config.json

{
  "data": {
    "audio_bos_value": 1026,
    "audio_eos_value": 1024,
    "audio_length": 3072,
    "audio_pad_value": 1025,
    "channels": 9,
    "delay_pattern": [
      0,
      8,
      9,
      10,
      11,
      12,
      13,
      14,
      15
    ],
    "text_length": 1024,
    "text_pad_value": 0
  },
  "model": {
    "decoder": {
      "cross_head_dim": 128,
      "cross_query_heads": 16,
      "gqa_head_dim": 128,
      "gqa_query_heads": 16,
      "kv_heads": 4,
      "n_embd": 2048,
      "n_hidden": 8192,
      "n_layer": 18
    },
    "dropout": 0.0,
    "encoder": {
      "head_dim": 128,
      "n_embd": 1024,
      "n_head": 16,
      "n_hidden": 4096,
      "n_layer": 12
    },
    "normalization_layer_epsilon": 1e-05,
    "rope_max_timescale": 10000,
    "rope_min_timescale": 1,
    "src_vocab_size": 256,
    "tgt_vocab_size": 1028,
    "weight_dtype": "float32"
  },
  "training": {},
  "version": "0.1"
}