nchen909 commited on
Commit
6bf1c20
1 Parent(s): e00cde7

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +33 -84
config.json CHANGED
@@ -1,84 +1,33 @@
1
- {
2
- "vocab_size": 50005,
3
- "max_position_embeddings": 1024,
4
- "d_model": 768,
5
- "encoder_ffn_dim": 3072,
6
- "encoder_layers": 6,
7
- "encoder_attention_heads": 12,
8
- "decoder_ffn_dim": 3072,
9
- "decoder_layers": 6,
10
- "decoder_attention_heads": 12,
11
- "dropout": 0.1,
12
- "attention_dropout": 0.1,
13
- "activation_dropout": 0.0,
14
- "activation_function": "gelu",
15
- "init_std": 0.02,
16
- "encoder_layerdrop": 0.0,
17
- "decoder_layerdrop": 0.0,
18
- "classifier_dropout": 0.0,
19
- "use_cache": true,
20
- "num_hidden_layers": 6,
21
- "scale_embedding": true,
22
- "return_dict": true,
23
- "output_hidden_states": false,
24
- "output_attentions": false,
25
- "torchscript": false,
26
- "torch_dtype": null,
27
- "use_bfloat16": false,
28
- "tf_legacy_loss": false,
29
- "pruned_heads": {},
30
- "tie_word_embeddings": true,
31
- "is_encoder_decoder": true,
32
- "is_decoder": false,
33
- "cross_attention_hidden_size": null,
34
- "add_cross_attention": false,
35
- "tie_encoder_decoder": false,
36
- "max_length": 20,
37
- "min_length": 0,
38
- "do_sample": false,
39
- "early_stopping": false,
40
- "num_beams": 1,
41
- "num_beam_groups": 1,
42
- "diversity_penalty": 0.0,
43
- "temperature": 1.0,
44
- "top_k": 50,
45
- "top_p": 1.0,
46
- "typical_p": 1.0,
47
- "repetition_penalty": 1.0,
48
- "length_penalty": 1.0,
49
- "no_repeat_ngram_size": 0,
50
- "encoder_no_repeat_ngram_size": 0,
51
- "bad_words_ids": null,
52
- "num_return_sequences": 1,
53
- "chunk_size_feed_forward": 0,
54
- "output_scores": false,
55
- "return_dict_in_generate": false,
56
- "forced_bos_token_id": null,
57
- "forced_eos_token_id": 2,
58
- "remove_invalid_values": false,
59
- "exponential_decay_length_penalty": null,
60
- "architectures": [
61
- "PLBartForConditionalGeneration"
62
- ],
63
- "finetuning_task": null,
64
- "id2label": {
65
- "0": "LABEL_0",
66
- "1": "LABEL_1"
67
- },
68
- "label2id": {
69
- "LABEL_0": 0,
70
- "LABEL_1": 1
71
- },
72
- "tokenizer_class": null,
73
- "prefix": null,
74
- "bos_token_id": 0,
75
- "pad_token_id": 1,
76
- "eos_token_id": 2,
77
- "sep_token_id": null,
78
- "decoder_start_token_id": null,
79
- "task_specific_params": null,
80
- "problem_type": null,
81
- "_name_or_path": "nchen909/plbart-base-finetuned-clone-detection",
82
- "transformers_version": "4.21.2",
83
- "model_type": "plbart"
84
- }
 
1
+ PLBartConfig {
2
+ "_name_or_path": "/root/autodl-tmp/HugCode/data/huggingface_models/plbart-base",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "PLBartForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "classifier_dropout": 0.0,
11
+ "d_model": 768,
12
+ "decoder_attention_heads": 12,
13
+ "decoder_ffn_dim": 3072,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 6,
16
+ "dropout": 0.1,
17
+ "encoder_attention_heads": 12,
18
+ "encoder_ffn_dim": 3072,
19
+ "encoder_layerdrop": 0.0,
20
+ "encoder_layers": 6,
21
+ "eos_token_id": 2,
22
+ "forced_eos_token_id": 2,
23
+ "init_std": 0.02,
24
+ "is_encoder_decoder": true,
25
+ "max_position_embeddings": 1024,
26
+ "model_type": "plbart",
27
+ "num_hidden_layers": 6,
28
+ "pad_token_id": 1,
29
+ "scale_embedding": true,
30
+ "transformers_version": "4.21.1",
31
+ "use_cache": true,
32
+ "vocab_size": 50005
33
+ }