config.json

{
  "architectures": [
    "MossSpeechForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "audio_pad_token_id": 512,
  "audio_vocab_size": 16512,
  "auto_map": {
    "AutoConfig": "configuration_moss_speech.MossSpeechConfig",
    "AutoModel": "modeling_moss_speech.MossSpeechForCausalLM",
    "AutoProcessor": "processing_moss_speech.MossSpeechProcessor"
  },
  "channels": 2,
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "eosp_token_id": 16384,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 40960,
  "max_window_layers": null,
  "modality_pad_token_id": 151667,
  "model_type": "moss_speech",
  "num_attention_heads": 32,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "num_modality_layers": 4,
  "num_shared_layers": 32,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": null,
  "sosp_token_id": 151646,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.0.dev0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151680,
  "vocab_size_list": [
    151680,
    16512
  ]
}