File size: 1,350 Bytes
a8c0c48
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
    "output_attentions": false,
    "output_hidden_states": false,
    "use_cache": true,
    "torchscript": false,
    "use_bfloat16": false,
    "pruned_heads": {},
    "is_encoder_decoder": false,
    "is_decoder": false,
    "max_length": 20,
    "min_length": 0,
    "do_sample": false,
    "early_stopping": false,
    "num_beams": 1,
    "temperature": 1.0,
    "top_k": 50,
    "top_p": 1.0,
    "repetition_penalty": 1.0,
    "length_penalty": 1.0,
    "no_repeat_ngram_size": 0,
    "bad_words_ids": null,
    "num_return_sequences": 1,
    "architectures": [
        "RobertaForMaskedLM"
    ],
    "finetuning_task": null,
    "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
    },
    "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
    },
    "prefix": null,
    "bos_token_id": 0,
    "pad_token_id": 1,
    "eos_token_id": 2,
    "decoder_start_token_id": null,
    "task_specific_params": null,
    "xla_device": null,
    "model_type": "roberta",
    "vocab_size": 50269,
    "hidden_size": 768,
    "num_hidden_layers": 12,
    "num_attention_heads": 12,
    "hidden_act": "gelu",
    "intermediate_size": 3072,
    "hidden_dropout_prob": 0.1,
    "attention_probs_dropout_prob": 0.1,
    "max_position_embeddings": 514,
    "type_vocab_size": 1,
    "initializer_range": 0.02,
    "layer_norm_eps": 1e-05
}