{
  "architectures": [
    "TaoNetForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_taonet.TaoNetConfig",
    "AutoModelForCausalLM": "modeling_taonet.TaoNetForCausalLM"
  },
  "bos_token_id": 1,
  "cnn_channels": [
    32,
    64,
    128
  ],
  "cnn_kernel_size": 3,
  "d_embed_rank": 96,
  "d_latent_kv": 768,
  "d_rope": 128,
  "dropout": 0.02,
  "dtype": "float32",
  "eos_token_id": 2,
  "gamma_activation": "gelu",
  "gamma_discretization": "bilinear",
  "gamma_dt_init": 0.01,
  "gamma_dt_max": 0.1,
  "gamma_dt_min": 0.001,
  "gamma_gate": true,
  "gamma_gate_bias": 2.0,
  "gamma_hidden_dim": 1536,
  "gamma_input_gate": true,
  "gamma_input_gate_bias": 2.0,
  "gamma_kernel_mode": "auto",
  "gamma_kernel_threshold": 64,
  "gamma_layer_scale_init": 0.1,
  "gamma_prenorm": true,
  "gamma_residual_scale": 1.0,
  "gamma_use_D": true,
  "gamma_use_output_linear": true,
  "gqa_groups": 1,
  "head_dim": 128,
  "hidden_dim": 1024,
  "hidden_dim_ff": 3072,
  "image_size": 224,
  "image_token": "<image>",
  "init_std": 0.02,
  "intermediate_dim": 4096,
  "max_seq_length": 1024,
  "model_type": "taonet",
  "num_heads": 8,
  "num_layers": 16,
  "pad_token_id": 3,
  "rope_scale": 40.0,
  "transformers_version": "5.1.0",
  "unk_token_id": 0,
  "use_factorized_embedding": true,
  "vision_encoder_type": "cnn",
  "vision_output_dim": 256,
  "vision_prefix_tokens": 10,
  "vocab_size": 8192,
  "yarn_alpha": 1.0,
  "yarn_enabled": false,
  "yarn_original_max_seq_length": null
}