config.json

{
  "architectures": [
    "SparkForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_spark.SparkConfig",
    "AutoModelForCausalLM": "modeling_spark.SparkForCausalLM"
  },
  "bos_token_id": 0,
  "coda_layers": 4,
  "dtype": "float32",
  "eos_token_id": 2,
  "gradient_checkpointing": false,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 256,
  "initializer_range": 0.02,
  "intermediate_size": 768,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "spark",
  "num_attention_heads": 4,
  "num_hidden_layers": 8,
  "num_key_value_heads": 1,
  "pad_token_id": 1,
  "prelude_layers": 1,
  "pretraining_tp": 1,
  "recurrent_layers": 3,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "rope_theta": 10000.0,
  "tie_word_embeddings": true,
  "transformers_version": "5.15.1",
  "use_cache": false,
  "use_flash_attn": false,
  "vocab_size": 4096,
  "xsa_projection": true
}