config.json

{
  "architectures": [
    "MERaLiONForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "configuration_meralion.MERaLiONConfig",
    "AutoModelForSpeechSeq2Seq": "modeling_meralion.MERaLiONForConditionalGeneration"
  },
  "head_dim": 256,
  "hidden_size": 3584,
  "intermediate_size": 14336,
  "model_type": "meralion",
  "num_attention_heads": 16,
  "num_hidden_layers": 42,
  "num_key_value_heads": 8,
  "sliding_window": 4096,
  "speech_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "openai/whisper-large-v2",
    "apply_spec_augment": true,
    "architectures": [
      "WhisperForConditionalGeneration"
    ],
    "begin_suppress_tokens": [
      220,
      50257
    ],
    "bos_token_id": 50257,
    "d_model": 1280,
    "decoder_attention_heads": 20,
    "decoder_ffn_dim": 5120,
    "decoder_layers": 32,
    "decoder_start_token_id": 50258,
    "encoder_attention_heads": 20,
    "encoder_ffn_dim": 5120,
    "encoder_layers": 32,
    "eos_token_id": 50257,
    "forced_decoder_ids": [
      [
        1,
        50259
      ],
      [
        2,
        50359
      ],
      [
        3,
        50363
      ]
    ],
    "mask_time_length": 20,
    "max_length": 448,
    "model_type": "whisper",
    "num_hidden_layers": 32,
    "num_mel_bins": 80,
    "pad_token_id": 50257,
    "suppress_tokens": [
      1,
      2,
      7,
      8,
      9,
      10,
      14,
      25,
      26,
      27,
      28,
      29,
      31,
      58,
      59,
      60,
      61,
      62,
      63,
      90,
      91,
      92,
      93,
      359,
      503,
      522,
      542,
      873,
      893,
      902,
      918,
      922,
      931,
      1350,
      1853,
      1982,
      2460,
      2627,
      3246,
      3253,
      3268,
      3536,
      3846,
      3961,
      4183,
      4667,
      6585,
      6647,
      7273,
      9061,
      9383,
      10428,
      10929,
      11938,
      12033,
      12331,
      12562,
      13793,
      14157,
      14635,
      15265,
      15618,
      16553,
      16604,
      18362,
      18956,
      20075,
      21675,
      22520,
      26130,
      26161,
      26435,
      28279,
      29464,
      31650,
      32302,
      32470,
      36865,
      42863,
      47425,
      49870,
      50254,
      50258,
      50358,
      50359,
      50360,
      50361,
      50362
    ],
    "torch_dtype": "bfloat16"
  },
  "speech_mlp_scale_factor": 15,
  "speech_token_index": 255999,
  "text_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "aisingapore/gemma2-9b-cpt-sea-lionv3-instruct",
    "architectures": [
      "Gemma2ForCausalLM"
    ],
    "eos_token_id": 107,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 3584,
    "intermediate_size": 14336,
    "model_type": "gemma2",
    "num_hidden_layers": 42,
    "num_attention_heads": 16,
    "num_key_value_heads": 8,
    "query_pre_attn_scalar": 256,
    "sliding_window_size": 4096,
    "torch_dtype": "bfloat16"
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.3"
}