Waleed-bin-Qamar commited on
Commit
7d1e0d9
1 Parent(s): c67ed51

Add trained model

Browse files
config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "bos_token_id": 101,
6
+ "decoder": {
7
+ "_name_or_path": "/content/model1",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "BertModel"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 101,
15
+ "chunk_size_feed_forward": 0,
16
+ "decoder_start_token_id": 101,
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "early_stopping": true,
20
+ "eos_token_id": 102,
21
+ "eos_token_ids": 1,
22
+ "finetuning_task": null,
23
+ "gradient_checkpointing": false,
24
+ "hidden_act": "gelu",
25
+ "hidden_dropout_prob": 0.1,
26
+ "hidden_size": 768,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 3072,
33
+ "is_decoder": true,
34
+ "is_encoder_decoder": false,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "layer_norm_eps": 1e-12,
40
+ "length_penalty": 1.0,
41
+ "max_length": 20,
42
+ "max_position_embeddings": 512,
43
+ "min_length": 0,
44
+ "model_type": "bert",
45
+ "no_repeat_ngram_size": 0,
46
+ "num_attention_heads": 12,
47
+ "num_beam_groups": 1,
48
+ "num_beams": 1,
49
+ "num_hidden_layers": 12,
50
+ "num_return_sequences": 1,
51
+ "output_attentions": false,
52
+ "output_hidden_states": false,
53
+ "output_past": true,
54
+ "output_scores": false,
55
+ "pad_token_id": 0,
56
+ "position_embedding_type": "absolute",
57
+ "prefix": null,
58
+ "pruned_heads": {},
59
+ "repetition_penalty": 1.0,
60
+ "return_dict": true,
61
+ "return_dict_in_generate": false,
62
+ "sep_token_id": null,
63
+ "task_specific_params": null,
64
+ "temperature": 1.0,
65
+ "tie_encoder_decoder": false,
66
+ "tie_word_embeddings": true,
67
+ "tokenizer_class": null,
68
+ "top_k": 50,
69
+ "top_p": 1.0,
70
+ "torchscript": false,
71
+ "transformers_version": "4.2.1",
72
+ "type_vocab_size": 2,
73
+ "use_bfloat16": false,
74
+ "use_cache": true,
75
+ "vocab_size": 30522,
76
+ "xla_device": null
77
+ },
78
+ "decoder_start_token_id": 101,
79
+ "early_stopping": true,
80
+ "encoder": {
81
+ "_name_or_path": "/content/model1",
82
+ "add_cross_attention": false,
83
+ "architectures": [
84
+ "BertModel"
85
+ ],
86
+ "attention_probs_dropout_prob": 0.1,
87
+ "bad_words_ids": null,
88
+ "bos_token_id": 0,
89
+ "chunk_size_feed_forward": 0,
90
+ "decoder_start_token_id": null,
91
+ "diversity_penalty": 0.0,
92
+ "do_sample": false,
93
+ "early_stopping": false,
94
+ "eos_token_id": null,
95
+ "eos_token_ids": 0,
96
+ "finetuning_task": null,
97
+ "gradient_checkpointing": false,
98
+ "hidden_act": "gelu",
99
+ "hidden_dropout_prob": 0.1,
100
+ "hidden_size": 768,
101
+ "id2label": {
102
+ "0": "LABEL_0",
103
+ "1": "LABEL_1"
104
+ },
105
+ "initializer_range": 0.02,
106
+ "intermediate_size": 3072,
107
+ "is_decoder": false,
108
+ "is_encoder_decoder": false,
109
+ "label2id": {
110
+ "LABEL_0": 0,
111
+ "LABEL_1": 1
112
+ },
113
+ "layer_norm_eps": 1e-12,
114
+ "length_penalty": 1.0,
115
+ "max_length": 20,
116
+ "max_position_embeddings": 512,
117
+ "min_length": 0,
118
+ "model_type": "bert",
119
+ "no_repeat_ngram_size": 0,
120
+ "num_attention_heads": 12,
121
+ "num_beam_groups": 1,
122
+ "num_beams": 1,
123
+ "num_hidden_layers": 12,
124
+ "num_return_sequences": 1,
125
+ "output_attentions": false,
126
+ "output_hidden_states": false,
127
+ "output_past": true,
128
+ "output_scores": false,
129
+ "pad_token_id": 0,
130
+ "position_embedding_type": "absolute",
131
+ "prefix": null,
132
+ "pruned_heads": {},
133
+ "repetition_penalty": 1.0,
134
+ "return_dict": true,
135
+ "return_dict_in_generate": false,
136
+ "sep_token_id": null,
137
+ "task_specific_params": null,
138
+ "temperature": 1.0,
139
+ "tie_encoder_decoder": false,
140
+ "tie_word_embeddings": true,
141
+ "tokenizer_class": null,
142
+ "top_k": 50,
143
+ "top_p": 1.0,
144
+ "torchscript": false,
145
+ "transformers_version": "4.2.1",
146
+ "type_vocab_size": 2,
147
+ "use_bfloat16": false,
148
+ "use_cache": true,
149
+ "vocab_size": 30522,
150
+ "xla_device": null
151
+ },
152
+ "eos_token_id": 102,
153
+ "is_encoder_decoder": true,
154
+ "length_penalty": 2.0,
155
+ "max_length": 32,
156
+ "min_length": 4,
157
+ "model_type": "encoder-decoder",
158
+ "no_repeat_ngram_size": 2,
159
+ "num_beams": 4,
160
+ "pad_token_id": 0,
161
+ "vocab_size": 30522
162
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:177e528f7424afe919f21beb9d49d0931b20918d594174c32422d8d27bdec9d7
3
+ size 989682745
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, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/1ec992491addc8a43e9196bea3ccaf98f3958ce101f111ba9096813cf1ab493c.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "nlpaueb/legal-bert-base-uncased", "do_basic_tokenize": true, "never_split": null}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff