{
    "architectures": [
        "SparkForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_spark.SparkConfig",
        "AutoModelForCausalLM": "modeling_spark.SparkForCausalLM",
        "AutoTokenizer": [
            "tokenization_spark.SparkTokenizer",
            null
        ]
    },
    "bos_token_id": 1,
    "dropout_rate": 0.0,
    "dtype": "bfloat16",
    "eos_token_id": 5,
    "ffn_hidden_size": 14336,
    "hidden_act": "fast_gelu",
    "hidden_size": 5120,
    "init_std": 0.014,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "layernorm_epsilon": 1e-05,
    "max_position_embeddings": 32768,
    "model_type": "spark",
    "num_attention_heads": 40,
    "num_heads": 40,
    "num_hidden_layers": 40,
    "num_key_value_heads": 40,
    "num_layers": 40,
    "pad_token_id": 0,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "tie_word_embeddings": true,
    "transformers_version": "4.56.1",
    "use_bias": true,
    "use_cache": true,
    "vocab_size": 60000,
    "torch_dtype": "bfloat16"
}