Hugging Face's logo

blab-jhu
/
test-32m-dec

PyTorch
modernbert
Model card Files Community
1
test-32m-dec
File size: 2,596 Bytes 
2b4eb92
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
 
{
    "allow_embedding_resizing": true,
    "_name_or_path": "ModernBERT-dec-32m",
    "architectures": [
      "ModernBertForCausalLM"
    ],
    "attention_layer": "rope",
    "attention_probs_dropout_prob": 0.0,
    "attn_out_bias": false,
    "attn_out_dropout_prob": 0.1,
    "attn_qkv_bias": false,
    "bert_layer": "prenorm",
    "classifier_dropout": null,
    "compile_model": true,
    "reference_compile": false,
    "decoder_bias": true,
    "deterministic_fa2": true,
    "embed_dropout_prob": 0.0,
    "embed_norm": true,
    "embedding_layer": "sans_pos",
    "encoder_layer": "base",
    "final_norm": true,
    "global_attn_every_n_layers": 3,
    "gradient_checkpointing": false,
    "head_class_act": "silu",
    "head_class_bias": false,
    "head_class_dropout": 0.0,
    "head_class_norm": false,
    "head_pred_act": "gelu",
    "head_pred_bias": false,
    "head_pred_dropout": 0.0,
    "head_pred_norm": true,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 384,
    "init_cutoff_factor": 2.0,
    "init_method": "full_megatron",
    "init_small_embedding": false,
    "init_std": 0.02,
    "initial_attention_layer": null,
    "initial_bert_layer": null,
    "initial_mlp_layer": null,
    "initializer_range": 0.02,
    "intermediate_size": 576,
    "layer_norm_eps": 1e-12,
    "local_attn_rotary_emb_base": -1,
    "local_attn_rotary_emb_dim": null,
    "loss_function": "fa_cross_entropy",
    "deterministic_flash_attn": false,
    "loss_kwargs": {
        "reduction": "mean"
    },
    "masked_prediction": false,
    "causal_mask": true,
    "max_position_embeddings": 1024,
    "mlp_dropout_prob": 0.0,
    "mlp_in_bias": false,
    "mlp_layer": "glu",
    "mlp_out_bias": false,
    "model_type": "modernbert",
    "norm_kwargs": {
        "bias": false,
        "eps": 1e-05
    },
    "normalization": "layernorm",
    "num_attention_heads": 6,
    "num_hidden_layers": 10,
    "num_initial_layers": 1,
    "pad_logits": true,
    "pad_token_id": null,
    "padding": "unpadded",
    "pooling_type": "cls",
    "position_embedding_type": "absolute",
    "global_rope_theta": 160000.0,
    "local_rope_theta": 160000.0,
    "rotary_emb_base": 160000.0,
    "rotary_emb_dim": 64,
    "rotary_emb_interleaved": false,
    "rotary_emb_scale_base": null,
    "skip_first_prenorm": true,
    "sliding_window": 128,
    "transformers_version": "4.44.1",
    "type_vocab_size": 2,
    "unpad_embeddings": true,
    "use_cache": true,
    "use_fa2": true,
    "use_sdpa_attn_mask": false,
    "vocab_size": 50368,
    "is_causal": true
}