 "vocab_size": 50264
68 }
69