{
  "dim": 1024,
  "ffn_dim_multiplier": 1,
  "hidden_dim": 4608,
  "n_heads": 16,
  "n_kv_heads": 8,
  "n_layers": 16,
  "norm_eps": 1e-5,
  "rope_theta": 1000000.0,
  "use_scaled_rope": false,
  "vocab_size": 65536,
  "use_hf_rope": true,
  "use_qk_norm": true,
  "qk_norm_before_rope": true,
  "layer_types": [
    "conv",
    "conv",
    "full_attention",
    "conv",
    "conv",
    "full_attention",
    "conv",
    "conv",
    "full_attention",
    "conv",
    "full_attention",
    "conv",
    "full_attention",
    "conv",
    "full_attention",
    "conv"
  ]
}