Hugging Face's logo

deepakint
/
knowledge-platform-ner

Token Classification
Transformers
Safetensors
English
German
modernbert
ner
named-entity-recognition
knowledge-platform
multilingual
patents
scientific-papers
cross-domain
english
german
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
deepakint commited on
Commit
4b57573
·
verified ·
1 Parent(s): b28843f

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. config.json +144 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +17 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForTokenClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": null,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "O",
24
+ "1": "B-PER",
25
+ "2": "I-PER",
26
+ "3": "B-ORG",
27
+ "4": "I-ORG",
28
+ "5": "B-LOC",
29
+ "6": "I-LOC",
30
+ "7": "B-ANIM",
31
+ "8": "I-ANIM",
32
+ "9": "B-BIO",
33
+ "10": "I-BIO",
34
+ "11": "B-CEL",
35
+ "12": "I-CEL",
36
+ "13": "B-DIS",
37
+ "14": "I-DIS",
38
+ "15": "B-EVE",
39
+ "16": "I-EVE",
40
+ "17": "B-FOOD",
41
+ "18": "I-FOOD",
42
+ "19": "B-INST",
43
+ "20": "I-INST",
44
+ "21": "B-MEDIA",
45
+ "22": "I-MEDIA",
46
+ "23": "B-MYTH",
47
+ "24": "I-MYTH",
48
+ "25": "B-PLANT",
49
+ "26": "I-PLANT",
50
+ "27": "B-TIME",
51
+ "28": "I-TIME",
52
+ "29": "B-VEHI",
53
+ "30": "I-VEHI"
54
+ },
55
+ "initializer_cutoff_factor": 2.0,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 1152,
58
+ "label2id": {
59
+ "B-ANIM": 7,
60
+ "B-BIO": 9,
61
+ "B-CEL": 11,
62
+ "B-DIS": 13,
63
+ "B-EVE": 15,
64
+ "B-FOOD": 17,
65
+ "B-INST": 19,
66
+ "B-LOC": 5,
67
+ "B-MEDIA": 21,
68
+ "B-MYTH": 23,
69
+ "B-ORG": 3,
70
+ "B-PER": 1,
71
+ "B-PLANT": 25,
72
+ "B-TIME": 27,
73
+ "B-VEHI": 29,
74
+ "I-ANIM": 8,
75
+ "I-BIO": 10,
76
+ "I-CEL": 12,
77
+ "I-DIS": 14,
78
+ "I-EVE": 16,
79
+ "I-FOOD": 18,
80
+ "I-INST": 20,
81
+ "I-LOC": 6,
82
+ "I-MEDIA": 22,
83
+ "I-MYTH": 24,
84
+ "I-ORG": 4,
85
+ "I-PER": 2,
86
+ "I-PLANT": 26,
87
+ "I-TIME": 28,
88
+ "I-VEHI": 30,
89
+ "O": 0
90
+ },
91
+ "layer_norm_eps": 1e-05,
92
+ "layer_types": [
93
+ "full_attention",
94
+ "sliding_attention",
95
+ "sliding_attention",
96
+ "full_attention",
97
+ "sliding_attention",
98
+ "sliding_attention",
99
+ "full_attention",
100
+ "sliding_attention",
101
+ "sliding_attention",
102
+ "full_attention",
103
+ "sliding_attention",
104
+ "sliding_attention",
105
+ "full_attention",
106
+ "sliding_attention",
107
+ "sliding_attention",
108
+ "full_attention",
109
+ "sliding_attention",
110
+ "sliding_attention",
111
+ "full_attention",
112
+ "sliding_attention",
113
+ "sliding_attention",
114
+ "full_attention"
115
+ ],
116
+ "local_attention": 128,
117
+ "max_position_embeddings": 8192,
118
+ "mlp_bias": false,
119
+ "mlp_dropout": 0.0,
120
+ "model_type": "modernbert",
121
+ "norm_bias": false,
122
+ "norm_eps": 1e-05,
123
+ "num_attention_heads": 12,
124
+ "num_hidden_layers": 22,
125
+ "pad_token_id": 50283,
126
+ "position_embedding_type": "absolute",
127
+ "rope_parameters": {
128
+ "full_attention": {
129
+ "rope_theta": 160000.0,
130
+ "rope_type": "default"
131
+ },
132
+ "sliding_attention": {
133
+ "rope_theta": 10000.0,
134
+ "rope_type": "default"
135
+ }
136
+ },
137
+ "sep_token_id": 50282,
138
+ "sparse_pred_ignore_index": -100,
139
+ "sparse_prediction": false,
140
+ "tie_word_embeddings": true,
141
+ "transformers_version": "5.6.0",
142
+ "use_cache": false,
143
+ "vocab_size": 50368
144
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc10f66ca0b71cb40cfc68f91f1826a5627cd22e141af5cf7189862fd606588
3
+ size 598528996
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 8192,
13
+ "pad_token": "[PAD]",
14
+ "sep_token": "[SEP]",
15
+ "tokenizer_class": "TokenizersBackend",
16
+ "unk_token": "[UNK]"
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e57a8425eda527131b441677c380b03bdfd2eb1ead2cc0bfab158dac678c835
3
+ size 4920