valhalla's picture
valhalla
HF staff
add flax model 3906683
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
    "BartForQuestionAnswering"
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": 12,
19
  "decoder_start_token_id": 2,
20
  "dropout": 0.1,
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
  "forced_eos_token_id": 2,
27
  "gradient_checkpointing": false,
28
  "id2label": {
29
    "0": "LABEL_0",
30
    "1": "LABEL_1"
31
  },
32
  "init_std": 0.02,
33
  "is_encoder_decoder": true,
34
  "label2id": {
35
    "LABEL_0": 0,
36
    "LABEL_1": 1
37
  },
38
  "max_position_embeddings": 1024,
39
  "model_type": "bart",
40
  "normalize_before": false,
41
  "normalize_embedding": true,
42
  "num_hidden_layers": 12,
43
  "output_past": false,
44
  "pad_token_id": 1,
45
  "prefix": " ",
46
  "scale_embedding": false,
47
  "static_position_embeddings": false,
48
  "task_specific_params": {
49
    "summarization": {
50
      "early_stopping": true,
51
      "length_penalty": 2.0,
52
      "max_length": 142,
53
      "min_length": 56,
54
      "no_repeat_ngram_size": 3,
55
      "num_beams": 4
56
    }
57
  },
58
  "transformers_version": "4.7.0.dev0",
59
  "use_cache": true,
60
  "vocab_size": 50265
61
}
62