ravfogs commited on
Commit
567a997
1 Parent(s): 72f2fa2

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +78 -68
config.json CHANGED
@@ -1,68 +1,78 @@
1
- {'return_dict': True,
2
- 'output_hidden_states': False,
3
- 'output_attentions': False,
4
- 'torchscript': False,
5
- 'torch_dtype': None,
6
- 'use_bfloat16': False,
7
- 'tf_legacy_loss': False,
8
- 'pruned_heads': {},
9
- 'tie_word_embeddings': True,
10
- 'is_encoder_decoder': False,
11
- 'is_decoder': False,
12
- 'cross_attention_hidden_size': None,
13
- 'add_cross_attention': False,
14
- 'tie_encoder_decoder': False,
15
- 'max_length': 20,
16
- 'min_length': 0,
17
- 'do_sample': False,
18
- 'early_stopping': False,
19
- 'num_beams': 1,
20
- 'num_beam_groups': 1,
21
- 'diversity_penalty': 0.0,
22
- 'temperature': 1.0,
23
- 'top_k': 50,
24
- 'top_p': 1.0,
25
- 'typical_p': 1.0,
26
- 'repetition_penalty': 1.0,
27
- 'length_penalty': 1.0,
28
- 'no_repeat_ngram_size': 0,
29
- 'encoder_no_repeat_ngram_size': 0,
30
- 'bad_words_ids': None,
31
- 'num_return_sequences': 1,
32
- 'chunk_size_feed_forward': 0,
33
- 'output_scores': False,
34
- 'return_dict_in_generate': False,
35
- 'forced_bos_token_id': None,
36
- 'forced_eos_token_id': None,
37
- 'remove_invalid_values': False,
38
- 'exponential_decay_length_penalty': None,
39
- 'suppress_tokens': None,
40
- 'begin_suppress_tokens': None,
41
- 'architectures': ['MPNetForMaskedLM'],
42
- 'finetuning_task': None,
43
- 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'},
44
- 'label2id': {'LABEL_0': 0, 'LABEL_1': 1},
45
- 'tokenizer_class': None,
46
- 'prefix': None,
47
- 'bos_token_id': 0,
48
- 'pad_token_id': 1,
49
- 'eos_token_id': 2,
50
- 'sep_token_id': None,
51
- 'decoder_start_token_id': None,
52
- 'task_specific_params': None,
53
- 'problem_type': None,
54
- '_name_or_path': 'microsoft/mpnet-base',
55
- 'transformers_version': '4.25.1',
56
- 'model_type': 'mpnet',
57
- 'vocab_size': 30527,
58
- 'hidden_size': 768,
59
- 'num_hidden_layers': 12,
60
- 'num_attention_heads': 12,
61
- 'hidden_act': 'gelu',
62
- 'intermediate_size': 3072,
63
- 'hidden_dropout_prob': 0.1,
64
- 'attention_probs_dropout_prob': 0.1,
65
- 'max_position_embeddings': 514,
66
- 'initializer_range': 0.02,
67
- 'layer_norm_eps': 1e-05,
68
- 'relative_attention_num_buckets': 32}
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "return_dict": true,
3
+ "output_hidden_states": false,
4
+ "output_attentions": false,
5
+ "torchscript": false,
6
+ "torch_dtype": null,
7
+ "use_bfloat16": false,
8
+ "tf_legacy_loss": false,
9
+ "pruned_heads": {},
10
+ "tie_word_embeddings": true,
11
+ "is_encoder_decoder": false,
12
+ "is_decoder": false,
13
+ "cross_attention_hidden_size": null,
14
+ "add_cross_attention": false,
15
+ "tie_encoder_decoder": false,
16
+ "max_length": 20,
17
+ "min_length": 0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "num_beams": 1,
21
+ "num_beam_groups": 1,
22
+ "diversity_penalty": 0.0,
23
+ "temperature": 1.0,
24
+ "top_k": 50,
25
+ "top_p": 1.0,
26
+ "typical_p": 1.0,
27
+ "repetition_penalty": 1.0,
28
+ "length_penalty": 1.0,
29
+ "no_repeat_ngram_size": 0,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "bad_words_ids": null,
32
+ "num_return_sequences": 1,
33
+ "chunk_size_feed_forward": 0,
34
+ "output_scores": false,
35
+ "return_dict_in_generate": false,
36
+ "forced_bos_token_id": null,
37
+ "forced_eos_token_id": null,
38
+ "remove_invalid_values": false,
39
+ "exponential_decay_length_penalty": null,
40
+ "suppress_tokens": null,
41
+ "begin_suppress_tokens": null,
42
+ "architectures": [
43
+ "MPNetForMaskedLM"
44
+ ],
45
+ "finetuning_task": null,
46
+ "id2label": {
47
+ "0": "LABEL_0",
48
+ "1": "LABEL_1"
49
+ },
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1
53
+ },
54
+ "tokenizer_class": null,
55
+ "prefix": null,
56
+ "bos_token_id": 0,
57
+ "pad_token_id": 1,
58
+ "eos_token_id": 2,
59
+ "sep_token_id": null,
60
+ "decoder_start_token_id": null,
61
+ "task_specific_params": null,
62
+ "problem_type": null,
63
+ "_name_or_path": "microsoft/mpnet-base",
64
+ "transformers_version": "4.25.1",
65
+ "model_type": "mpnet",
66
+ "vocab_size": 30527,
67
+ "hidden_size": 768,
68
+ "num_hidden_layers": 12,
69
+ "num_attention_heads": 12,
70
+ "hidden_act": "gelu",
71
+ "intermediate_size": 3072,
72
+ "hidden_dropout_prob": 0.1,
73
+ "attention_probs_dropout_prob": 0.1,
74
+ "max_position_embeddings": 514,
75
+ "initializer_range": 0.02,
76
+ "layer_norm_eps": 1e-05,
77
+ "relative_attention_num_buckets": 32
78
+ }