system
Update config.json d378062
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": 12,
18
  "decoder_start_token_id": 2,
19
  "dropout": 0.1,
20
  "encoder_attention_heads": 16,
21
  "encoder_ffn_dim": 4096,
22
  "encoder_layerdrop": 0.0,
23
  "encoder_layers": 12,
24
  "eos_token_id": 2,
25
  "id2label": {
26
    "0": "LABEL_0",
27
    "1": "LABEL_1",
28
    "2": "LABEL_2"
29
  },
30
  "init_std": 0.02,
31
  "is_encoder_decoder": true,
32
  "label2id": {
33
    "LABEL_0": 0,
34
    "LABEL_1": 1,
35
    "LABEL_2": 2
36
  },
37
  "max_position_embeddings": 1024,
38
  "model_type": "bart",
39
  "normalize_before": false,
40
  "normalize_embedding": true,
41
  "num_hidden_layers": 12,
42
  "output_past": false,
43
  "pad_token_id": 1,
44
  "prefix": " ",
45
  "scale_embedding": false,
46
  "static_position_embeddings": false,
47
  "task_specific_params": {
48
    "summarization": {
49
      "early_stopping": true,
50
      "length_penalty": 2.0,
51
      "max_length": 142,
52
      "min_length": 56,
53
      "no_repeat_ngram_size": 3,
54
      "num_beams": 4
55
    }
56
  },
57
  "vocab_size": 50265
58
}
59