config.json

{
  "model_type": "rodan-modern",
  "architecture": "ModernLM",
  "framework": "mlx",
  "params": 11460000,
  "vocab_size": 8192,
  "dim": 320,
  "n_layers": 8,
  "n_heads": 8,
  "n_kv_heads": 1,
  "head_dim": 40,
  "ffn_hidden": 768,
  "max_len": 512,
  "rope_base": 200000.0,
  "norm": "rmsnorm",
  "norm_eps": 1e-5,
  "activation": "swiglu",
  "qk_norm": true,
  "tied_embeddings": true,
  "value_residual": true,
  "ple_rank": 16,
  "lrm": true,
  "attention": "mqa",
  "tokenizer": "byte-level BPE (8k), eot id 0",
  "notes": "Custom MLX decoder-only transformer. Load with model_opt.ModernLM(ModernConfig(**fields)) + load_weights('model.safetensors'). See README."
}