{
  "angle_init_scale": 0.1,
  "architectures": [
    "GRTForSequenceClassification"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "coupling_init_mode": "diagonal",
  "coupling_init_scale": 0.01,
  "dtype": "float32",
  "eos_token_id": 151643,
  "ffn_n_rotations": 21,
  "hidden_size": 256,
  "id2label": {
    "0": "LABEL_0"
  },
  "initializer_range": 0.02,
  "intermediate_size": 1024,
  "label2id": {
    "LABEL_0": 0
  },
  "learnable_residual_gates": true,
  "learnable_rope": true,
  "log_magnitude_init": 0.0,
  "max_position_embeddings": 2048,
  "model_type": "grt",
  "n_mixer_rotations": 1,
  "n_qkv_rotations": 11,
  "num_attention_heads": 4,
  "num_hidden_layers": 12,
  "output_scale_init": 30.0,
  "pad_token_id": 151643,
  "peri_ln": false,
  "phase_init_scale": 0.1,
  "pos_freq_base": 10000.0,
  "problem_type": "regression",
  "residual_gate_mode": "bounded_depth",
  "residual_norm_mode": "none",
  "tie_word_embeddings": false,
  "transformers_version": "5.21.0.dev0",
  "use_cache": false,
  "vocab_size": 151669
}