{
  "architectures": [
    "Phi4FlashForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "microsoft/Phi-4-mini-flash-reasoning--configuration_phi4flash.Phi4FlashConfig",
    "AutoModelForCausalLM": "microsoft/Phi-4-mini-flash-reasoning--modeling_phi4flash.Phi4FlashForCausalLM",
    "AutoTokenizer": "Xenova/gpt-4o"
  },
  "bos_token_id": 199999,
  "embd_pdrop": 0.0,
  "eos_token_id": 199999,
  "hidden_act": "silu",
  "hidden_size": 64,
  "initializer_range": 0.02,
  "intermediate_size": 64,
  "layer_norm_eps": 1e-05,
  "lm_head_bias": false,
  "mamba_conv_bias": true,
  "mamba_d_conv": 4,
  "mamba_d_state": 16,
  "mamba_dt_rank": 4,
  "mamba_expand": 2,
  "mamba_proj_bias": false,
  "max_position_embeddings": 262144,
  "mb_per_layer": 2,
  "mlp_bias": false,
  "model_type": "phi4flash",
  "num_attention_heads": 2,
  "num_hidden_layers": 4,
  "num_key_value_heads": 2,
  "pad_token_id": 199999,
  "resid_pdrop": 0.0,
  "rope_theta": 10000.0,
  "sliding_window": 512,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.54.0.dev0",
  "use_cache": true,
  "vocab_size": 200064
}