{
  "architectures": [
    "GRTImageForConditionalGeneration"
  ],
  "dtype": "float32",
  "image_token_id": 151655,
  "model_type": "grt_image",
  "text_config": {
    "_name_or_path": "MatterWaveAI/grt-30m",
    "angle_init_scale": 0.1,
    "architectures": [
      "GRTForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "chunk_size_feed_forward": 0,
    "coupling_init_mode": "diagonal",
    "coupling_init_scale": 0.01,
    "dtype": "float32",
    "eos_token_id": 151643,
    "ffn_n_experts": 0,
    "ffn_n_rotations": 21,
    "hidden_size": 256,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 1024,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "learnable_residual_gates": true,
    "learnable_rope": true,
    "log_magnitude_init": 0.0,
    "max_position_embeddings": 2048,
    "model_type": "grt",
    "mor_delta_scale": 0.5,
    "mor_mode": "direct",
    "mor_router_mode": "rotational",
    "mor_split_routers": false,
    "mor_top_k": null,
    "n_mixer_rotations": 1,
    "n_qkv_rotations": 11,
    "num_attention_heads": 4,
    "num_hidden_layers": 12,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scale_init": 30.0,
    "pad_token_id": 151643,
    "peri_ln": false,
    "phase_init_scale": 0.1,
    "pos_freq_base": 10000.0,
    "problem_type": null,
    "residual_gate_mode": "bounded_depth",
    "residual_norm_mode": "none",
    "return_dict": true,
    "rope_placement": "stream",
    "tie_word_embeddings": true,
    "use_cache": true,
    "vocab_size": 151669
  },
  "tie_word_embeddings": true,
  "transformers_version": "5.21.0.dev0",
  "vision_config": {
    "_name_or_path": "",
    "angle_init_scale": 0.1,
    "architectures": null,
    "attention_dropout": 0.0,
    "chunk_size_feed_forward": 0,
    "coupling_init_mode": "diagonal",
    "coupling_init_scale": 0.01,
    "decoder_n_rotations": 15,
    "dtype": null,
    "ffn_n_rotations": 21,
    "hidden_size": 256,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": 224,
    "initializer_range": 0.02,
    "intermediate_size": 1024,
    "is_causal": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "learnable_residual_gates": true,
    "learnable_rope": true,
    "merger_n_rotations": 21,
    "model_type": "grt_vision",
    "n_mixer_rotations": 1,
    "n_qkv_rotations": 11,
    "num_attention_heads": 4,
    "num_channels": 3,
    "num_hidden_layers": 6,
    "output_attentions": false,
    "output_hidden_states": false,
    "patch_n_rotations": 11,
    "patch_size": 14,
    "patches_per_token": 4,
    "peri_ln": false,
    "pos_freq_base": 10000.0,
    "problem_type": null,
    "residual_gate_mode": "bounded_depth",
    "residual_norm_mode": "none",
    "return_dict": true,
    "spatial_merge_size": 2
  },
  "vision_end_token_id": 151653,
  "vision_start_token_id": 151652
}