| { |
| "transformers_version": "5.12.1", |
| "architectures": [ |
| "ModernBertForTokenClassification" |
| ], |
| "output_hidden_states": false, |
| "return_dict": true, |
| "dtype": "bfloat16", |
| "chunk_size_feed_forward": 0, |
| "is_encoder_decoder": false, |
| "id2label": { |
| "0": "B-protein", |
| "1": "B-protein_complex", |
| "2": "B-protein_enum", |
| "3": "B-protein_familiy_or_group", |
| "4": "B-protein_variant", |
| "5": "I-protein", |
| "6": "I-protein_complex", |
| "7": "I-protein_enum", |
| "8": "I-protein_familiy_or_group", |
| "9": "I-protein_variant", |
| "10": "O" |
| }, |
| "label2id": { |
| "B-protein": 0, |
| "B-protein_complex": 1, |
| "B-protein_enum": 2, |
| "B-protein_familiy_or_group": 3, |
| "B-protein_variant": 4, |
| "I-protein": 5, |
| "I-protein_complex": 6, |
| "I-protein_enum": 7, |
| "I-protein_familiy_or_group": 8, |
| "I-protein_variant": 9, |
| "O": 10 |
| }, |
| "problem_type": null, |
| "vocab_size": 50368, |
| "hidden_size": 1024, |
| "intermediate_size": 2624, |
| "num_hidden_layers": 28, |
| "num_attention_heads": 16, |
| "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", |
| "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": 0.2, |
| "classifier_bias": false, |
| "classifier_activation": "silu", |
| "deterministic_flash_attn": false, |
| "sparse_prediction": false, |
| "sparse_pred_ignore_index": -100, |
| "tie_word_embeddings": true, |
| "_name_or_path": "OpenMed/OpenMed-NER-ProteinDetect-ModernClinical-395M", |
| "global_attn_every_n_layers": 3, |
| "gradient_checkpointing": false, |
| "layer_norm_eps": 1e-07, |
| "model_type": "modernbert", |
| "position_embedding_type": "absolute", |
| "repad_logits_with_grad": false, |
| "output_attentions": false, |
| "max_sequence_length": 512 |
| } |
