Waleed-bin-Qamar commited on
Commit
2a831f3
1 Parent(s): 5c5c5e1

Add trained model

Browse files
config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "/content/model1",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "BertModel"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "decoder_start_token_id": null,
16
+ "diversity_penalty": 0.0,
17
+ "do_sample": false,
18
+ "early_stopping": false,
19
+ "eos_token_id": null,
20
+ "finetuning_task": null,
21
+ "gradient_checkpointing": false,
22
+ "hidden_act": "gelu",
23
+ "hidden_dropout_prob": 0.1,
24
+ "hidden_size": 768,
25
+ "id2label": {
26
+ "0": "LABEL_0",
27
+ "1": "LABEL_1"
28
+ },
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
+ "is_decoder": true,
32
+ "is_encoder_decoder": false,
33
+ "label2id": {
34
+ "LABEL_0": 0,
35
+ "LABEL_1": 1
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "length_penalty": 1.0,
39
+ "max_length": 20,
40
+ "max_position_embeddings": 512,
41
+ "min_length": 0,
42
+ "model_type": "bert",
43
+ "no_repeat_ngram_size": 0,
44
+ "num_attention_heads": 12,
45
+ "num_beam_groups": 1,
46
+ "num_beams": 1,
47
+ "num_hidden_layers": 12,
48
+ "num_return_sequences": 1,
49
+ "output_attentions": false,
50
+ "output_hidden_states": false,
51
+ "output_scores": false,
52
+ "pad_token_id": 0,
53
+ "position_embedding_type": "absolute",
54
+ "prefix": null,
55
+ "pruned_heads": {},
56
+ "repetition_penalty": 1.0,
57
+ "return_dict": true,
58
+ "return_dict_in_generate": false,
59
+ "sep_token_id": null,
60
+ "task_specific_params": null,
61
+ "temperature": 1.0,
62
+ "tie_encoder_decoder": false,
63
+ "tie_word_embeddings": true,
64
+ "tokenizer_class": null,
65
+ "top_k": 50,
66
+ "top_p": 1.0,
67
+ "torchscript": false,
68
+ "transformers_version": "4.2.1",
69
+ "type_vocab_size": 2,
70
+ "use_bfloat16": false,
71
+ "use_cache": true,
72
+ "vocab_size": 28996,
73
+ "xla_device": null
74
+ },
75
+ "decoder_start_token_id": 101,
76
+ "do_sample": true,
77
+ "encoder": {
78
+ "_name_or_path": "/content/model1",
79
+ "add_cross_attention": false,
80
+ "architectures": [
81
+ "BertModel"
82
+ ],
83
+ "attention_probs_dropout_prob": 0.1,
84
+ "bad_words_ids": null,
85
+ "bos_token_id": null,
86
+ "chunk_size_feed_forward": 0,
87
+ "decoder_start_token_id": null,
88
+ "diversity_penalty": 0.0,
89
+ "do_sample": false,
90
+ "early_stopping": false,
91
+ "eos_token_id": null,
92
+ "finetuning_task": null,
93
+ "gradient_checkpointing": false,
94
+ "hidden_act": "gelu",
95
+ "hidden_dropout_prob": 0.1,
96
+ "hidden_size": 768,
97
+ "id2label": {
98
+ "0": "LABEL_0",
99
+ "1": "LABEL_1"
100
+ },
101
+ "initializer_range": 0.02,
102
+ "intermediate_size": 3072,
103
+ "is_decoder": false,
104
+ "is_encoder_decoder": false,
105
+ "label2id": {
106
+ "LABEL_0": 0,
107
+ "LABEL_1": 1
108
+ },
109
+ "layer_norm_eps": 1e-12,
110
+ "length_penalty": 1.0,
111
+ "max_length": 20,
112
+ "max_position_embeddings": 512,
113
+ "min_length": 0,
114
+ "model_type": "bert",
115
+ "no_repeat_ngram_size": 0,
116
+ "num_attention_heads": 12,
117
+ "num_beam_groups": 1,
118
+ "num_beams": 1,
119
+ "num_hidden_layers": 12,
120
+ "num_return_sequences": 1,
121
+ "output_attentions": false,
122
+ "output_hidden_states": false,
123
+ "output_scores": false,
124
+ "pad_token_id": 0,
125
+ "position_embedding_type": "absolute",
126
+ "prefix": null,
127
+ "pruned_heads": {},
128
+ "repetition_penalty": 1.0,
129
+ "return_dict": true,
130
+ "return_dict_in_generate": false,
131
+ "sep_token_id": null,
132
+ "task_specific_params": null,
133
+ "temperature": 1.0,
134
+ "tie_encoder_decoder": false,
135
+ "tie_word_embeddings": true,
136
+ "tokenizer_class": null,
137
+ "top_k": 50,
138
+ "top_p": 1.0,
139
+ "torchscript": false,
140
+ "transformers_version": "4.2.1",
141
+ "type_vocab_size": 2,
142
+ "use_bfloat16": false,
143
+ "use_cache": true,
144
+ "vocab_size": 28996,
145
+ "xla_device": null
146
+ },
147
+ "eos_token_id": 102,
148
+ "is_encoder_decoder": true,
149
+ "max_length": 376,
150
+ "min_length": 30,
151
+ "model_type": "encoder-decoder",
152
+ "pad_token_id": 0,
153
+ "temperature": 0.92,
154
+ "vocab_size": 28996
155
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab219c4cb332abf0f7ef50702c03090b011875748de58711a848bfd441ceb124
3
+ size 980300921
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "emilyalsentzer/Bio_ClinicalBERT", "do_basic_tokenize": true, "never_split": null}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff