Hugging Face's logo

FishCaduceus
/
FishCaduceus-28L-512-FishGUE

Transformers
English
DNA
genomics
fish
sequence-classification
FishCaduceus
Fish_GUE
fine-tuned
single-nucleotide
Model card Files
xet
 Community
bioinfoihb commited on
Commit
e66a674
·
verified ·
1 Parent(s): 73b4f7e

Add FishCaduceus-28L-512 FishGUE fine-tuned models

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. CTCF_TF/config.json +66 -0
  2. CTCF_TF/pytorch_model.bin +3 -0
  3. CTCF_TF/special_tokens_map.json +23 -0
  4. CTCF_TF/tokenizer.json +75 -0
  5. CTCF_TF/tokenizer_config.json +34 -0
  6. H3K27me3/config.json +66 -0
  7. H3K27me3/pytorch_model.bin +3 -0
  8. H3K27me3/special_tokens_map.json +23 -0
  9. H3K27me3/tokenizer.json +75 -0
  10. H3K27me3/tokenizer_config.json +34 -0
  11. H3K4me1/config.json +66 -0
  12. H3K4me1/pytorch_model.bin +3 -0
  13. H3K4me1/special_tokens_map.json +23 -0
  14. H3K4me1/tokenizer.json +75 -0
  15. H3K4me1/tokenizer_config.json +34 -0
  16. H3K4me3/config.json +66 -0
  17. H3K4me3/pytorch_model.bin +3 -0
  18. H3K4me3/special_tokens_map.json +23 -0
  19. H3K4me3/tokenizer.json +75 -0
  20. H3K4me3/tokenizer_config.json +34 -0
  21. H3K9me3/config.json +66 -0
  22. H3K9me3/pytorch_model.bin +3 -0
  23. H3K9me3/special_tokens_map.json +23 -0
  24. H3K9me3/tokenizer.json +75 -0
  25. H3K9me3/tokenizer_config.json +34 -0
  26. H3k27ac/config.json +66 -0
  27. H3k27ac/pytorch_model.bin +3 -0
  28. H3k27ac/special_tokens_map.json +23 -0
  29. H3k27ac/tokenizer.json +75 -0
  30. H3k27ac/tokenizer_config.json +34 -0
  31. Pou5f1_TF/config.json +66 -0
  32. Pou5f1_TF/pytorch_model.bin +3 -0
  33. Pou5f1_TF/special_tokens_map.json +23 -0
  34. Pou5f1_TF/tokenizer.json +75 -0
  35. Pou5f1_TF/tokenizer_config.json +34 -0
  36. README.md +85 -1
  37. Sox2_TF/config.json +66 -0
  38. Sox2_TF/pytorch_model.bin +3 -0
  39. Sox2_TF/special_tokens_map.json +23 -0
  40. Sox2_TF/tokenizer.json +75 -0
  41. Sox2_TF/tokenizer_config.json +34 -0
  42. prom_1k_all/config.json +66 -0
  43. prom_1k_all/pytorch_model.bin +3 -0
  44. prom_1k_all/special_tokens_map.json +23 -0
  45. prom_1k_all/tokenizer.json +75 -0
  46. prom_1k_all/tokenizer_config.json +34 -0
  47. prom_1k_notata/config.json +66 -0
  48. prom_1k_notata/pytorch_model.bin +3 -0
  49. prom_1k_notata/special_tokens_map.json +23 -0
  50. prom_1k_notata/tokenizer.json +75 -0
CTCF_TF/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000",
3
+ "architectures": [
4
+ "CaduceusForSequenceClassification"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_caduceus.CaduceusConfig",
8
+ "AutoModel": "modeling_caduceus.Caduceus",
9
+ "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM",
10
+ "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification"
11
+ },
12
+ "bidirectional": true,
13
+ "bidirectional_strategy": "add",
14
+ "bidirectional_weight_tie": true,
15
+ "complement_map": {
16
+ "0": 0,
17
+ "1": 1,
18
+ "2": 2,
19
+ "3": 6,
20
+ "4": 5,
21
+ "5": 4,
22
+ "6": 3,
23
+ "7": 7
24
+ },
25
+ "d_model": 768,
26
+ "fused_add_norm": true,
27
+ "id2label": {
28
+ "0": "Not",
29
+ "1": "Yes"
30
+ },
31
+ "initializer_cfg": {
32
+ "initializer_range": 0.02,
33
+ "n_residuals_per_layer": 1,
34
+ "rescale_prenorm_residual": true
35
+ },
36
+ "label2id": {
37
+ "Not": 0,
38
+ "Yes": 1
39
+ },
40
+ "model_type": "caduceus",
41
+ "n_layer": 28,
42
+ "norm_epsilon": 1e-05,
43
+ "pad_token_id": 0,
44
+ "pad_vocab_size_multiple": 8,
45
+ "problem_type": "single_label_classification",
46
+ "rcps": true,
47
+ "residual_in_fp32": true,
48
+ "rms_norm": true,
49
+ "ssm_cfg": {
50
+ "bias": false,
51
+ "conv_bias": true,
52
+ "d_conv": 4,
53
+ "d_state": 16,
54
+ "dt_init": "random",
55
+ "dt_init_floor": 0.0001,
56
+ "dt_max": 0.1,
57
+ "dt_min": 0.001,
58
+ "dt_rank": "auto",
59
+ "dt_scale": 1.0,
60
+ "expand": 2,
61
+ "use_fast_path": true
62
+ },
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.30.2",
65
+ "vocab_size": 8
66
+ }
CTCF_TF/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e8dda5cf6acab5031c20201af194fe45734c61b186b098dbafa50c33eb76fa8
3
+ size 448617482
CTCF_TF/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": {
3
+ "content": "[MASK]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "[PAD]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
CTCF_TF/tokenizer.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 800,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 800
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[MASK]",
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
+ "normalizer": {
49
+ "type": "Lowercase"
50
+ },
51
+ "pre_tokenizer": {
52
+ "type": "Whitespace"
53
+ },
54
+ "post_processor": null,
55
+ "decoder": null,
56
+ "model": {
57
+ "type": "BPE",
58
+ "dropout": null,
59
+ "unk_token": "[UNK]",
60
+ "continuing_subword_prefix": null,
61
+ "end_of_word_suffix": null,
62
+ "fuse_unk": false,
63
+ "byte_fallback": false,
64
+ "vocab": {
65
+ "[PAD]": 0,
66
+ "[MASK]": 1,
67
+ "[UNK]": 2,
68
+ "a": 3,
69
+ "c": 4,
70
+ "g": 5,
71
+ "t": 6
72
+ },
73
+ "merges": []
74
+ }
75
+ }
CTCF_TF/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "mask_token": "[MASK]",
30
+ "model_max_length": 800,
31
+ "pad_token": "[PAD]",
32
+ "tokenizer_class": "PreTrainedTokenizerFast",
33
+ "unk_token": "[UNK]"
34
+ }
H3K27me3/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000",
3
+ "architectures": [
4
+ "CaduceusForSequenceClassification"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_caduceus.CaduceusConfig",
8
+ "AutoModel": "modeling_caduceus.Caduceus",
9
+ "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM",
10
+ "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification"
11
+ },
12
+ "bidirectional": true,
13
+ "bidirectional_strategy": "add",
14
+ "bidirectional_weight_tie": true,
15
+ "complement_map": {
16
+ "0": 0,
17
+ "1": 1,
18
+ "2": 2,
19
+ "3": 6,
20
+ "4": 5,
21
+ "5": 4,
22
+ "6": 3,
23
+ "7": 7
24
+ },
25
+ "d_model": 768,
26
+ "fused_add_norm": true,
27
+ "id2label": {
28
+ "0": "Not",
29
+ "1": "Yes"
30
+ },
31
+ "initializer_cfg": {
32
+ "initializer_range": 0.02,
33
+ "n_residuals_per_layer": 1,
34
+ "rescale_prenorm_residual": true
35
+ },
36
+ "label2id": {
37
+ "Not": 0,
38
+ "Yes": 1
39
+ },
40
+ "model_type": "caduceus",
41
+ "n_layer": 28,
42
+ "norm_epsilon": 1e-05,
43
+ "pad_token_id": 0,
44
+ "pad_vocab_size_multiple": 8,
45
+ "problem_type": "single_label_classification",
46
+ "rcps": true,
47
+ "residual_in_fp32": true,
48
+ "rms_norm": true,
49
+ "ssm_cfg": {
50
+ "bias": false,
51
+ "conv_bias": true,
52
+ "d_conv": 4,
53
+ "d_state": 16,
54
+ "dt_init": "random",
55
+ "dt_init_floor": 0.0001,
56
+ "dt_max": 0.1,
57
+ "dt_min": 0.001,
58
+ "dt_rank": "auto",
59
+ "dt_scale": 1.0,
60
+ "expand": 2,
61
+ "use_fast_path": true
62
+ },
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.30.2",
65
+ "vocab_size": 8
66
+ }
H3K27me3/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3913e3e4a2b32bc59630148dacf338975e90d26a390b78eaa19cbf38f1f26ee
3
+ size 448617482
H3K27me3/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": {
3
+ "content": "[MASK]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "[PAD]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
H3K27me3/tokenizer.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 2500,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 2500
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[MASK]",
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
+ "normalizer": {
49
+ "type": "Lowercase"
50
+ },
51
+ "pre_tokenizer": {
52
+ "type": "Whitespace"
53
+ },
54
+ "post_processor": null,
55
+ "decoder": null,
56
+ "model": {
57
+ "type": "BPE",
58
+ "dropout": null,
59
+ "unk_token": "[UNK]",
60
+ "continuing_subword_prefix": null,
61
+ "end_of_word_suffix": null,
62
+ "fuse_unk": false,
63
+ "byte_fallback": false,
64
+ "vocab": {
65
+ "[PAD]": 0,
66
+ "[MASK]": 1,
67
+ "[UNK]": 2,
68
+ "a": 3,
69
+ "c": 4,
70
+ "g": 5,
71
+ "t": 6
72
+ },
73
+ "merges": []
74
+ }
75
+ }
H3K27me3/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "mask_token": "[MASK]",
30
+ "model_max_length": 2500,
31
+ "pad_token": "[PAD]",
32
+ "tokenizer_class": "PreTrainedTokenizerFast",
33
+ "unk_token": "[UNK]"
34
+ }
H3K4me1/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000",
3
+ "architectures": [
4
+ "CaduceusForSequenceClassification"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_caduceus.CaduceusConfig",
8
+ "AutoModel": "modeling_caduceus.Caduceus",
9
+ "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM",
10
+ "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification"
11
+ },
12
+ "bidirectional": true,
13
+ "bidirectional_strategy": "add",
14
+ "bidirectional_weight_tie": true,
15
+ "complement_map": {
16
+ "0": 0,
17
+ "1": 1,
18
+ "2": 2,
19
+ "3": 6,
20
+ "4": 5,
21
+ "5": 4,
22
+ "6": 3,
23
+ "7": 7
24
+ },
25
+ "d_model": 768,
26
+ "fused_add_norm": true,
27
+ "id2label": {
28
+ "0": "Not",
29
+ "1": "Yes"
30
+ },
31
+ "initializer_cfg": {
32
+ "initializer_range": 0.02,
33
+ "n_residuals_per_layer": 1,
34
+ "rescale_prenorm_residual": true
35
+ },
36
+ "label2id": {
37
+ "Not": 0,
38
+ "Yes": 1
39
+ },
40
+ "model_type": "caduceus",
41
+ "n_layer": 28,
42
+ "norm_epsilon": 1e-05,
43
+ "pad_token_id": 0,
44
+ "pad_vocab_size_multiple": 8,
45
+ "problem_type": "single_label_classification",
46
+ "rcps": true,
47
+ "residual_in_fp32": true,
48
+ "rms_norm": true,
49
+ "ssm_cfg": {
50
+ "bias": false,
51
+ "conv_bias": true,
52
+ "d_conv": 4,
53
+ "d_state": 16,
54
+ "dt_init": "random",
55
+ "dt_init_floor": 0.0001,
56
+ "dt_max": 0.1,
57
+ "dt_min": 0.001,
58
+ "dt_rank": "auto",
59
+ "dt_scale": 1.0,
60
+ "expand": 2,
61
+ "use_fast_path": true
62
+ },
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.30.2",
65
+ "vocab_size": 8
66
+ }
H3K4me1/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ee35d6f7adca370081f96c4d74a5f2e8ac68ce58b187c5c9c3962803a3f3f0f
3
+ size 448617482
H3K4me1/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": {
3
+ "content": "[MASK]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "[PAD]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
H3K4me1/tokenizer.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 2500,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 2500
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[MASK]",
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
+ "normalizer": {
49
+ "type": "Lowercase"
50
+ },
51
+ "pre_tokenizer": {
52
+ "type": "Whitespace"
53
+ },
54
+ "post_processor": null,
55
+ "decoder": null,
56
+ "model": {
57
+ "type": "BPE",
58
+ "dropout": null,
59
+ "unk_token": "[UNK]",
60
+ "continuing_subword_prefix": null,
61
+ "end_of_word_suffix": null,
62
+ "fuse_unk": false,
63
+ "byte_fallback": false,
64
+ "vocab": {
65
+ "[PAD]": 0,
66
+ "[MASK]": 1,
67
+ "[UNK]": 2,
68
+ "a": 3,
69
+ "c": 4,
70
+ "g": 5,
71
+ "t": 6
72
+ },
73
+ "merges": []
74
+ }
75
+ }
H3K4me1/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "mask_token": "[MASK]",
30
+ "model_max_length": 2500,
31
+ "pad_token": "[PAD]",
32
+ "tokenizer_class": "PreTrainedTokenizerFast",
33
+ "unk_token": "[UNK]"
34
+ }
H3K4me3/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000",
3
+ "architectures": [
4
+ "CaduceusForSequenceClassification"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_caduceus.CaduceusConfig",
8
+ "AutoModel": "modeling_caduceus.Caduceus",
9
+ "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM",
10
+ "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification"
11
+ },
12
+ "bidirectional": true,
13
+ "bidirectional_strategy": "add",
14
+ "bidirectional_weight_tie": true,
15
+ "complement_map": {
16
+ "0": 0,
17
+ "1": 1,
18
+ "2": 2,
19
+ "3": 6,
20
+ "4": 5,
21
+ "5": 4,
22
+ "6": 3,
23
+ "7": 7
24
+ },
25
+ "d_model": 768,
26
+ "fused_add_norm": true,
27
+ "id2label": {
28
+ "0": "Not",
29
+ "1": "Yes"
30
+ },
31
+ "initializer_cfg": {
32
+ "initializer_range": 0.02,
33
+ "n_residuals_per_layer": 1,
34
+ "rescale_prenorm_residual": true
35
+ },
36
+ "label2id": {
37
+ "Not": 0,
38
+ "Yes": 1
39
+ },
40
+ "model_type": "caduceus",
41
+ "n_layer": 28,
42
+ "norm_epsilon": 1e-05,
43
+ "pad_token_id": 0,
44
+ "pad_vocab_size_multiple": 8,
45
+ "problem_type": "single_label_classification",
46
+ "rcps": true,
47
+ "residual_in_fp32": true,
48
+ "rms_norm": true,
49
+ "ssm_cfg": {
50
+ "bias": false,
51
+ "conv_bias": true,
52
+ "d_conv": 4,
53
+ "d_state": 16,
54
+ "dt_init": "random",
55
+ "dt_init_floor": 0.0001,
56
+ "dt_max": 0.1,
57
+ "dt_min": 0.001,
58
+ "dt_rank": "auto",
59
+ "dt_scale": 1.0,
60
+ "expand": 2,
61
+ "use_fast_path": true
62
+ },
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.30.2",
65
+ "vocab_size": 8
66
+ }
H3K4me3/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4071e9692a2cd55fe394130810326106cfa160a346d3d9d968ccb3c65877c72
3
+ size 448617482
H3K4me3/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": {
3
+ "content": "[MASK]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "[PAD]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
H3K4me3/tokenizer.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 2500,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 2500
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[MASK]",
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
+ "normalizer": {
49
+ "type": "Lowercase"
50
+ },
51
+ "pre_tokenizer": {
52
+ "type": "Whitespace"
53
+ },
54
+ "post_processor": null,
55
+ "decoder": null,
56
+ "model": {
57
+ "type": "BPE",
58
+ "dropout": null,
59
+ "unk_token": "[UNK]",
60
+ "continuing_subword_prefix": null,
61
+ "end_of_word_suffix": null,
62
+ "fuse_unk": false,
63
+ "byte_fallback": false,
64
+ "vocab": {
65
+ "[PAD]": 0,
66
+ "[MASK]": 1,
67
+ "[UNK]": 2,
68
+ "a": 3,
69
+ "c": 4,
70
+ "g": 5,
71
+ "t": 6
72
+ },
73
+ "merges": []
74
+ }
75
+ }
H3K4me3/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "mask_token": "[MASK]",
30
+ "model_max_length": 2500,
31
+ "pad_token": "[PAD]",
32
+ "tokenizer_class": "PreTrainedTokenizerFast",
33
+ "unk_token": "[UNK]"
34
+ }
H3K9me3/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000",
3
+ "architectures": [
4
+ "CaduceusForSequenceClassification"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_caduceus.CaduceusConfig",
8
+ "AutoModel": "modeling_caduceus.Caduceus",
9
+ "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM",
10
+ "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification"
11
+ },
12
+ "bidirectional": true,
13
+ "bidirectional_strategy": "add",
14
+ "bidirectional_weight_tie": true,
15
+ "complement_map": {
16
+ "0": 0,
17
+ "1": 1,
18
+ "2": 2,
19
+ "3": 6,
20
+ "4": 5,
21
+ "5": 4,
22
+ "6": 3,
23
+ "7": 7
24
+ },
25
+ "d_model": 768,
26
+ "fused_add_norm": true,
27
+ "id2label": {
28
+ "0": "Not",
29
+ "1": "Yes"
30
+ },
31
+ "initializer_cfg": {
32
+ "initializer_range": 0.02,
33
+ "n_residuals_per_layer": 1,
34
+ "rescale_prenorm_residual": true
35
+ },
36
+ "label2id": {
37
+ "Not": 0,
38
+ "Yes": 1
39
+ },
40
+ "model_type": "caduceus",
41
+ "n_layer": 28,
42
+ "norm_epsilon": 1e-05,
43
+ "pad_token_id": 0,
44
+ "pad_vocab_size_multiple": 8,
45
+ "problem_type": "single_label_classification",
46
+ "rcps": true,
47
+ "residual_in_fp32": true,
48
+ "rms_norm": true,
49
+ "ssm_cfg": {
50
+ "bias": false,
51
+ "conv_bias": true,
52
+ "d_conv": 4,
53
+ "d_state": 16,
54
+ "dt_init": "random",
55
+ "dt_init_floor": 0.0001,
56
+ "dt_max": 0.1,
57
+ "dt_min": 0.001,
58
+ "dt_rank": "auto",
59
+ "dt_scale": 1.0,
60
+ "expand": 2,
61
+ "use_fast_path": true
62
+ },
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.30.2",
65
+ "vocab_size": 8
66
+ }
H3K9me3/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69c48115f5192a694e042cd849bfc9133f891457f308ddb603fe6e96b90680f
3
+ size 448617482
H3K9me3/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": {
3
+ "content": "[MASK]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "[PAD]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
H3K9me3/tokenizer.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 2500,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 2500
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[MASK]",
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
+ "normalizer": {
49
+ "type": "Lowercase"
50
+ },
51
+ "pre_tokenizer": {
52
+ "type": "Whitespace"
53
+ },
54
+ "post_processor": null,
55
+ "decoder": null,
56
+ "model": {
57
+ "type": "BPE",
58
+ "dropout": null,
59
+ "unk_token": "[UNK]",
60
+ "continuing_subword_prefix": null,
61
+ "end_of_word_suffix": null,
62
+ "fuse_unk": false,
63
+ "byte_fallback": false,
64
+ "vocab": {
65
+ "[PAD]": 0,
66
+ "[MASK]": 1,
67
+ "[UNK]": 2,
68
+ "a": 3,
69
+ "c": 4,
70
+ "g": 5,
71
+ "t": 6
72
+ },
73
+ "merges": []
74
+ }
75
+ }
H3K9me3/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "mask_token": "[MASK]",
30
+ "model_max_length": 2500,
31
+ "pad_token": "[PAD]",
32
+ "tokenizer_class": "PreTrainedTokenizerFast",
33
+ "unk_token": "[UNK]"
34
+ }
H3k27ac/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000",
3
+ "architectures": [
4
+ "CaduceusForSequenceClassification"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_caduceus.CaduceusConfig",
8
+ "AutoModel": "modeling_caduceus.Caduceus",
9
+ "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM",
10
+ "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification"
11
+ },
12
+ "bidirectional": true,
13
+ "bidirectional_strategy": "add",
14
+ "bidirectional_weight_tie": true,
15
+ "complement_map": {
16
+ "0": 0,
17
+ "1": 1,
18
+ "2": 2,
19
+ "3": 6,
20
+ "4": 5,
21
+ "5": 4,
22
+ "6": 3,
23
+ "7": 7
24
+ },
25
+ "d_model": 768,
26
+ "fused_add_norm": true,
27
+ "id2label": {
28
+ "0": "Not",
29
+ "1": "Yes"
30
+ },
31
+ "initializer_cfg": {
32
+ "initializer_range": 0.02,
33
+ "n_residuals_per_layer": 1,
34
+ "rescale_prenorm_residual": true
35
+ },
36
+ "label2id": {
37
+ "Not": 0,
38
+ "Yes": 1
39
+ },
40
+ "model_type": "caduceus",
41
+ "n_layer": 28,
42
+ "norm_epsilon": 1e-05,
43
+ "pad_token_id": 0,
44
+ "pad_vocab_size_multiple": 8,
45
+ "problem_type": "single_label_classification",
46
+ "rcps": true,
47
+ "residual_in_fp32": true,
48
+ "rms_norm": true,
49
+ "ssm_cfg": {
50
+ "bias": false,
51
+ "conv_bias": true,
52
+ "d_conv": 4,
53
+ "d_state": 16,
54
+ "dt_init": "random",
55
+ "dt_init_floor": 0.0001,
56
+ "dt_max": 0.1,
57
+ "dt_min": 0.001,
58
+ "dt_rank": "auto",
59
+ "dt_scale": 1.0,
60
+ "expand": 2,
61
+ "use_fast_path": true
62
+ },
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.30.2",
65
+ "vocab_size": 8
66
+ }
H3k27ac/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b8373e811ee0c6ca80f5178606cba651639c9984c417d6b58cddf40e104d53
3
+ size 448617482
H3k27ac/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": {
3
+ "content": "[MASK]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "[PAD]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
H3k27ac/tokenizer.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 2500,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 2500
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[MASK]",
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
+ "normalizer": {
49
+ "type": "Lowercase"
50
+ },
51
+ "pre_tokenizer": {
52
+ "type": "Whitespace"
53
+ },
54
+ "post_processor": null,
55
+ "decoder": null,
56
+ "model": {
57
+ "type": "BPE",
58
+ "dropout": null,
59
+ "unk_token": "[UNK]",
60
+ "continuing_subword_prefix": null,
61
+ "end_of_word_suffix": null,
62
+ "fuse_unk": false,
63
+ "byte_fallback": false,
64
+ "vocab": {
65
+ "[PAD]": 0,
66
+ "[MASK]": 1,
67
+ "[UNK]": 2,
68
+ "a": 3,
69
+ "c": 4,
70
+ "g": 5,
71
+ "t": 6
72
+ },
73
+ "merges": []
74
+ }
75
+ }
H3k27ac/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "mask_token": "[MASK]",
30
+ "model_max_length": 2500,
31
+ "pad_token": "[PAD]",
32
+ "tokenizer_class": "PreTrainedTokenizerFast",
33
+ "unk_token": "[UNK]"
34
+ }
Pou5f1_TF/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000",
3
+ "architectures": [
4
+ "CaduceusForSequenceClassification"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_caduceus.CaduceusConfig",
8
+ "AutoModel": "modeling_caduceus.Caduceus",
9
+ "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM",
10
+ "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification"
11
+ },
12
+ "bidirectional": true,
13
+ "bidirectional_strategy": "add",
14
+ "bidirectional_weight_tie": true,
15
+ "complement_map": {
16
+ "0": 0,
17
+ "1": 1,
18
+ "2": 2,
19
+ "3": 6,
20
+ "4": 5,
21
+ "5": 4,
22
+ "6": 3,
23
+ "7": 7
24
+ },
25
+ "d_model": 768,
26
+ "fused_add_norm": true,
27
+ "id2label": {
28
+ "0": "Not",
29
+ "1": "Yes"
30
+ },
31
+ "initializer_cfg": {
32
+ "initializer_range": 0.02,
33
+ "n_residuals_per_layer": 1,
34
+ "rescale_prenorm_residual": true
35
+ },
36
+ "label2id": {
37
+ "Not": 0,
38
+ "Yes": 1
39
+ },
40
+ "model_type": "caduceus",
41
+ "n_layer": 28,
42
+ "norm_epsilon": 1e-05,
43
+ "pad_token_id": 0,
44
+ "pad_vocab_size_multiple": 8,
45
+ "problem_type": "single_label_classification",
46
+ "rcps": true,
47
+ "residual_in_fp32": true,
48
+ "rms_norm": true,
49
+ "ssm_cfg": {
50
+ "bias": false,
51
+ "conv_bias": true,
52
+ "d_conv": 4,
53
+ "d_state": 16,
54
+ "dt_init": "random",
55
+ "dt_init_floor": 0.0001,
56
+ "dt_max": 0.1,
57
+ "dt_min": 0.001,
58
+ "dt_rank": "auto",
59
+ "dt_scale": 1.0,
60
+ "expand": 2,
61
+ "use_fast_path": true
62
+ },
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.30.2",
65
+ "vocab_size": 8
66
+ }
Pou5f1_TF/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ca6135205cadf782f624110f7e795f80f0940f1f96536ca0228adf6bb2df846
3
+ size 448617482
Pou5f1_TF/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": {
3
+ "content": "[MASK]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "[PAD]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
Pou5f1_TF/tokenizer.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 800,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 800
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[MASK]",
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
+ "normalizer": {
49
+ "type": "Lowercase"
50
+ },
51
+ "pre_tokenizer": {
52
+ "type": "Whitespace"
53
+ },
54
+ "post_processor": null,
55
+ "decoder": null,
56
+ "model": {
57
+ "type": "BPE",
58
+ "dropout": null,
59
+ "unk_token": "[UNK]",
60
+ "continuing_subword_prefix": null,
61
+ "end_of_word_suffix": null,
62
+ "fuse_unk": false,
63
+ "byte_fallback": false,
64
+ "vocab": {
65
+ "[PAD]": 0,
66
+ "[MASK]": 1,
67
+ "[UNK]": 2,
68
+ "a": 3,
69
+ "c": 4,
70
+ "g": 5,
71
+ "t": 6
72
+ },
73
+ "merges": []
74
+ }
75
+ }
Pou5f1_TF/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "mask_token": "[MASK]",
30
+ "model_max_length": 800,
31
+ "pad_token": "[PAD]",
32
+ "tokenizer_class": "PreTrainedTokenizerFast",
33
+ "unk_token": "[UNK]"
34
+ }
README.md CHANGED
@@ -1,3 +1,87 @@
1
  ---
2
- license: cc-by-nc-sa-4.0
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
+ library_name: transformers
5
+ tags:
6
+ - DNA
7
+ - genomics
8
+ - fish
9
+ - sequence-classification
10
+ - FishCaduceus
11
+ - Fish_GUE
12
+ - fine-tuned
13
+ - single-nucleotide
14
  ---
15
+
16
+ # FishCaduceus-28L-512-FishGUE
17
+
18
+ `FishCaduceus-28L-512-FishGUE` is a collection of 17 task-specific models obtained by fine-tuning the pretrained `FishCaduceus-28L-512` DNA language model on downstream fish genomic function prediction tasks from Fish_GUE.
19
+
20
+ ## Model description
21
+
22
+ This repository contains one FishCaduceus backbone family and one fine-tuned sequence-classification model for each included task. The original task directory names are retained so that the repository can be used with `subfolder`-based loading.
23
+
24
+ ## Base model
25
+
26
+ The base model is [`FishCaduceus/FishCaduceus-28L-512`](https://huggingface.co/FishCaduceus/FishCaduceus-28L-512).
27
+
28
+ ## Included downstream tasks
29
+
30
+ | Task directory | Task description |
31
+ |---|---|
32
+ | `CTCF_TF` | CTCF transcription factor binding site prediction |
33
+ | `H3k27ac` | H3K27ac histone modification prediction |
34
+ | `H3K27me3` | H3K27me3 histone modification prediction |
35
+ | `H3K4me1` | H3K4me1 histone modification prediction |
36
+ | `H3K4me3` | H3K4me3 histone modification prediction |
37
+ | `H3K9me3` | H3K9me3 histone modification prediction |
38
+ | `Pou5f1_TF` | Pou5f1 transcription factor binding site prediction |
39
+ | `Sox2_TF` | Sox2 transcription factor binding site prediction |
40
+ | `prom_1k_all` | Promoter prediction using 1-kb sequences |
41
+ | `prom_1k_notata` | Promoter prediction using 1-kb sequences for the non-TATA promoter subset |
42
+ | `prom_1k_tata` | Promoter prediction using 1-kb sequences for the TATA promoter subset |
43
+ | `prom_300_all` | Promoter prediction using 300-bp sequences |
44
+ | `prom_300_notata` | Promoter prediction using 300-bp sequences for the non-TATA promoter subset |
45
+ | `prom_300_tata` | Promoter prediction using 300-bp sequences for the TATA promoter subset |
46
+ | `splice_acceptor` | Splice acceptor site prediction |
47
+ | `splice_donor` | Splice donor site prediction |
48
+ | `splice_all` | Splice site classification |
49
+
50
+ ## Repository structure
51
+
52
+ The repository contains 17 task directories. Each task retains its original name and contains a configuration, model weight file, and tokenizer files where present.
53
+
54
+ ## Training data
55
+
56
+ These models were fine-tuned on the corresponding downstream genomic function prediction tasks from Fish_GUE. No task sample counts are asserted here.
57
+
58
+ ## Intended uses
59
+
60
+ The models are intended for research on fish genomic sequence representation and task-specific genomic function prediction.
61
+
62
+ ## Limitations
63
+
64
+ The task models reflect the training data and task definitions used by Fish_GUE. Transfer to other species, assemblies, sequence lengths, or label definitions should be validated independently.
65
+
66
+ ## How to use
67
+
68
+ The audited task configurations declare `CaduceusForSequenceClassification`, `model_type: caduceus`, binary or three-way label mappings through `id2label`/`label2id`, and an `auto_map` for Caduceus classes. Loading with Transformers is expected to require `trust_remote_code=True` and an environment that provides the referenced Caduceus implementation. The task directories do not contain custom Python implementation files, so standalone execution from this repository alone is not guaranteed.
69
+
70
+ ## Files in this repository
71
+
72
+ Intermediate checkpoints, test metrics, test predictions, and training argument files were deliberately excluded. Model weights, configurations, and tokenizer files needed by the original task exports were retained.
73
+
74
+ ## Citation
75
+
76
+ The FishCaduceus manuscript is in preparation. Citation information will be added after publication.
77
+
78
+ ## Acknowledgements
79
+
80
+ FishCaduceus was developed for research on fish genomes at the Institute of Hydrobiology, Chinese Academy of Sciences.
81
+
82
+ ## Contact
83
+
84
+ Xiao-Qin Xia
85
+ Institute of Hydrobiology, Chinese Academy of Sciences
86
+ Email: xqxia@ihb.ac.cn
87
+
Sox2_TF/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000",
3
+ "architectures": [
4
+ "CaduceusForSequenceClassification"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_caduceus.CaduceusConfig",
8
+ "AutoModel": "modeling_caduceus.Caduceus",
9
+ "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM",
10
+ "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification"
11
+ },
12
+ "bidirectional": true,
13
+ "bidirectional_strategy": "add",
14
+ "bidirectional_weight_tie": true,
15
+ "complement_map": {
16
+ "0": 0,
17
+ "1": 1,
18
+ "2": 2,
19
+ "3": 6,
20
+ "4": 5,
21
+ "5": 4,
22
+ "6": 3,
23
+ "7": 7
24
+ },
25
+ "d_model": 768,
26
+ "fused_add_norm": true,
27
+ "id2label": {
28
+ "0": "Not",
29
+ "1": "Yes"
30
+ },
31
+ "initializer_cfg": {
32
+ "initializer_range": 0.02,
33
+ "n_residuals_per_layer": 1,
34
+ "rescale_prenorm_residual": true
35
+ },
36
+ "label2id": {
37
+ "Not": 0,
38
+ "Yes": 1
39
+ },
40
+ "model_type": "caduceus",
41
+ "n_layer": 28,
42
+ "norm_epsilon": 1e-05,
43
+ "pad_token_id": 0,
44
+ "pad_vocab_size_multiple": 8,
45
+ "problem_type": "single_label_classification",
46
+ "rcps": true,
47
+ "residual_in_fp32": true,
48
+ "rms_norm": true,
49
+ "ssm_cfg": {
50
+ "bias": false,
51
+ "conv_bias": true,
52
+ "d_conv": 4,
53
+ "d_state": 16,
54
+ "dt_init": "random",
55
+ "dt_init_floor": 0.0001,
56
+ "dt_max": 0.1,
57
+ "dt_min": 0.001,
58
+ "dt_rank": "auto",
59
+ "dt_scale": 1.0,
60
+ "expand": 2,
61
+ "use_fast_path": true
62
+ },
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.30.2",
65
+ "vocab_size": 8
66
+ }
Sox2_TF/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:942cd5cdd707aec9d95b2170172ba7658e278e5ce539c03dea62db2c81ba2121
3
+ size 448617482
Sox2_TF/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": {
3
+ "content": "[MASK]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "[PAD]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
Sox2_TF/tokenizer.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 800,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 800
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[MASK]",
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
+ "normalizer": {
49
+ "type": "Lowercase"
50
+ },
51
+ "pre_tokenizer": {
52
+ "type": "Whitespace"
53
+ },
54
+ "post_processor": null,
55
+ "decoder": null,
56
+ "model": {
57
+ "type": "BPE",
58
+ "dropout": null,
59
+ "unk_token": "[UNK]",
60
+ "continuing_subword_prefix": null,
61
+ "end_of_word_suffix": null,
62
+ "fuse_unk": false,
63
+ "byte_fallback": false,
64
+ "vocab": {
65
+ "[PAD]": 0,
66
+ "[MASK]": 1,
67
+ "[UNK]": 2,
68
+ "a": 3,
69
+ "c": 4,
70
+ "g": 5,
71
+ "t": 6
72
+ },
73
+ "merges": []
74
+ }
75
+ }
Sox2_TF/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "mask_token": "[MASK]",
30
+ "model_max_length": 800,
31
+ "pad_token": "[PAD]",
32
+ "tokenizer_class": "PreTrainedTokenizerFast",
33
+ "unk_token": "[UNK]"
34
+ }
prom_1k_all/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000",
3
+ "architectures": [
4
+ "CaduceusForSequenceClassification"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_caduceus.CaduceusConfig",
8
+ "AutoModel": "modeling_caduceus.Caduceus",
9
+ "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM",
10
+ "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification"
11
+ },
12
+ "bidirectional": true,
13
+ "bidirectional_strategy": "add",
14
+ "bidirectional_weight_tie": true,
15
+ "complement_map": {
16
+ "0": 0,
17
+ "1": 1,
18
+ "2": 2,
19
+ "3": 6,
20
+ "4": 5,
21
+ "5": 4,
22
+ "6": 3,
23
+ "7": 7
24
+ },
25
+ "d_model": 768,
26
+ "fused_add_norm": true,
27
+ "id2label": {
28
+ "0": "Not",
29
+ "1": "Yes"
30
+ },
31
+ "initializer_cfg": {
32
+ "initializer_range": 0.02,
33
+ "n_residuals_per_layer": 1,
34
+ "rescale_prenorm_residual": true
35
+ },
36
+ "label2id": {
37
+ "Not": 0,
38
+ "Yes": 1
39
+ },
40
+ "model_type": "caduceus",
41
+ "n_layer": 28,
42
+ "norm_epsilon": 1e-05,
43
+ "pad_token_id": 0,
44
+ "pad_vocab_size_multiple": 8,
45
+ "problem_type": "single_label_classification",
46
+ "rcps": true,
47
+ "residual_in_fp32": true,
48
+ "rms_norm": true,
49
+ "ssm_cfg": {
50
+ "bias": false,
51
+ "conv_bias": true,
52
+ "d_conv": 4,
53
+ "d_state": 16,
54
+ "dt_init": "random",
55
+ "dt_init_floor": 0.0001,
56
+ "dt_max": 0.1,
57
+ "dt_min": 0.001,
58
+ "dt_rank": "auto",
59
+ "dt_scale": 1.0,
60
+ "expand": 2,
61
+ "use_fast_path": true
62
+ },
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.30.2",
65
+ "vocab_size": 8
66
+ }
prom_1k_all/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d782300acb5388969f0d664a3ce08f23c94b203482c5bf0b0631b243525bd70
3
+ size 448617482
prom_1k_all/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": {
3
+ "content": "[MASK]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "[PAD]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
prom_1k_all/tokenizer.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 1000,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 1000
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[MASK]",
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
+ "normalizer": {
49
+ "type": "Lowercase"
50
+ },
51
+ "pre_tokenizer": {
52
+ "type": "Whitespace"
53
+ },
54
+ "post_processor": null,
55
+ "decoder": null,
56
+ "model": {
57
+ "type": "BPE",
58
+ "dropout": null,
59
+ "unk_token": "[UNK]",
60
+ "continuing_subword_prefix": null,
61
+ "end_of_word_suffix": null,
62
+ "fuse_unk": false,
63
+ "byte_fallback": false,
64
+ "vocab": {
65
+ "[PAD]": 0,
66
+ "[MASK]": 1,
67
+ "[UNK]": 2,
68
+ "a": 3,
69
+ "c": 4,
70
+ "g": 5,
71
+ "t": 6
72
+ },
73
+ "merges": []
74
+ }
75
+ }
prom_1k_all/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "mask_token": "[MASK]",
30
+ "model_max_length": 1000,
31
+ "pad_token": "[PAD]",
32
+ "tokenizer_class": "PreTrainedTokenizerFast",
33
+ "unk_token": "[UNK]"
34
+ }
prom_1k_notata/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nvme0/wb_ssd0/FishCaduceus/pretrained_model/FishCaduceus_train_l28_512/checkpoint-40000",
3
+ "architectures": [
4
+ "CaduceusForSequenceClassification"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_caduceus.CaduceusConfig",
8
+ "AutoModel": "modeling_caduceus.Caduceus",
9
+ "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM",
10
+ "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification"
11
+ },
12
+ "bidirectional": true,
13
+ "bidirectional_strategy": "add",
14
+ "bidirectional_weight_tie": true,
15
+ "complement_map": {
16
+ "0": 0,
17
+ "1": 1,
18
+ "2": 2,
19
+ "3": 6,
20
+ "4": 5,
21
+ "5": 4,
22
+ "6": 3,
23
+ "7": 7
24
+ },
25
+ "d_model": 768,
26
+ "fused_add_norm": true,
27
+ "id2label": {
28
+ "0": "Not",
29
+ "1": "Yes"
30
+ },
31
+ "initializer_cfg": {
32
+ "initializer_range": 0.02,
33
+ "n_residuals_per_layer": 1,
34
+ "rescale_prenorm_residual": true
35
+ },
36
+ "label2id": {
37
+ "Not": 0,
38
+ "Yes": 1
39
+ },
40
+ "model_type": "caduceus",
41
+ "n_layer": 28,
42
+ "norm_epsilon": 1e-05,
43
+ "pad_token_id": 0,
44
+ "pad_vocab_size_multiple": 8,
45
+ "problem_type": "single_label_classification",
46
+ "rcps": true,
47
+ "residual_in_fp32": true,
48
+ "rms_norm": true,
49
+ "ssm_cfg": {
50
+ "bias": false,
51
+ "conv_bias": true,
52
+ "d_conv": 4,
53
+ "d_state": 16,
54
+ "dt_init": "random",
55
+ "dt_init_floor": 0.0001,
56
+ "dt_max": 0.1,
57
+ "dt_min": 0.001,
58
+ "dt_rank": "auto",
59
+ "dt_scale": 1.0,
60
+ "expand": 2,
61
+ "use_fast_path": true
62
+ },
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.30.2",
65
+ "vocab_size": 8
66
+ }
prom_1k_notata/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86e0c0dab34b7ab3bf6562978e20846548dc0fcd007c52e5eab6dbf8e2136f31
3
+ size 448617482
prom_1k_notata/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": {
3
+ "content": "[MASK]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "[PAD]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
prom_1k_notata/tokenizer.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 1000,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 1000
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[MASK]",
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
+ "normalizer": {
49
+ "type": "Lowercase"
50
+ },
51
+ "pre_tokenizer": {
52
+ "type": "Whitespace"
53
+ },
54
+ "post_processor": null,
55
+ "decoder": null,
56
+ "model": {
57
+ "type": "BPE",
58
+ "dropout": null,
59
+ "unk_token": "[UNK]",
60
+ "continuing_subword_prefix": null,
61
+ "end_of_word_suffix": null,
62
+ "fuse_unk": false,
63
+ "byte_fallback": false,
64
+ "vocab": {
65
+ "[PAD]": 0,
66
+ "[MASK]": 1,
67
+ "[UNK]": 2,
68
+ "a": 3,
69
+ "c": 4,
70
+ "g": 5,
71
+ "t": 6
72
+ },
73
+ "merges": []
74
+ }
75
+ }