vinayh19 commited on
Commit
49a5c30
·
verified ·
1 Parent(s): 558f09a

changed the file names

Browse files

file name changed to match the dnabert2 structure for the standard script top be able to pick up the files

Files changed (3) hide show
  1. config.json +31 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +52 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "zhihan1996/DNABERT-2-117M",
3
+ "alibi_starting_size": 512,
4
+ "architectures": [
5
+ "BertForMaskedLM"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "zhihan1996/DNABERT-2-117M--configuration_bert.BertConfig",
10
+ "AutoModel": "zhihan1996/DNABERT-2-117M--bert_layers.BertModel",
11
+ "AutoModelForMaskedLM": "zhihan1996/DNABERT-2-117M--bert_layers.BertForMaskedLM",
12
+ "AutoModelForSequenceClassification": "zhihan1996/DNABERT-2-117M--bert_layers.BertForSequenceClassification"
13
+ },
14
+ "classifier_dropout": null,
15
+ "gradient_checkpointing": false,
16
+ "hidden_act": "gelu",
17
+ "hidden_dropout_prob": 0.1,
18
+ "hidden_size": 768,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.41.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 4096
31
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "mask_token": "[MASK]",
47
+ "model_max_length": 1000000000000000019884624838656,
48
+ "pad_token": "[PAD]",
49
+ "sep_token": "[SEP]",
50
+ "tokenizer_class": "PreTrainedTokenizerFast",
51
+ "unk_token": "[UNK]"
52
+ }