{ "backbone": "answerdotai/ModernBERT-large", "backbone_config": { "pad_token_id": 50283, "bos_token_id": 50281, "eos_token_id": 50282, "cls_token_id": 50281, "sep_token_id": 50282, "tie_word_embeddings": true, "vocab_size": 50368, "max_position_embeddings": 8192, "hidden_size": 1024, "intermediate_size": 2624, "num_hidden_layers": 28, "num_attention_heads": 16, "initializer_range": 0.02, "initializer_cutoff_factor": 2.0, "norm_eps": 1e-05, "norm_bias": false, "attention_bias": false, "attention_dropout": 0.0, "hidden_activation": "gelu", "local_attention": 128, "embedding_dropout": 0.0, "mlp_bias": false, "mlp_dropout": 0.0, "decoder_bias": true, "classifier_pooling": "mean", "classifier_dropout": 0.0, "classifier_bias": false, "classifier_activation": "gelu", "deterministic_flash_attn": false, "sparse_prediction": false, "sparse_pred_ignore_index": -100, "layer_types": [ "full_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "full_attention" ], "global_attn_every_n_layers": 3, "rope_parameters": { "sliding_attention": { "rope_type": "default", "rope_theta": 10000.0 }, "full_attention": { "rope_type": "default", "rope_theta": 160000.0 } }, "return_dict": true, "output_hidden_states": false, "dtype": "float32", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "architectures": [ "ModernBertForMaskedLM" ], "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "_name_or_path": "answerdotai/ModernBERT-large", "transformers_version": "5.2.0", "gradient_checkpointing": false, "layer_norm_eps": 1e-05, "position_embedding_type": "absolute", "model_type": "modernbert", "output_attentions": false }, "attn_implementation": "sdpa", "head_layers": 2, "head_heads": 16, "head_ff": 2048, "dropout": 0.1, "esc_hidden": 256, "max_len": 2048, "head_max_len": 192, "escalate_threshold": 0.5, "name": "Kodama Core" }