Waleed-bin-Qamar commited on
Commit
25e07fd
1 Parent(s): e4a4e12

Add trained model

Browse files
config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "decoder_start_token_id": null,
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "eos_token_id": null,
21
+ "eos_token_ids": 0,
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
+ "torch_dtype": "float32",
71
+ "torchscript": false,
72
+ "transformers_version": "4.2.1",
73
+ "type_vocab_size": 2,
74
+ "use_bfloat16": false,
75
+ "use_cache": true,
76
+ "vocab_size": 30522,
77
+ "xla_device": null
78
+ },
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
+ "classifier_dropout": null,
91
+ "decoder_start_token_id": null,
92
+ "diversity_penalty": 0.0,
93
+ "do_sample": false,
94
+ "early_stopping": false,
95
+ "eos_token_id": null,
96
+ "eos_token_ids": 0,
97
+ "finetuning_task": null,
98
+ "gradient_checkpointing": false,
99
+ "hidden_act": "gelu",
100
+ "hidden_dropout_prob": 0.1,
101
+ "hidden_size": 768,
102
+ "id2label": {
103
+ "0": "LABEL_0",
104
+ "1": "LABEL_1"
105
+ },
106
+ "initializer_range": 0.02,
107
+ "intermediate_size": 3072,
108
+ "is_decoder": false,
109
+ "is_encoder_decoder": false,
110
+ "label2id": {
111
+ "LABEL_0": 0,
112
+ "LABEL_1": 1
113
+ },
114
+ "layer_norm_eps": 1e-12,
115
+ "length_penalty": 1.0,
116
+ "max_length": 20,
117
+ "max_position_embeddings": 512,
118
+ "min_length": 0,
119
+ "model_type": "bert",
120
+ "no_repeat_ngram_size": 0,
121
+ "num_attention_heads": 12,
122
+ "num_beam_groups": 1,
123
+ "num_beams": 1,
124
+ "num_hidden_layers": 12,
125
+ "num_return_sequences": 1,
126
+ "output_attentions": false,
127
+ "output_hidden_states": false,
128
+ "output_past": true,
129
+ "output_scores": false,
130
+ "pad_token_id": 0,
131
+ "position_embedding_type": "absolute",
132
+ "prefix": null,
133
+ "pruned_heads": {},
134
+ "repetition_penalty": 1.0,
135
+ "return_dict": true,
136
+ "return_dict_in_generate": false,
137
+ "sep_token_id": null,
138
+ "task_specific_params": null,
139
+ "temperature": 1.0,
140
+ "tie_encoder_decoder": false,
141
+ "tie_word_embeddings": true,
142
+ "tokenizer_class": null,
143
+ "top_k": 50,
144
+ "top_p": 1.0,
145
+ "torch_dtype": "float32",
146
+ "torchscript": false,
147
+ "transformers_version": "4.2.1",
148
+ "type_vocab_size": 2,
149
+ "use_bfloat16": false,
150
+ "use_cache": true,
151
+ "vocab_size": 30522,
152
+ "xla_device": null
153
+ },
154
+ "is_encoder_decoder": true,
155
+ "length_penalty": 2.0,
156
+ "max_length": 26,
157
+ "model_type": "encoder-decoder",
158
+ "no_repeat_ngram_size": 3,
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 sha256:8bb11487b8a15addd0eb6d83b6685725649c33834fe5eb0cccb30eed7e427eec
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, "do_basic_tokenize": true, "model_max_length": 512, "name_or_path": "Waleed-bin-Qamar/PT-LegalBert-wl-3EP2", "never_split": null, "special_tokens_map_file": "/root/.cache/huggingface/hub/models--nlpaueb--legal-bert-base-uncased/snapshots/15b570cbf88259610b082a167dacc190124f60f6/special_tokens_map.json", "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff