| { | |
| "architectures": [ | |
| "ModernBertForTokenClassification" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 50281, | |
| "classifier_activation": "gelu", | |
| "classifier_bias": false, | |
| "classifier_dropout": 0.2, | |
| "classifier_pooling": "mean", | |
| "cls_token_id": 50281, | |
| "decoder_bias": true, | |
| "deterministic_flash_attn": false, | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 50282, | |
| "global_attn_every_n_layers": 3, | |
| "global_rope_theta": 160000.0, | |
| "gradient_checkpointing": false, | |
| "hidden_activation": "gelu", | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "O", | |
| "1": "B-DNA", | |
| "2": "B-RNA", | |
| "3": "B-cell_line", | |
| "4": "B-cell_type", | |
| "5": "B-protein", | |
| "6": "I-DNA", | |
| "7": "I-RNA", | |
| "8": "I-cell_line", | |
| "9": "I-cell_type", | |
| "10": "I-protein" | |
| }, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2624, | |
| "label2id": { | |
| "B-DNA": 1, | |
| "B-RNA": 2, | |
| "B-cell_line": 3, | |
| "B-cell_type": 4, | |
| "B-protein": 5, | |
| "I-DNA": 6, | |
| "I-RNA": 7, | |
| "I-cell_line": 8, | |
| "I-cell_type": 9, | |
| "I-protein": 10, | |
| "O": 0 | |
| }, | |
| "layer_norm_eps": 1e-07, | |
| "local_attention": 128, | |
| "local_rope_theta": 10000.0, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "mlp_dropout": 0.0, | |
| "model_type": "modernbert", | |
| "norm_bias": false, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "pad_token_id": 50283, | |
| "position_embedding_type": "absolute", | |
| "repad_logits_with_grad": false, | |
| "sep_token_id": 50282, | |
| "sparse_pred_ignore_index": -100, | |
| "sparse_prediction": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.53.2", | |
| "vocab_size": 50368 | |
| } | |