VictorMorand commited on
Commit
ad28b57
·
verified ·
1 Parent(s): bdec378

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. config.json +83 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
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": 50282,
19
+ "global_attn_every_n_layers": 3,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 512,
23
+ "id2label": {
24
+ "0": "LABEL_0"
25
+ },
26
+ "initializer_cutoff_factor": 2.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 768,
29
+ "is_causal": false,
30
+ "label2id": {
31
+ "LABEL_0": 0
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "layer_types": [
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention"
54
+ ],
55
+ "local_attention": 128,
56
+ "max_position_embeddings": 7999,
57
+ "mlp_bias": false,
58
+ "mlp_dropout": 0.0,
59
+ "model_type": "modernbert",
60
+ "norm_bias": false,
61
+ "norm_eps": 1e-05,
62
+ "num_attention_heads": 8,
63
+ "num_hidden_layers": 19,
64
+ "pad_token_id": 50283,
65
+ "position_embedding_type": "sans_pos",
66
+ "repad_logits_with_grad": false,
67
+ "rope_parameters": {
68
+ "full_attention": {
69
+ "rope_theta": 160000.0,
70
+ "rope_type": "default"
71
+ },
72
+ "sliding_attention": {
73
+ "rope_theta": 160000.0,
74
+ "rope_type": "default"
75
+ }
76
+ },
77
+ "sep_token_id": 50282,
78
+ "sparse_pred_ignore_index": -100,
79
+ "sparse_prediction": false,
80
+ "tie_word_embeddings": true,
81
+ "transformers_version": "5.0.0",
82
+ "vocab_size": 50368
83
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f10ff815bc1d9ec0db7c87f7cfb42a2c7628d30d2d7e29fdf769cf5878adfd8
3
+ size 273643524