| { |
| "architectures": [ |
| "ModernBertModel" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attention_probs_dropout_prob": 0.1, |
| "bos_token_id": 50000, |
| "classifier_activation": "gelu", |
| "classifier_bias": false, |
| "classifier_dropout": 0.0, |
| "classifier_pooling": "cls", |
| "cls_token_id": 50281, |
| "decoder_bias": true, |
| "deterministic_flash_attn": false, |
| "embedding_dropout": 0.0, |
| "eos_token_id": 50001, |
| "global_attn_every_n_layers": 3, |
| "global_rope_theta": 160000.0, |
| "hidden_activation": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "initializer_cutoff_factor": 2.0, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "local_attention": 128, |
| "local_attention_rope_theta": 10000, |
| "local_attention_window": 128, |
| "local_rope_theta": 10000.0, |
| "max_position_embeddings": 2048, |
| "mlp_bias": false, |
| "mlp_dropout": 0.0, |
| "model_type": "modernbert", |
| "norm_bias": false, |
| "norm_eps": 1e-05, |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "pad_token_id": 0, |
| "reference_compile": true, |
| "repad_logits_with_grad": false, |
| "rope_theta": 160000, |
| "sep_token_id": 50282, |
| "sparse_pred_ignore_index": -100, |
| "sparse_prediction": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.50.0", |
| "type_vocab_size": 2, |
| "vocab_size": 50004 |
| } |
|
|
