Hugging Face's logo

Pragformer
/
PragFormer

Text Classification
Transformers
PyTorch
pragformer_reduction
feature-extraction
custom_code
Model card Files Community
PragFormer
File size: 3,448 Bytes 
bf5e8a3
9029422
bf5e8a3
af0032a
bf5e8a3
9029422
 
 
 
af0032a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9097e70
 
 
 
 
 
 
 
 
af0032a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b1abea4
af0032a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bf5e8a3
af0032a
 
 
967c5e2
af0032a
bf5e8a3
af0032a
bf5e8a3
 
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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
 
{
  "_name_or_path": "Pragformer/PragFormer",
  "architectures": [
    "BERT_Arch"
  ],
  "auto_map": {
    "AutoConfig": "model_config.PragFormerConfig",
    "AutoModel": "model.BERT_Arch"
  },
  "bert": {
    "_commit_hash": "43cf2d48e8c75d255dccab2a19e40d4774fd8853",
    "_name_or_path": "NTUYG/DeepSCC-RoBERTa",
    "add_cross_attention": false,
    "architectures": [
      "RobertaForSequenceClassification"
    ],
    "attention_probs_dropout_prob": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "classifier_dropout": null,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "gradient_checkpointing": false,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1",
      "10": "LABEL_10",
      "11": "LABEL_11",
      "12": "LABEL_12",
      "13": "LABEL_13",
      "14": "LABEL_14",
      "15": "LABEL_15",
      "16": "LABEL_16",
      "17": "LABEL_17",
      "18": "LABEL_18",
      "2": "LABEL_2",
      "3": "LABEL_3",
      "4": "LABEL_4",
      "5": "LABEL_5",
      "6": "LABEL_6",
      "7": "LABEL_7",
      "8": "LABEL_8",
      "9": "LABEL_9"
    },
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1,
      "LABEL_10": 10,
      "LABEL_11": 11,
      "LABEL_12": 12,
      "LABEL_13": 13,
      "LABEL_14": 14,
      "LABEL_15": 15,
      "LABEL_16": 16,
      "LABEL_17": 17,
      "LABEL_18": 18,
      "LABEL_2": 2,
      "LABEL_3": 3,
      "LABEL_4": 4,
      "LABEL_5": 5,
      "LABEL_6": 6,
      "LABEL_7": 7,
      "LABEL_8": 8,
      "LABEL_9": 9
    },
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 514,
    "min_length": 0,
    "model_type": "roberta",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 1,
    "position_embedding_type": "absolute",
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "transformers_version": "4.2.0",
    "type_vocab_size": 1,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 50265
  },
  "dropout": 0.2,
  "fc1": 512,
  "fc2": 2,
  "model_type": "pragformer_reduction",
  "softmax_dim": 1,
  "torch_dtype": "float32",
  "transformers_version": "4.25.1"
}