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_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 "eos_token_ids": [
28 2
29 ],
30 "extra_pos_embeddings": 2,
31 "forced_eos_token_id": 2,
32 "gradient_checkpointing": false,
33 "id2label": {
34 "0": "LABEL_0",
35 "1": "LABEL_1",
36 "2": "LABEL_2"
37 },
38 "init_std": 0.02,
39 "is_encoder_decoder": true,
40 "label2id": {
41 "LABEL_0": 0,
42 "LABEL_1": 1,
43 "LABEL_2": 2
44 },
45 "length_penalty": 0.5,
46 "max_length": 62,
47 "max_position_embeddings": 1024,
48 "min_length": 11,
49 "model_type": "bart",
50 "no_repeat_ngram_size": 3,
51 "normalize_before": false,
52 "normalize_embedding": true,
53 "num_beams": 6,
54 "num_hidden_layers": 12,
55 "output_past": true,
56 "pad_token_id": 1,
57 "prefix": " ",
58 "replacing_rate": 0,
59 "save_step": 58,
60 "scale_embedding": false,
61 "static_position_embeddings": false,
62 "student_decoder_layers": null,
63 "student_encoder_layers": null,
64 "task_specific_params": {},
65 "transformers_version": "4.7.0.dev0",
66 "use_cache": true,
67 "vocab_size": 50264
68 }
69