Hugging Face's logo

AmirErez
/
BBERT-models

Transformers
Safetensors
biology
genomics
dna-sequence
bacterial-classification
bert
Model card Files
xet
 Community
AmirErez commited on
Commit
76df518
·
verified ·
1 Parent(s): c41c33c

Add 768H BBERT backbone (epoch 100, freeze2)

Browse files
Files changed (4) hide show
  1. bbert_768H_epoch100/config.json +29 -0
  2. bbert_768H_epoch100/model.safetensors +3 -0
  3. bbert_768H_epoch100/tokenizer.json +214 -0
  4. bbert_768H_epoch100/tokenizer_config.json +22 -0
bbert_768H_epoch100/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 1536,
16
+ "is_decoder": false,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "bert",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 6,
22
+ "pad_token_id": 0,
23
+ "position_embedding_type": "absolute",
24
+ "tie_word_embeddings": true,
25
+ "transformers_version": "5.6.2",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 12
29
+ }
bbert_768H_epoch100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab62f0aea4345e37340cd6424435524969217d37b6fa19da80727a42204cd1a
3
+ size 117451720
bbert_768H_epoch100/tokenizer.json ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 102,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 102
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 3,
16
+ "pad_type_id": 0,
17
+ "pad_token": "<pad>"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "<s>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "</s>",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": false,
36
+ "special": true
37
+ },
38
+ {
39
+ "id": 2,
40
+ "content": "<unk>",
41
+ "single_word": false,
42
+ "lstrip": false,
43
+ "rstrip": false,
44
+ "normalized": false,
45
+ "special": true
46
+ },
47
+ {
48
+ "id": 3,
49
+ "content": "<pad>",
50
+ "single_word": false,
51
+ "lstrip": false,
52
+ "rstrip": false,
53
+ "normalized": false,
54
+ "special": true
55
+ },
56
+ {
57
+ "id": 4,
58
+ "content": "<cls>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ {
66
+ "id": 5,
67
+ "content": "<sep>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
+ },
74
+ {
75
+ "id": 6,
76
+ "content": "<msk>",
77
+ "single_word": false,
78
+ "lstrip": false,
79
+ "rstrip": false,
80
+ "normalized": false,
81
+ "special": true
82
+ },
83
+ {
84
+ "id": 7,
85
+ "content": "T",
86
+ "single_word": false,
87
+ "lstrip": false,
88
+ "rstrip": false,
89
+ "normalized": true,
90
+ "special": false
91
+ },
92
+ {
93
+ "id": 8,
94
+ "content": "C",
95
+ "single_word": false,
96
+ "lstrip": false,
97
+ "rstrip": false,
98
+ "normalized": true,
99
+ "special": false
100
+ },
101
+ {
102
+ "id": 9,
103
+ "content": "A",
104
+ "single_word": false,
105
+ "lstrip": false,
106
+ "rstrip": false,
107
+ "normalized": true,
108
+ "special": false
109
+ },
110
+ {
111
+ "id": 10,
112
+ "content": "G",
113
+ "single_word": false,
114
+ "lstrip": false,
115
+ "rstrip": false,
116
+ "normalized": true,
117
+ "special": false
118
+ },
119
+ {
120
+ "id": 11,
121
+ "content": "N",
122
+ "single_word": false,
123
+ "lstrip": false,
124
+ "rstrip": false,
125
+ "normalized": true,
126
+ "special": false
127
+ }
128
+ ],
129
+ "normalizer": null,
130
+ "pre_tokenizer": {
131
+ "type": "Whitespace"
132
+ },
133
+ "post_processor": {
134
+ "type": "TemplateProcessing",
135
+ "single": [
136
+ {
137
+ "SpecialToken": {
138
+ "id": "<cls>",
139
+ "type_id": 0
140
+ }
141
+ },
142
+ {
143
+ "Sequence": {
144
+ "id": "A",
145
+ "type_id": 0
146
+ }
147
+ },
148
+ {
149
+ "SpecialToken": {
150
+ "id": "<sep>",
151
+ "type_id": 0
152
+ }
153
+ }
154
+ ],
155
+ "pair": [
156
+ {
157
+ "SpecialToken": {
158
+ "id": "<cls>",
159
+ "type_id": 0
160
+ }
161
+ },
162
+ {
163
+ "Sequence": {
164
+ "id": "A",
165
+ "type_id": 0
166
+ }
167
+ },
168
+ {
169
+ "SpecialToken": {
170
+ "id": "<sep>",
171
+ "type_id": 0
172
+ }
173
+ },
174
+ {
175
+ "Sequence": {
176
+ "id": "B",
177
+ "type_id": 1
178
+ }
179
+ },
180
+ {
181
+ "SpecialToken": {
182
+ "id": "<sep>",
183
+ "type_id": 1
184
+ }
185
+ }
186
+ ],
187
+ "special_tokens": {
188
+ "<cls>": {
189
+ "id": "<cls>",
190
+ "ids": [
191
+ 4
192
+ ],
193
+ "tokens": [
194
+ "<cls>"
195
+ ]
196
+ },
197
+ "<sep>": {
198
+ "id": "<sep>",
199
+ "ids": [
200
+ 5
201
+ ],
202
+ "tokens": [
203
+ "<sep>"
204
+ ]
205
+ }
206
+ }
207
+ },
208
+ "decoder": null,
209
+ "model": {
210
+ "type": "WordLevel",
211
+ "vocab": {},
212
+ "unk_token": "<unk>"
213
+ }
214
+ }
bbert_768H_epoch100/tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<cls>",
6
+ "eos_token": "</s>",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
+ "mask_token": "<msk>",
10
+ "max_length": 102,
11
+ "model_max_length": 512,
12
+ "pad_to_multiple_of": null,
13
+ "pad_token": "<pad>",
14
+ "pad_token_type_id": 0,
15
+ "padding_side": "right",
16
+ "sep_token": "<sep>",
17
+ "stride": 0,
18
+ "tokenizer_class": "TokenizersBackend",
19
+ "truncation_side": "right",
20
+ "truncation_strategy": "longest_first",
21
+ "unk_token": "<unk>"
22
+ }