skt/A.X-Encoder-base

1{2  "architectures": [3    "ModernBertForMaskedLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 0,8  "classifier_activation": "gelu",9  "classifier_bias": false,10  "classifier_dropout": 0.0,11  "classifier_pooling": "mean",12  "cls_token_id": 0,13  "decoder_bias": true,14  "deterministic_flash_attn": false,15  "embedding_dropout": 0.0,16  "eos_token_id": 1,17  "global_attn_every_n_layers": 3,18  "global_rope_theta": 160000,19  "gradient_checkpointing": false,20  "hidden_activation": "gelu",21  "hidden_size": 768,22  "initializer_cutoff_factor": 2.0,23  "initializer_range": 0.02,24  "intermediate_size": 1152,25  "layer_norm_eps": 1e-05,26  "local_attention": 128,27  "local_rope_theta": 10000.0,28  "max_position_embeddings": 16384,29  "mlp_bias": false,30  "mlp_dropout": 0.0,31  "model_type": "modernbert",32  "norm_bias": false,33  "norm_eps": 1e-05,34  "num_attention_heads": 12,35  "num_hidden_layers": 22,36  "pad_token_id": 49999,37  "position_embedding_type": "absolute",38  "reference_compile": true,39  "repad_logits_with_grad": false,40  "sep_token_id": 1,41  "sparse_pred_ignore_index": -100,42  "sparse_prediction": false,43  "torch_dtype": "bfloat16",44  "transformers_version": "4.50.0",45  "vocab_size": 5000046}47