{
  "activation_dropout": 0.1,
  "activation_fn": "gelu",
  "apply_mask": false,
  "arch": "avsp_llm",
  "architectures": [
    "AVSPLLMModel"
  ],
  "attention_dropout": 0.1,
  "audio_dropout": 0.0,
  "audio_feat_dim": 104,
  "auto_map": {
    "AutoConfig": "configuration.AVSPLLMConfig",
    "AutoModel": "modelling.AVSPLLMModel"
  },
  "conv_bias": false,
  "conv_feature_layers": "[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2",
  "conv_pos": 128,
  "conv_pos_groups": 16,
  "data": null,
  "decoder_activation_dropout": 0.0,
  "decoder_attention_dropout": 0.1,
  "decoder_attention_heads": 4,
  "decoder_dropout": 0.1,
  "decoder_embed_dim": 2560,
  "decoder_ffn_embed_dim": 3072,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 6,
  "decoder_learned_pos": false,
  "decoder_normalize_before": false,
  "dropout": 0.1,
  "dropout_features": 0.0,
  "dropout_input": 0.0,
  "encoder_attention_heads": 16,
  "encoder_embed_dim": 1024,
  "encoder_ffn_embed_dim": 4096,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 24,
  "extractor_mode": "default",
  "feature_ds_rate": 1,
  "feature_grad_mult": 1.0,
  "final_dim": 256,
  "final_dropout": 0.1,
  "freeze_finetune_updates": 0,
  "ignored_weights": [],
  "input_modality": "video",
  "label_rate": 25,
  "latent_temp": [
    2.0,
    0.5,
    0.999995
  ],
  "layer_norm_first": false,
  "layerdrop": 0.0,
  "llm_ckpt_path": "vilm/vinallama-2.7b",
  "logit_temp": 0.1,
  "mask_channel_length": 64,
  "mask_channel_min_space": 1,
  "mask_channel_other": 0.0,
  "mask_channel_prob": 0.5,
  "mask_channel_selection": "static",
  "mask_length": 10,
  "mask_length_audio": 10,
  "mask_length_image": 10,
  "mask_min_space": 1,
  "mask_other": 0.0,
  "mask_prob": 0.5,
  "mask_prob_audio": 0.65,
  "mask_prob_image": 0.65,
  "mask_selection": "static",
  "masking_type": "input",
  "masking_updates": 0,
  "max_target_positions": 2048,
  "modality_dropout": 0.0,
  "modality_fuse": "concat",
  "model_type": "avsp_llm",
  "no_mask_channel_overlap": false,
  "no_mask_overlap": false,
  "no_pretrained_weights": false,
  "no_scale_embedding": true,
  "no_token_positional_embeddings": false,
  "normalize": false,
  "num_classes": 2004,
  "num_frames": 16,
  "num_frozen_layers": 0,
  "pretrained": "tanthinhdt/ViAVSP-LLM_v1.0",
  "resnet_relu_type": "prelu",
  "resnet_weights": null,
  "sample_rate": 25,
  "selection_type": "same_other_seq",
  "share_decoder_input_output_embed": false,
  "sim_type": "cosine",
  "skip_masked": false,
  "skip_nomask": false,
  "sub_encoder_layers": 0,
  "target_glu": false,
  "torch_dtype": "float32",
  "transformers_version": "4.41.2",
  "untie_final_proj": false,
  "w2v_args": null
}