AdamCodd commited on
Commit
4279b04
·
verified ·
1 Parent(s): 64ac7e9

Upload 4 files

Browse files
Files changed (4) hide show
  1. config.json +88 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +17 -0
config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "causal_mask": false,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "dtype": "float32",
17
+ "embedding_dropout": 0.0,
18
+ "eos_token_id": null,
19
+ "global_attn_every_n_layers": 3,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 512,
23
+ "id2label": {
24
+ "0": "ENTAILMENT",
25
+ "1": "NEUTRAL",
26
+ "2": "CONTRADICTION"
27
+ },
28
+ "initializer_cutoff_factor": 2.0,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 768,
31
+ "is_causal": false,
32
+ "label2id": {
33
+ "CONTRADICTION": 2,
34
+ "ENTAILMENT": 0,
35
+ "NEUTRAL": 1
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "layer_types": [
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
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "full_attention"
58
+ ],
59
+ "local_attention": 128,
60
+ "max_position_embeddings": 7999,
61
+ "mlp_bias": false,
62
+ "mlp_dropout": 0.0,
63
+ "model_type": "modernbert",
64
+ "norm_bias": false,
65
+ "norm_eps": 1e-05,
66
+ "num_attention_heads": 8,
67
+ "num_hidden_layers": 19,
68
+ "pad_token_id": 50283,
69
+ "position_embedding_type": "sans_pos",
70
+ "problem_type": "single_label_classification",
71
+ "rope_parameters": {
72
+ "full_attention": {
73
+ "rope_theta": 160000.0,
74
+ "rope_type": "default"
75
+ },
76
+ "sliding_attention": {
77
+ "rope_theta": 160000.0,
78
+ "rope_type": "default"
79
+ }
80
+ },
81
+ "sep_token_id": 50282,
82
+ "sparse_pred_ignore_index": -100,
83
+ "sparse_prediction": false,
84
+ "tie_word_embeddings": true,
85
+ "transformers_version": "5.14.1",
86
+ "use_cache": false,
87
+ "vocab_size": 50368
88
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:437774d3c3688e384482070b71a229eb356c065eb4a4c5f0dc0053aa65255ef6
3
+ size 273647628
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
+ }