| { |
| "architectures": [ |
| "ModernBertForMaskedLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 2, |
| "classifier_activation": "gelu", |
| "classifier_bias": false, |
| "classifier_dropout": 0.0, |
| "classifier_pooling": "cls", |
| "cls_token_id": 2, |
| "decoder_bias": true, |
| "deterministic_flash_attn": false, |
| "dtype": "float32", |
| "embedding_dropout": 0.0, |
| "eos_token_id": 3, |
| "global_attn_every_n_layers": 3, |
| "global_rope_theta": 160000.0, |
| "hidden_activation": "gelu", |
| "hidden_size": 640, |
| "initializer_cutoff_factor": 2.0, |
| "initializer_range": 0.02, |
| "intermediate_size": 960, |
| "local_attention": 128, |
| "local_rope_theta": 10000.0, |
| "mask_token_id": 4, |
| "max_position_embeddings": 8192, |
| "mlp_bias": false, |
| "mlp_dropout": 0.0, |
| "model_type": "modernbert", |
| "norm_bias": false, |
| "norm_eps": 1e-05, |
| "num_attention_heads": 10, |
| "num_hidden_layers": 18, |
| "pad_token_id": 0, |
| "repad_logits_with_grad": false, |
| "sep_token_id": 3, |
| "sparse_pred_ignore_index": -100, |
| "sparse_prediction": true, |
| "tokenizer_identity_sha256": "7dbaf80b50202ab56ec3e8d1b169bba4fda88751b9076c30692b6c0a78e2cef0", |
| "tokenizer_manifest_identity_sha256": "f5be87232500f26ccd626fa352c53217651f8031a840f23d824dfb1a838c6b30", |
| "transformers_version": "4.57.6", |
| "unk_token_id": 1, |
| "vocab_size": 50048 |
| } |
|
|
