Hugging Face's logo

Dexifried
/
dex-router-model

Safetensors
modernbert
Model card Files
xet
 Community
Dexifried commited on
Commit
e819c8b
·
verified ·
1 Parent(s): c4def3b

Dex Neural Framework: Stabilized 9-Intent Matrix

Browse files
Files changed (4) hide show
  1. config.json +101 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +16 -0
config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "ACCESS_MEMORY",
24
+ "1": "AIDER_SURGERY",
25
+ "2": "CODE_REVIEW",
26
+ "3": "DYNAMIC_BROKER",
27
+ "4": "IMAGE_GEN",
28
+ "5": "LOCAL_CMD",
29
+ "6": "SOCIAL_CHAT",
30
+ "7": "STRATEGIC_PLANNER",
31
+ "8": "UPDATE_MEMORY"
32
+ },
33
+ "initializer_cutoff_factor": 2.0,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 1152,
36
+ "label2id": {
37
+ "ACCESS_MEMORY": 0,
38
+ "AIDER_SURGERY": 1,
39
+ "CODE_REVIEW": 2,
40
+ "DYNAMIC_BROKER": 3,
41
+ "IMAGE_GEN": 4,
42
+ "LOCAL_CMD": 5,
43
+ "SOCIAL_CHAT": 6,
44
+ "STRATEGIC_PLANNER": 7,
45
+ "UPDATE_MEMORY": 8
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "layer_types": [
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "full_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "full_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "full_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "full_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "full_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "full_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "full_attention"
71
+ ],
72
+ "local_attention": 128,
73
+ "max_position_embeddings": 8192,
74
+ "mlp_bias": false,
75
+ "mlp_dropout": 0.0,
76
+ "model_type": "modernbert",
77
+ "norm_bias": false,
78
+ "norm_eps": 1e-05,
79
+ "num_attention_heads": 12,
80
+ "num_hidden_layers": 22,
81
+ "pad_token_id": 50283,
82
+ "position_embedding_type": "absolute",
83
+ "problem_type": "single_label_classification",
84
+ "rope_parameters": {
85
+ "full_attention": {
86
+ "rope_theta": 160000.0,
87
+ "rope_type": "default"
88
+ },
89
+ "sliding_attention": {
90
+ "rope_theta": 10000.0,
91
+ "rope_type": "default"
92
+ }
93
+ },
94
+ "sep_token_id": 50282,
95
+ "sparse_pred_ignore_index": -100,
96
+ "sparse_prediction": false,
97
+ "tie_word_embeddings": true,
98
+ "transformers_version": "5.3.0",
99
+ "use_cache": false,
100
+ "vocab_size": 50368
101
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:677b9392e650f10879aa29316104063e2d4d6fbcb44992bd713331e061918e7d
3
+ size 598461316
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
+ }