Back to model page
Model card Files and versions Use in transformers
ynie / bart-large-snli_mnli_fever_anli_R1_R2_R3-nli / config.json
system Update config.json 571c092
raw history blame
1,369 Bytes
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
{
  "_num_labels": 3,
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "add_bias_logits": false,
  "add_final_layer_norm": false,
  "architectures": [
    "BartForSequenceClassification"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "classif_dropout": 0.0,
  "d_model": 1024,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 2,
  "dropout": 0.1,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 4096,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "eos_token_id": 2,
  "extra_pos_embeddings": 2,
  "id2label": {
    "0": "entailment",
    "1": "neutral",
    "2": "contradiction"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "entailment": 0,
    "neutral": 1,
    "contradiction": 2
  },
  "max_position_embeddings": 1024,
  "model_type": "bart",
  "normalize_before": false,
  "normalize_embedding": true,
  "num_hidden_layers": 12,
  "output_past": false,
  "pad_token_id": 1,
  "prefix": " ",
  "scale_embedding": false,
  "static_position_embeddings": false,
  "task_specific_params": {
    "summarization": {
      "early_stopping": true,
      "length_penalty": 2.0,
      "max_length": 142,
      "min_length": 56,
      "no_repeat_ngram_size": 3,
      "num_beams": 4
    }
  },
  "vocab_size": 50265
}