Hugging Face's logo

lumicero
/
BioNER-DS

Safetensors
Model card Files
xet
 Community
4

Upload 28 files

#2
by SenomyNearl - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+242197
-0
Files changed (28) hide show
  1. seed_42_config2/best_model/config.json +39 -0
  2. seed_42_config2/best_model/model.safetensors +3 -0
  3. seed_42_config2/best_model/special_tokens_map.json +7 -0
  4. seed_42_config2/best_model/tokenizer.json +0 -0
  5. seed_42_config2/best_model/tokenizer_config.json +58 -0
  6. seed_42_config2/best_model/training_args.bin +3 -0
  7. seed_42_config2/best_model/vocab.txt +0 -0
  8. seed_42_config3/best_model/config.json +38 -0
  9. seed_42_config3/best_model/model.safetensors +3 -0
  10. seed_42_config3/best_model/special_tokens_map.json +7 -0
  11. seed_42_config3/best_model/tokenizer.json +0 -0
  12. seed_42_config3/best_model/tokenizer_config.json +58 -0
  13. seed_42_config3/best_model/training_args.bin +3 -0
  14. seed_42_config3/best_model/vocab.txt +0 -0
  15. seed_42_config4/phase1/best_model/config.json +46 -0
  16. seed_42_config4/phase1/best_model/model.safetensors +3 -0
  17. seed_42_config4/phase1/best_model/special_tokens_map.json +7 -0
  18. seed_42_config4/phase1/best_model/tokenizer.json +0 -0
  19. seed_42_config4/phase1/best_model/tokenizer_config.json +58 -0
  20. seed_42_config4/phase1/best_model/training_args.bin +3 -0
  21. seed_42_config4/phase1/best_model/vocab.txt +0 -0
  22. seed_42_config4/phase2/best_model/config.json +46 -0
  23. seed_42_config4/phase2/best_model/model.safetensors +3 -0
  24. seed_42_config4/phase2/best_model/special_tokens_map.json +7 -0
  25. seed_42_config4/phase2/best_model/tokenizer.json +0 -0
  26. seed_42_config4/phase2/best_model/tokenizer_config.json +58 -0
  27. seed_42_config4/phase2/best_model/training_args.bin +3 -0
  28. seed_42_config4/phase2/best_model/vocab.txt +0 -0
seed_42_config2/best_model/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-Chemical",
14
+ "2": "I-Chemical",
15
+ "3": "B-Disease",
16
+ "4": "I-Disease"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "B-Chemical": 1,
22
+ "B-Disease": 3,
23
+ "I-Chemical": 2,
24
+ "I-Disease": 4,
25
+ "O": 0
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "transformers_version": "4.57.6",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 28996,
38
+ "xla_device": null
39
+ }
seed_42_config2/best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f6dcb1e9c39778d1596b9316781d740d49dade6361e31014526ceb6aeeba7c
3
+ size 430917436
seed_42_config2/best_model/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
seed_42_config2/best_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_42_config2/best_model/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
seed_42_config2/best_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6581ecd8213421719d99178fe37eae714722a1c6d54dd12fd035de3f3ad809f
3
+ size 5905
seed_42_config2/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
seed_42_config3/best_model/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-Chemical",
14
+ "2": "I-Chemical",
15
+ "3": "B-Disease",
16
+ "4": "I-Disease"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "B-Chemical": 1,
22
+ "B-Disease": 3,
23
+ "I-Chemical": 2,
24
+ "I-Disease": 4,
25
+ "O": 0
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "transformers_version": "4.57.6",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 30522
38
+ }
seed_42_config3/best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5c726623fd4739af5943e35a924f26bbecce9e486eedc13596c606483d971a
3
+ size 435605316
seed_42_config3/best_model/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
seed_42_config3/best_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_42_config3/best_model/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
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
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
seed_42_config3/best_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba8bbfc039ee5f803cf49e3c26f4d06b7ac8b48a0e20add24ea9e17d56820ab3
3
+ size 5905
seed_42_config3/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
seed_42_config4/phase1/best_model/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-Chemical",
14
+ "2": "I-Chemical",
15
+ "3": "B-Disease",
16
+ "4": "I-Disease",
17
+ "5": "B-Virus",
18
+ "6": "I-Virus",
19
+ "7": "B-Gene",
20
+ "8": "I-Gene"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "B-Chemical": 1,
26
+ "B-Disease": 3,
27
+ "B-Gene": 7,
28
+ "B-Virus": 5,
29
+ "I-Chemical": 2,
30
+ "I-Disease": 4,
31
+ "I-Gene": 8,
32
+ "I-Virus": 6,
33
+ "O": 0
34
+ },
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 512,
37
+ "model_type": "bert",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "transformers_version": "4.57.6",
43
+ "type_vocab_size": 2,
44
+ "use_cache": true,
45
+ "vocab_size": 30522
46
+ }
seed_42_config4/phase1/best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c74cee8a76f1d3ec82b2e95b1513d3d3fde9274d6cc122737b4a0f217febdde
3
+ size 435617620
seed_42_config4/phase1/best_model/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
seed_42_config4/phase1/best_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_42_config4/phase1/best_model/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
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
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
seed_42_config4/phase1/best_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7070df6b39ff005c75d8827357ed6f8b98469d7c09fa62ed79980fdf0c97e614
3
+ size 5905
seed_42_config4/phase1/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
seed_42_config4/phase2/best_model/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-Chemical",
14
+ "2": "I-Chemical",
15
+ "3": "B-Disease",
16
+ "4": "I-Disease",
17
+ "5": "B-Virus",
18
+ "6": "I-Virus",
19
+ "7": "B-Gene",
20
+ "8": "I-Gene"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "B-Chemical": 1,
26
+ "B-Disease": 3,
27
+ "B-Gene": 7,
28
+ "B-Virus": 5,
29
+ "I-Chemical": 2,
30
+ "I-Disease": 4,
31
+ "I-Gene": 8,
32
+ "I-Virus": 6,
33
+ "O": 0
34
+ },
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 512,
37
+ "model_type": "bert",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "transformers_version": "4.57.6",
43
+ "type_vocab_size": 2,
44
+ "use_cache": true,
45
+ "vocab_size": 30522
46
+ }
seed_42_config4/phase2/best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5480899f8f45a68efabb8e96bfc60860de8996ba53f1bb77fb349890db1db97
3
+ size 435617620
seed_42_config4/phase2/best_model/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
seed_42_config4/phase2/best_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_42_config4/phase2/best_model/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
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
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
seed_42_config4/phase2/best_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e292d63ce6de5d4b5a8156f56601a2cd4d0e65d04e175c5589039b355354510
3
+ size 5905
seed_42_config4/phase2/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff