| { | |
| "architectures": [ | |
| "ModernBertDecoderForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token": "[CLS]", | |
| "bos_token_id": 50281, | |
| "causal_mask": true, | |
| "classifier_activation": "gelu", | |
| "classifier_bias": false, | |
| "classifier_dropout": 0.0, | |
| "classifier_pooling": "mean", | |
| "cls_token_id": 50281, | |
| "decoder_bias": true, | |
| "deterministic_flash_attn": false, | |
| "embedding_dropout": 0.0, | |
| "eos_token": "[SEP]", | |
| "eos_token_id": 50282, | |
| "global_attn_every_n_layers": 3, | |
| "global_rope_theta": 160000.0, | |
| "gradient_checkpointing": false, | |
| "hidden_activation": "gelu", | |
| "hidden_size": 32, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 32, | |
| "is_causal": true, | |
| "layer_norm_eps": 1e-05, | |
| "layer_types": [ | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "local_rope_theta": 160000.0, | |
| "masked_prediction": false, | |
| "max_position_embeddings": 7999, | |
| "mlp_bias": false, | |
| "mlp_dropout": 0.0, | |
| "model_type": "modernbert-decoder", | |
| "norm_bias": false, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 2, | |
| "pad_token_id": 50283, | |
| "position_embedding_type": "sans_pos", | |
| "reference_compile": false, | |
| "sep_token_id": 50282, | |
| "sliding_window": 64, | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.54.0.dev0", | |
| "unk_token": "[UNK]", | |
| "use_cache": true, | |
| "vocab_size": 50368 | |
| } | |