config.json

{
    "architectures": [
        "DeweyV1"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoModel": "modeling_dewey_v1.DeweyV1"
    },
    "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,
    "embedding_dropout": 0.0,
    "eos_token_id": 50282,
    "global_attn_every_n_layers": 3,
    "global_rope_theta": 73780400,
    "gradient_checkpointing": false,
    "hidden_activation": "gelu",
    "hidden_size": 1024,
    "initializer_cutoff_factor": 2.0,
    "initializer_range": 0.02,
    "intermediate_size": 2624,
    "layer_norm_eps": 1e-05,
    "local_attention": 128,
    "local_rope_theta": 10000.0,
    "max_position_embeddings": 131072,
    "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",
    "sep_token_id": 50282,
    "torch_dtype": "float32",
    "transformers_version": "4.49.0",
    "vector_size": 2048,
    "single_vector_type":"cls_add_mean",
    "vocab_size": 50370,
    "tie_word_embeddings":false
}