Waleed-bin-Qamar commited on
Commit
33b9b46
·
1 Parent(s): 1849d1e

Add trained model

Browse files
config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "classifier_dropout": null,
17
+ "decoder_start_token_id": 101,
18
+ "directionality": "bidi",
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": true,
22
+ "eos_token_id": 102,
23
+ "eos_token_ids": 1,
24
+ "finetuning_task": null,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "max_position_embeddings": 512,
45
+ "min_length": 0,
46
+ "model_type": "bert",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_attention_heads": 12,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_hidden_layers": 12,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": 0,
57
+ "pooler_fc_size": 768,
58
+ "pooler_num_attention_heads": 12,
59
+ "pooler_num_fc_layers": 3,
60
+ "pooler_size_per_head": 128,
61
+ "pooler_type": "first_token_transform",
62
+ "position_embedding_type": "absolute",
63
+ "prefix": null,
64
+ "pruned_heads": {},
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "sep_token_id": null,
69
+ "task_specific_params": null,
70
+ "temperature": 1.0,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": "float32",
77
+ "torchscript": false,
78
+ "transformers_version": "4.2.1",
79
+ "type_vocab_size": 2,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 30522,
83
+ "xla_device": null
84
+ },
85
+ "decoder_start_token_id": 101,
86
+ "early_stopping": true,
87
+ "encoder": {
88
+ "_name_or_path": "/content/model1",
89
+ "add_cross_attention": false,
90
+ "architectures": [
91
+ "BertModel"
92
+ ],
93
+ "attention_probs_dropout_prob": 0.1,
94
+ "bad_words_ids": null,
95
+ "bos_token_id": null,
96
+ "chunk_size_feed_forward": 0,
97
+ "classifier_dropout": null,
98
+ "decoder_start_token_id": null,
99
+ "directionality": "bidi",
100
+ "diversity_penalty": 0.0,
101
+ "do_sample": false,
102
+ "early_stopping": false,
103
+ "eos_token_id": null,
104
+ "finetuning_task": null,
105
+ "gradient_checkpointing": false,
106
+ "hidden_act": "gelu",
107
+ "hidden_dropout_prob": 0.1,
108
+ "hidden_size": 768,
109
+ "id2label": {
110
+ "0": "LABEL_0",
111
+ "1": "LABEL_1"
112
+ },
113
+ "initializer_range": 0.02,
114
+ "intermediate_size": 3072,
115
+ "is_decoder": false,
116
+ "is_encoder_decoder": false,
117
+ "label2id": {
118
+ "LABEL_0": 0,
119
+ "LABEL_1": 1
120
+ },
121
+ "layer_norm_eps": 1e-12,
122
+ "length_penalty": 1.0,
123
+ "max_length": 20,
124
+ "max_position_embeddings": 512,
125
+ "min_length": 0,
126
+ "model_type": "bert",
127
+ "no_repeat_ngram_size": 0,
128
+ "num_attention_heads": 12,
129
+ "num_beam_groups": 1,
130
+ "num_beams": 1,
131
+ "num_hidden_layers": 12,
132
+ "num_return_sequences": 1,
133
+ "output_attentions": false,
134
+ "output_hidden_states": false,
135
+ "output_scores": false,
136
+ "pad_token_id": 0,
137
+ "pooler_fc_size": 768,
138
+ "pooler_num_attention_heads": 12,
139
+ "pooler_num_fc_layers": 3,
140
+ "pooler_size_per_head": 128,
141
+ "pooler_type": "first_token_transform",
142
+ "position_embedding_type": "absolute",
143
+ "prefix": null,
144
+ "pruned_heads": {},
145
+ "repetition_penalty": 1.0,
146
+ "return_dict": true,
147
+ "return_dict_in_generate": false,
148
+ "sep_token_id": null,
149
+ "task_specific_params": null,
150
+ "temperature": 1.0,
151
+ "tie_encoder_decoder": false,
152
+ "tie_word_embeddings": true,
153
+ "tokenizer_class": null,
154
+ "top_k": 50,
155
+ "top_p": 1.0,
156
+ "torch_dtype": "float32",
157
+ "torchscript": false,
158
+ "transformers_version": "4.2.1",
159
+ "type_vocab_size": 2,
160
+ "use_bfloat16": false,
161
+ "use_cache": true,
162
+ "vocab_size": 30522,
163
+ "xla_device": null
164
+ },
165
+ "eos_token_id": 102,
166
+ "is_encoder_decoder": true,
167
+ "length_penalty": 2.0,
168
+ "max_length": 32,
169
+ "min_length": 4,
170
+ "model_type": "encoder-decoder",
171
+ "no_repeat_ngram_size": 2,
172
+ "num_beams": 4,
173
+ "pad_token_id": 0,
174
+ "vocab_size": 30522
175
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b9afbba9c29cf91ea91cae87dc402f4fd98d52a5e8ed6e90acc51b192644ad
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, "max_length": 512, "model_max_length": 1000000000000000019884624838656, "name_or_path": "Waleed-bin-Qamar/PT-CaseLawBert-wl-3EP2", "never_split": null, "special_tokens_map_file": null, "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff