Hugging Face's logo

davanstrien
/
modernbert-hf-dataset-domain-v3

Text Classification
Transformers
Safetensors
English
modernbert
dataset-classification
huggingface-hub
domain-classification
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
davanstrien HF Staff commited on
Commit
5c68e28
·
verified ·
1 Parent(s): 66286b9

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +102 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +16 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
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": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "biology",
24
+ "1": "chemistry",
25
+ "2": "climate",
26
+ "3": "code",
27
+ "4": "cybersecurity",
28
+ "5": "finance",
29
+ "6": "legal",
30
+ "7": "math",
31
+ "8": "medical",
32
+ "9": "none"
33
+ },
34
+ "initializer_cutoff_factor": 2.0,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 1152,
37
+ "label2id": {
38
+ "biology": 0,
39
+ "chemistry": 1,
40
+ "climate": 2,
41
+ "code": 3,
42
+ "cybersecurity": 4,
43
+ "finance": 5,
44
+ "legal": 6,
45
+ "math": 7,
46
+ "medical": 8,
47
+ "none": 9
48
+ },
49
+ "layer_norm_eps": 1e-05,
50
+ "layer_types": [
51
+ "full_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "full_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "full_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "full_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "full_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "full_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "full_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "full_attention"
73
+ ],
74
+ "local_attention": 128,
75
+ "max_position_embeddings": 8192,
76
+ "mlp_bias": false,
77
+ "mlp_dropout": 0.0,
78
+ "model_type": "modernbert",
79
+ "norm_bias": false,
80
+ "norm_eps": 1e-05,
81
+ "num_attention_heads": 12,
82
+ "num_hidden_layers": 22,
83
+ "pad_token_id": 50283,
84
+ "position_embedding_type": "absolute",
85
+ "rope_parameters": {
86
+ "full_attention": {
87
+ "rope_theta": 160000.0,
88
+ "rope_type": "default"
89
+ },
90
+ "sliding_attention": {
91
+ "rope_theta": 10000.0,
92
+ "rope_type": "default"
93
+ }
94
+ },
95
+ "sep_token_id": 50282,
96
+ "sparse_pred_ignore_index": -100,
97
+ "sparse_prediction": false,
98
+ "tie_word_embeddings": true,
99
+ "transformers_version": "5.4.0",
100
+ "use_cache": false,
101
+ "vocab_size": 50368
102
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f09af377ce0eb59558825d4bf8e1dec99427fa0716d2ae177200f07503f6ad
3
+ size 598464400
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "mask_token": "[MASK]",
7
+ "model_input_names": [
8
+ "input_ids",
9
+ "attention_mask"
10
+ ],
11
+ "model_max_length": 8192,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21b6f8c07a420bfe5761939898f0cd7bfbeb1b2e9f8998c2e8b4d855a95285a6
3
+ size 5201