parameter_breakdown.json

{
  "text_encoder": 22861056,
  "image_encoder": 8434512,
  "audio_encoder_native_mn20_merged": 19886566,
  "image_projection": 12306560,
  "audio_projection": 12306560,
  "text_projection": 11323520,
  "total_exact_loaded_params": 87118774
}