{
  "angle_init_scale": 0.1,
  "architectures": [
    "GRTForCausalLM"
  ],
  "bos_token_id": 2,
  "coupling_init_scale": 0.01,
  "d_ff": null,
  "d_model": 256,
  "dropout": 0.0,
  "eos_token_id": 3,
  "ffn_mult": 4,
  "ffn_n_rotations": 21,
  "learnable_rope": true,
  "log_magnitude_init": 0.0,
  "max_seq_len": 1024,
  "model_type": "grt",
  "n_blocks": 12,
  "n_heads": 4,
  "n_mixer_rotations": 1,
  "n_qkv_rotations": 11,
  "num_hidden_layers": 12,
  "output_scale_init": 30.0,
  "pad_token_id": 0,
  "phase_init_scale": 0.1,
  "pos_freq_base": 10000.0,
  "residual_gate_mode": "bounded_depth",
  "transformers_version": "4.47.1",
  "vocab_size": 50000
}