distilbart-xsum-1-1

distilbart-xsum-1-1 / config.json
system
Update config.json bddbacb
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
  "d_model": 1024,
14
  "decoder_attention_heads": 16,
15
  "decoder_ffn_dim": 4096,
16
  "decoder_layerdrop": 0.0,
17
  "decoder_layers": 1,
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": 1,
25
  "eos_token_id": 2,
26
  "eos_token_ids": [
27
    2
28
  ],
29
  "extra_pos_embeddings": 2,
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
  "max_length": 62,
43
  "max_position_embeddings": 1024,
44
  "min_length": 11,
45
  "model_type": "bart",
46
  "no_repeat_ngram_size": 3,
47
  "normalize_before": false,
48
  "normalize_embedding": true,
49
  "num_beams": 6,
50
  "num_hidden_layers": 1,
51
  "output_past": true,
52
  "pad_token_id": 1,
53
  "prefix": " ",
54
  "replacing_rate": 0,
55
  "save_step": 59,
56
  "scale_embedding": false,
57
  "static_position_embeddings": false,
58
  "student_decoder_layers": null,
59
  "student_encoder_layers": null,
60
  "task_specific_params": {},
61
  "vocab_size": 50264
62
}
63