| { |
| "architectures": [ |
| "ModernBertForSequenceClassification" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 50281, |
| "classifier_activation": "gelu", |
| "classifier_bias": false, |
| "classifier_dropout": 0.0, |
| "classifier_pooling": "mean", |
| "cls_token_id": 50281, |
| "decoder_bias": true, |
| "deterministic_flash_attn": false, |
| "dtype": "float32", |
| "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": 768, |
| "id2label": { |
| "0": "biology", |
| "1": "business", |
| "2": "chemistry", |
| "3": "computer science", |
| "4": "drlcloud", |
| "5": "economics", |
| "6": "engineering", |
| "7": "health", |
| "8": "history", |
| "9": "law", |
| "10": "math", |
| "11": "other", |
| "12": "philosophy", |
| "13": "physics", |
| "14": "psychology" |
| }, |
| "initializer_cutoff_factor": 2.0, |
| "initializer_range": 0.02, |
| "intermediate_size": 1152, |
| "label2id": { |
| "biology": 0, |
| "business": 1, |
| "chemistry": 2, |
| "computer science": 3, |
| "drlcloud": 4, |
| "economics": 5, |
| "engineering": 6, |
| "health": 7, |
| "history": 8, |
| "law": 9, |
| "math": 10, |
| "other": 11, |
| "philosophy": 12, |
| "physics": 13, |
| "psychology": 14 |
| }, |
| "layer_norm_eps": 1e-05, |
| "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": 12, |
| "num_hidden_layers": 22, |
| "pad_token_id": 50283, |
| "position_embedding_type": "absolute", |
| "problem_type": "single_label_classification", |
| "repad_logits_with_grad": false, |
| "sep_token_id": 50282, |
| "sparse_pred_ignore_index": -100, |
| "sparse_prediction": false, |
| "transformers_version": "4.57.1", |
| "vocab_size": 50368 |
| } |
|
|
