{
  "architectures": [
    "LlamaKDA"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "model.LlamaKDAConfig",
    "AutoModelForCausalLM": "model.LlamaKDA"
  },
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "intermediate_size": 5120,
  "kda_allow_neg_eigval": false,
  "kda_conv_bias": false,
  "kda_conv_size": 4,
  "kda_every": 4,
  "kda_expand_v": 1.0,
  "kda_full_attn_every": null,
  "kda_full_attn_layers": null,
  "kda_full_attn_range": null,
  "kda_head_dim": 128,
  "kda_layer_types": [
    "kda",
    "full",
    "full",
    "full",
    "kda",
    "full",
    "full",
    "full",
    "kda",
    "full",
    "full",
    "full",
    "kda",
    "full",
    "full",
    "full",
    "kda",
    "full",
    "full",
    "full",
    "kda",
    "full",
    "full",
    "full",
    "kda",
    "full",
    "full",
    "full",
    "kda",
    "full",
    "full",
    "full"
  ],
  "kda_lower_bound": null,
  "kda_num_heads": 12,
  "kda_num_v_heads": null,
  "kda_offset": 0,
  "kda_safe_gate": false,
  "kda_use_short_conv": true,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "model_type": "llama_kda",
  "num_attention_heads": 12,
  "num_hidden_layers": 32,
  "num_key_value_heads": 6,
  "pad_token_id": 2,
  "pretraining_tp": 1,
  "qk_norm": true,
  "qk_norm_eps": 1e-06,
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "rope_theta": 1000000,
    "rope_type": "default"
  },
  "tie_word_embeddings": true,
  "transformers_version": "5.8.0",
  "use_cache": false,
  "vocab_size": 32000
}