ucrelnlp/PyMUSAS-Neural-Multilingual-Small-BEM

1{2  "architectures": [3    "ModernBertForMaskedLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 2,8  "classifier_activation": "gelu",9  "classifier_bias": false,10  "classifier_dropout": 0.0,11  "classifier_pooling": "mean",12  "cls_token_id": 1,13  "decoder_bias": true,14  "deterministic_flash_attn": false,15  "dtype": "float32",16  "embedding_dropout": 0.0,17  "eos_token_id": 1,18  "global_attn_every_n_layers": 3,19  "global_rope_theta": 160000,20  "gradient_checkpointing": false,21  "hidden_activation": "gelu",22  "hidden_size": 384,23  "initializer_cutoff_factor": 2.0,24  "initializer_range": 0.02,25  "intermediate_size": 1152,26  "layer_norm_eps": 1e-05,27  "local_attention": 128,28  "local_rope_theta": 160000,29  "mask_token_id": 4,30  "max_position_embeddings": 8192,31  "mlp_bias": false,32  "mlp_dropout": 0.0,33  "model_type": "modernbert",34  "norm_bias": false,35  "norm_eps": 1e-05,36  "num_attention_heads": 6,37  "num_hidden_layers": 22,38  "pad_token_id": 0,39  "position_embedding_type": "sans_pos",40  "repad_logits_with_grad": false,41  "sep_token_id": 1,42  "sparse_pred_ignore_index": -100,43  "sparse_prediction": false,44  "transformers_version": "4.57.1",45  "vocab_size": 25600046}47