File size: 1,113 Bytes
2689ec7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "architectures": [
    "MiniLMForPreTraining"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "do_sample": false,
  "eos_token_ids": 0,
  "finetuning_task": null,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 384,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "is_decoder": false,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "layer_norm_eps": 1e-12,
  "length_penalty": 1.0,
  "max_length": 20,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_beams": 1,
  "num_hidden_layers": 3,
  "num_labels": 2,
  "num_return_sequences": 1,
  "num_rnn_layer": 1,
  "output_attentions": false,
  "output_hidden_states": true,
  "output_past": true,
  "pad_token_id": 0,
  "pruned_heads": {},
  "repetition_penalty": 1.0,
  "rnn": "lstm",
  "rnn_dropout": 0.0,
  "rnn_hidden": 768,
  "split": 10,
  "temperature": 1.0,
  "top_k": 50,
  "top_p": 1.0,
  "torchscript": false,
  "type_vocab_size": 2,
  "use_bfloat16": false,
  "vocab_size": 4101
}