Hugging Face's logo

MarsSecurity
/
tech-entity-biencoder

ONNX
modernbert
Model card Files
xet
 Community
zeevmarssec commited on
Commit
4c68ef0
·
verified ·
1 Parent(s): 67c5f5f

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. 1_Pooling/config.json +10 -0
  2. config.json +88 -0
  3. config_sentence_transformers.json +14 -0
  4. modules.json +14 -0
  5. onnx/model.onnx +3 -0
  6. sentence_bert_config.json +4 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +23 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertModel"
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": "LABEL_0"
24
+ },
25
+ "initializer_cutoff_factor": 2.0,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 1152,
28
+ "label2id": {
29
+ "LABEL_0": 0
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "layer_types": [
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "full_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "full_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "full_attention"
55
+ ],
56
+ "local_attention": 128,
57
+ "max_position_embeddings": 8192,
58
+ "mlp_bias": false,
59
+ "mlp_dropout": 0.0,
60
+ "model_type": "modernbert",
61
+ "norm_bias": false,
62
+ "norm_eps": 1e-05,
63
+ "num_attention_heads": 12,
64
+ "num_hidden_layers": 22,
65
+ "pad_token_id": 50283,
66
+ "position_embedding_type": "absolute",
67
+ "repad_logits_with_grad": false,
68
+ "rope_parameters": {
69
+ "full_attention": {
70
+ "rope_theta": 160000.0,
71
+ "rope_type": "default"
72
+ },
73
+ "sliding_attention": {
74
+ "rope_theta": 10000.0,
75
+ "rope_type": "default"
76
+ }
77
+ },
78
+ "sentence_transformers": {
79
+ "activation_fn": "torch.nn.modules.activation.Sigmoid",
80
+ "version": "5.0.0"
81
+ },
82
+ "sep_token_id": 50282,
83
+ "sparse_pred_ignore_index": -100,
84
+ "sparse_prediction": false,
85
+ "tie_word_embeddings": true,
86
+ "transformers_version": "5.2.0",
87
+ "vocab_size": 50368
88
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "SentenceTransformer",
3
+ "__version__": {
4
+ "sentence_transformers": "5.2.3",
5
+ "transformers": "5.2.0",
6
+ "pytorch": "2.10.0"
7
+ },
8
+ "prompts": {
9
+ "query": "",
10
+ "document": ""
11
+ },
12
+ "default_prompt_name": null,
13
+ "similarity_fn_name": "cosine"
14
+ }
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12784c5ad7de1e39a2180ac4cdb5623c28b6c24cd643af2132cc666c60fae5a1
3
+ size 596598081
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 1024,
3
+ "do_lower_case": false
4
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": true,
6
+ "mask_token": "[MASK]",
7
+ "max_length": 1024,
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 1024,
13
+ "pad_to_multiple_of": null,
14
+ "pad_token": "[PAD]",
15
+ "pad_token_type_id": 0,
16
+ "padding_side": "right",
17
+ "sep_token": "[SEP]",
18
+ "stride": 0,
19
+ "tokenizer_class": "TokenizersBackend",
20
+ "truncation_side": "right",
21
+ "truncation_strategy": "longest_first",
22
+ "unk_token": "[UNK]"
23
+ }