{ "model_type": "shannon2", "architectures": [ "Shannon2MultiHead" ], "auto_map": { "AutoConfig": "configuration_shannon2.Shannon2Config", "AutoModel": "modeling_shannon2.Shannon2MultiHead" }, "encoder_name_or_path": "answerdotai/ModernBERT-base", "encoder_config": { "transformers_version": "5.6.2", "architectures": [ "ModernBertForMaskedLM" ], "output_hidden_states": false, "return_dict": true, "dtype": "float32", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "vocab_size": 50368, "hidden_size": 768, "intermediate_size": 1152, "num_hidden_layers": 22, "num_attention_heads": 12, "hidden_activation": "gelu", "max_position_embeddings": 8192, "initializer_range": 0.02, "initializer_cutoff_factor": 2.0, "norm_eps": 1e-05, "norm_bias": false, "pad_token_id": 50283, "eos_token_id": 50282, "bos_token_id": 50281, "cls_token_id": 50281, "sep_token_id": 50282, "attention_bias": false, "attention_dropout": 0.0, "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" ], "rope_parameters": { "sliding_attention": { "rope_type": "default", "rope_theta": 10000.0 }, "full_attention": { "rope_type": "default", "rope_theta": 160000.0 } }, "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, "tie_word_embeddings": true, "_name_or_path": "answerdotai/ModernBERT-base", "global_attn_every_n_layers": 3, "gradient_checkpointing": false, "layer_norm_eps": 1e-05, "model_type": "modernbert", "position_embedding_type": "absolute", "output_attentions": false }, "max_position_embeddings": 4096, "head_h1": 512, "head_h2": 256, "dropout": 0.1, "torch_dtype": "float32" }