config.json

{
  "audio_llama_proj_model": "",
  "beats_cfg": {
    "activation_dropout": 0.0,
    "activation_fn": "gelu",
    "attention_dropout": 0.0,
    "conv_bias": false,
    "conv_pos": 128,
    "conv_pos_groups": 16,
    "deep_norm": true,
    "dropout": 0.0,
    "dropout_input": 0.0,
    "embed_dim": 512,
    "encoder_attention_heads": 12,
    "encoder_embed_dim": 768,
    "encoder_ffn_embed_dim": 3072,
    "encoder_layerdrop": 0.05,
    "encoder_layers": 12,
    "finetuned_model": true,
    "gru_rel_pos": true,
    "input_patch_size": 16,
    "layer_norm_first": false,
    "layer_wise_gradient_decay_ratio": 0.6,
    "max_distance": 800,
    "num_buckets": 320,
    "predictor_class": 527,
    "predictor_dropout": 0.0,
    "relative_position_embedding": true
  },
  "downsample_factor": 8,
  "end_sym": "<|end_of_text|>",
  "freeze_audio_QFormer": false,
  "freeze_audio_llama_proj": false,
  "freeze_beats": true,
  "llama_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
  "lora": true,
  "lora_alpha": 32,
  "lora_dropout": 0.1,
  "lora_rank": 32,
  "max_pooling": false,
  "max_txt_len": 160,
  "num_audio_query_token": 1,
  "prompt_template": "<|start_header_id|>user<|end_header_id|>\n\n{}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
  "second_per_window": 0.333333,
  "second_stride": 0.333333,
  "use_audio_Qformer": true,
  "window_level_Qformer": true
}