config.json

{
  "architectures": [
    "InklingForConditionalGeneration"
  ],
  "model_type": "inkling_mm_model",
  "eos_token_id": 200006,
  "text_config": {
    "model_max_length": 1048576,
    "torch_dtype": "bfloat16",
    "hidden_size": 4096,
    "num_hidden_layers": 4,
    "vocab_size": 201024,
    "num_attention_heads": 32,
    "num_key_value_heads": 8,
    "head_dim": 128,
    "d_rel": 16,
    "rel_extent": 1024,
    "q_bias": false,
    "o_bias": false,
    "log_scaling_n_floor": 128000,
    "log_scaling_alpha": 0.1,
    "rms_norm_eps": 1e-06,
    "use_embed_norm": true,
    "local_layer_ids": [
      0,
      1,
      2,
      3
    ],
    "dense_mlp_idx": 2,
    "use_sconv": true,
    "sconv_kernel_size": 4,
    "unpadded_vocab_size": 200058,
    "logits_mup_width_multiplier": 16.0,
    "final_logit_softcapping": null,
    "swa_head_dim": 128,
    "swa_num_attention_heads": 32,
    "swa_num_key_value_heads": 8,
    "sliding_window_size": 512,
    "n_routed_experts": 256,
    "num_experts_per_tok": 6,
    "n_shared_experts": 2,
    "shared_expert_sink": true,
    "dense_intermediate_size": 16384,
    "intermediate_size": 2048,
    "route_scale": 8.0,
    "use_gate_bias": true,
    "gate_activation": "sigmoid",
    "norm_after_topk": true,
    "use_global_scale": true
  },
  "audio_config": {
    "decoder_dmodel": 4096,
    "n_mel_bins": 80,
    "mel_vocab_size": 16,
    "bias": false,
    "dmel_min_value": -7.0,
    "dmel_max_value": 2.0,
    "use_audio_norm": true,
    "audio_mode": "dmel"
  },
  "vision_config": {
    "vision_encoder_type": "hmlp",
    "decoder_dmodel": 4096,
    "patch_size": 40,
    "temporal_patch_size": 2,
    "n_channels": 3,
    "n_layers": 4,
    "use_vision_norm": true
  },
  "mtp_config": {
    "num_nextn_predict_layers": 8,
    "chain_hidden_post_norm": false,
    "local_layer_ids": [
      0,
      2,
      4,
      5,
      6,
      7
    ]
  }
}