config.json

{
  "_sliding_window_pattern": 6,
  "architectures": [
    "FlashHeadGemma3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_logit_softcapping": null,
  "auto_map": {
    "AutoConfig": "configuration_flash_head_gemma3_text.FlashHeadGemma3TextConfig",
    "AutoModelForCausalLM": "modeling_flash_head_gemma3_text.FlashHeadGemma3ForCausalLM"
  },
  "bos_token_id": 2,
  "cache_implementation": "hybrid",
  "creation_time": 1753799722.0919366,
  "enforce_equal_cluster_sizes": true,
  "eos_token_id": [
    1,
    106
  ],
  "final_logit_softcapping": null,
  "flash_head_cache_dir": "flash_head_assets",
  "flash_head_special_token_ids": [
    1,
    106
  ],
  "head_dim": 256,
  "hidden_activation": "gelu_pytorch_tanh",
  "hidden_size": 1152,
  "initializer_range": 0.02,
  "intermediate_size": 6912,
  "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",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention"
  ],
  "max_position_embeddings": 32768,
  "model_type": "flash_head_gemma3_text",
  "n_clusters": 16384,
  "num_attention_heads": 4,
  "num_hidden_layers": 26,
  "num_key_value_heads": 1,
  "pad_token_id": 0,
  "query_pre_attn_scalar": 256,
  "rms_norm_eps": 1e-06,
  "rope_local_base_freq": 10000,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": 512,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 262144
}