model_config.json

{
  "vocab_size": 8192,
  "d_model": 384,
  "n_heads": 6,
  "n_kv_heads": 2,
  "head_dim": 64,
  "d_ff": 1024,
  "max_seq_len": 512,
  "rope_theta": 10000.0,
  "rms_eps": 1e-06,
  "tie_embeddings": true,
  "n_prelude": 1,
  "n_recurrent": 2,
  "n_coda": 1,
  "n_loops": 16,
  "max_loops": 256,
  "state_init": "prelude",
  "state_init_std": 0.4,
  "input_injection": "add",
  "state_norm": "none",
  "update_rule": "residual",
  "update_gate_init": 3.0,
  "depth_cond": "none",
  "depth_cond_input": "progress",
  "depth_cond_dim": 64,
  "loop_noise": 0.0,
  "noise_schedule": "linear",
  "halting": "none",
  "halt_prior": 0.1,
  "halt_kl_weight": 0.01,
  "init_std": 0.02,
  "depth_scaled_init": true
}