Hugging Face's logo

yangheng
/
PlantRNA-FM

Fill-Mask
Transformers
Safetensors
rna
esm
biology
OmniGenome
Inference Endpoints
Model card Files Community
yangheng commited on
Commit
18339d3
•
1 Parent(s): 96d7572

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +30 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer_config.json +52 -0
  5. vocab.txt +24 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../output/checkpoint-13400",
3
+ "architectures": [
4
+ "EsmForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "classifier_dropout": null,
8
+ "emb_layer_norm_before": false,
9
+ "esmfold_config": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0,
12
+ "hidden_size": 480,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1920,
15
+ "is_folding_model": false,
16
+ "layer_norm_eps": 1e-05,
17
+ "mask_token_id": 9,
18
+ "max_position_embeddings": 1026,
19
+ "model_type": "esm",
20
+ "num_attention_heads": 20,
21
+ "num_hidden_layers": 12,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "rotary",
24
+ "token_dropout": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.38.0.dev0",
27
+ "use_cache": true,
28
+ "vocab_list": null,
29
+ "vocab_size": 24
30
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f66172a243d589945b0b270cde3c5567c09d4ba537fcd710c8295e0d60d8c4
3
+ size 135983172
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "<cls>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<cls>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<eos>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "23": {
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
+ "eos_token": "<eos>",
47
+ "mask_token": "<mask>",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "<pad>",
50
+ "tokenizer_class": "EsmTokenizer",
51
+ "unk_token": "<unk>"
52
+ }
vocab.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <cls>
2
+ <pad>
3
+ <eos>
4
+ <unk>
5
+ A
6
+ C
7
+ G
8
+ T
9
+ N
10
+ U
11
+ a
12
+ c
13
+ g
14
+ t
15
+ n
16
+ u
17
+ (
18
+ )
19
+ .
20
+ *
21
+ 1
22
+ 2
23
+ 3
24
+ <mask>