config.json

{
    "_sliding_window_pattern": 6,
    "architectures": [
        "Gemma3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_logit_softcapping": null,
    "bos_token_id": 2,
    "eos_token_id": 1,
    "final_logit_softcapping": null,
    "head_dim": 256,
    "hidden_activation": "gelu_pytorch_tanh",
    "hidden_size": 640,
    "initializer_range": 0.02,
    "intermediate_size": 2048,
    "layer_types": [
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "full_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "full_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "full_attention"
    ],
    "max_position_embeddings": 32768,
    "model_type": "gemma3_text",
    "num_attention_heads": 4,
    "num_hidden_layers": 18,
    "num_key_value_heads": 1,
    "pad_token_id": 0,
    "query_pre_attn_scalar": 256,
    "rms_norm_eps": 1e-06,
    "rope_local_base_freq": 10000.0,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "sliding_window": 512,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.55.0.dev0",
    "use_bidirectional_attention": false,
    "use_cache": true,
    "vocab_size": 262144
}