{ "metadata": { "total_size": 22443162928 }, "weight_map": { "audio_head.headnorm.weight": "model-00005-of-00005.safetensors", "audio_head.heads.0.bias": "model-00005-of-00005.safetensors", "audio_head.heads.0.weight": "model-00005-of-00005.safetensors", "audio_head.heads.1.bias": "model-00005-of-00005.safetensors", "audio_head.heads.1.weight": "model-00005-of-00005.safetensors", "audio_head.heads.2.bias": "model-00005-of-00005.safetensors", "audio_head.heads.2.weight": "model-00005-of-00005.safetensors", "audio_head.heads.3.bias": "model-00005-of-00005.safetensors", "audio_head.heads.3.weight": "model-00005-of-00005.safetensors", "audio_head.heads.4.bias": "model-00005-of-00005.safetensors", "audio_head.heads.4.weight": "model-00005-of-00005.safetensors", "audio_head.heads.5.bias": "model-00005-of-00005.safetensors", "audio_head.heads.5.weight": "model-00005-of-00005.safetensors", "audio_head.heads.6.bias": "model-00005-of-00005.safetensors", "audio_head.heads.6.weight": "model-00005-of-00005.safetensors", "audio_head.heads.7.bias": "model-00005-of-00005.safetensors", "audio_head.heads.7.weight": "model-00005-of-00005.safetensors", "audio_head.transformer_layers.0.layernorm1.weight": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.0.layernorm2.weight": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.0.linear1.bias": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.0.linear1.weight": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.0.linear2.bias": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.0.linear2.weight": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.0.self_attention.in_proj_bias": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.0.self_attention.in_proj_weight": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.0.self_attention.out_proj.bias": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.0.self_attention.out_proj.weight": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.1.layernorm1.weight": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.1.layernorm2.weight": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.1.linear1.bias": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.1.linear1.weight": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.1.linear2.bias": "model-00005-of-00005.safetensors", "audio_head.transformer_layers.1.linear2.weight": "model-00005-of-00005.safetensors", "audio_head.transformer_layers.1.self_attention.in_proj_bias": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.1.self_attention.in_proj_weight": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.1.self_attention.out_proj.bias": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.1.self_attention.out_proj.weight": "model-00004-of-00005.safetensors", "audio_head.transformer_layers.2.layernorm1.weight": "model-00005-of-00005.safetensors", "audio_head.transformer_layers.2.layernorm2.weight": "model-00005-of-00005.safetensors", "audio_head.transformer_layers.2.linear1.bias": "model-00005-of-00005.safetensors", "audio_head.transformer_layers.2.linear1.weight": "model-00005-of-00005.safetensors", "audio_head.transformer_layers.2.linear2.bias": "model-00005-of-00005.safetensors", "audio_head.transformer_layers.2.linear2.weight": "model-00005-of-00005.safetensors", "audio_head.transformer_layers.2.self_attention.in_proj_bias": "model-00005-of-00005.safetensors", "audio_head.transformer_layers.2.self_attention.in_proj_weight": "model-00005-of-00005.safetensors", "audio_head.transformer_layers.2.self_attention.out_proj.bias": "model-00005-of-00005.safetensors", "audio_head.transformer_layers.2.self_attention.out_proj.weight": "model-00005-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.down_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.gate_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.proj_decoder.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.proj_decoder.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.up_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.0.codebook.cluster_size": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.0.codebook.embed": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.0.codebook.embed_avg": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.1.codebook.cluster_size": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.1.codebook.embed": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.1.codebook.embed_avg": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.2.codebook.cluster_size": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.2.codebook.embed": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.2.codebook.embed_avg": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.3.codebook.cluster_size": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.3.codebook.embed": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.3.codebook.embed_avg": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.4.codebook.cluster_size": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.4.codebook.embed": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.4.codebook.embed_avg": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.5.codebook.cluster_size": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.5.codebook.embed": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.5.codebook.embed_avg": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.6.codebook.cluster_size": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.6.codebook.embed": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.6.codebook.embed_avg": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.7.codebook.cluster_size": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.7.codebook.embed": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_bridge_model.vq_list.7.codebook.embed_avg": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.dconv1.conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.dconv1.conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.dconv1.norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.dconv1.norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.dconv2.conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.dconv2.conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.dconv2.norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.dconv2.norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.0.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.1.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.2.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.3.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.4.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.5.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.6.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.layers.7.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.positional_embedding": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.10.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.10.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.12.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.12.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.4.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.4.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.6.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.6.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.7.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.7.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.9.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_decoder.post_net.layers.9.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.down_blocks.0.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.final_block.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.final_block.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.final_block.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.final_block.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.final_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.final_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.0.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.1.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.10.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.11.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.2.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.3.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.4.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.5.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.6.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.7.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.8.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.mid_blocks.9.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.time_mlp.linear_1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.time_mlp.linear_1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.time_mlp.linear_2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.time_mlp.linear_2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.0.block1.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.0.block1.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.0.block1.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.0.block1.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.0.block2.block.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.0.block2.block.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.0.block2.block.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.0.block2.block.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.0.mlp.1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.0.mlp.1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.0.res_conv.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.0.res_conv.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.0.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.1.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.2.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.attn1.to_k.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.attn1.to_out.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.attn1.to_out.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.attn1.to_q.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.attn1.to_v.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.ff.net.0.proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.ff.net.0.proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.ff.net.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.ff.net.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.norm1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.norm1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.norm3.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.1.3.norm3.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.conditional_decoder.up_blocks.0.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.final_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.in_mlp.0.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.in_mlp.0.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.in_mlp.2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.in_mlp.2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.positional_embedding": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.0.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.1.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.10.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.11.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.2.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.3.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.4.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.5.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.6.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.7.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.8.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_flow_matching_decoder.prenet.transformer_layers.9.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.conv1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.conv1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.conv2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.conv2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.0.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.1.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.10.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.11.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.12.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.13.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.14.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.15.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.16.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.17.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.18.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.19.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.2.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.20.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.21.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.22.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.23.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.24.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.25.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.26.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.27.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.28.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.29.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.3.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.30.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.31.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.4.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.5.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.6.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.7.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.8.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.fc1.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.fc1.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.fc2.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.fc2.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.final_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.final_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.self_attn.out_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.self_attn.out_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.layers.9.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", "audio_tokenizer.audio_model.positional_embedding": "model-00004-of-00005.safetensors", "lm_head.weight": "model-00005-of-00005.safetensors", "model.audio_embed_layers.0.weight": "model-00004-of-00005.safetensors", "model.audio_embed_layers.1.weight": "model-00004-of-00005.safetensors", "model.audio_embed_layers.2.weight": "model-00004-of-00005.safetensors", "model.audio_embed_layers.3.weight": "model-00004-of-00005.safetensors", "model.audio_embed_layers.4.weight": "model-00004-of-00005.safetensors", "model.audio_embed_layers.5.weight": "model-00004-of-00005.safetensors", "model.audio_embed_layers.6.weight": "model-00004-of-00005.safetensors", "model.audio_embed_layers.7.weight": "model-00004-of-00005.safetensors", "model.embed_tokens.weight": "model-00001-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.W_pack.bias": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.W_pack.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.W_pack.bias": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.W_pack.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.W_pack.bias": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.W_pack.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.W_pack.bias": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.W_pack.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.W_pack.bias": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.W_pack.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.W_pack.bias": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.W_pack.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.W_pack.bias": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.W_pack.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.W_pack.bias": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.W_pack.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.W_pack.bias": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.W_pack.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.W_pack.bias": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.W_pack.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.W_pack.bias": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.W_pack.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.W_pack.bias": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.W_pack.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.W_pack.bias": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.W_pack.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.W_pack.bias": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.W_pack.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.W_pack.bias": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.W_pack.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.W_pack.bias": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.W_pack.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.W_pack.bias": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.W_pack.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.W_pack.bias": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.W_pack.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.W_pack.bias": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.W_pack.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.W_pack.bias": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.W_pack.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.27.self_attn.W_pack.bias": "model-00004-of-00005.safetensors", "model.layers.27.self_attn.W_pack.weight": "model-00004-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.W_pack.bias": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.W_pack.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.W_pack.bias": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.W_pack.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.5.self_attn.W_pack.bias": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.W_pack.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.6.self_attn.W_pack.bias": "model-00002-of-00005.safetensors", "model.layers.6.self_attn.W_pack.weight": "model-00002-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.W_pack.bias": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.W_pack.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.W_pack.bias": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.W_pack.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.W_pack.bias": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.W_pack.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.norm.weight": "model-00004-of-00005.safetensors", "model.visual_bridge_model.ln_q.bias": "model-00001-of-00005.safetensors", "model.visual_bridge_model.ln_q.weight": "model-00001-of-00005.safetensors", "model.visual_bridge_model.mlp.0.bias": "model-00001-of-00005.safetensors", "model.visual_bridge_model.mlp.0.weight": "model-00001-of-00005.safetensors", "model.visual_bridge_model.mlp.2.bias": "model-00001-of-00005.safetensors", "model.visual_bridge_model.mlp.2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.0.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.0.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.0.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.0.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.0.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.0.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.0.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.0.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.0.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.0.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.0.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.0.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.1.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.1.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.1.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.1.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.1.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.1.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.1.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.1.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.1.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.1.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.1.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.1.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.10.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.10.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.10.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.10.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.10.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.10.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.10.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.10.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.10.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.10.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.10.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.10.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.11.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.11.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.11.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.11.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.11.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.11.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.11.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.11.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.11.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.11.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.11.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.11.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.12.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.12.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.12.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.12.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.12.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.12.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.12.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.12.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.12.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.12.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.12.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.12.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.13.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.13.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.13.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.13.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.13.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.13.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.13.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.13.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.13.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.13.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.13.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.13.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.14.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.14.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.14.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.14.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.14.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.14.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.14.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.14.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.14.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.14.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.14.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.14.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.15.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.15.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.15.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.15.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.15.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.15.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.15.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.15.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.15.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.15.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.15.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.15.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.16.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.16.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.16.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.16.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.16.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.16.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.16.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.16.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.16.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.16.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.16.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.16.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.17.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.17.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.17.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.17.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.17.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.17.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.17.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.17.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.17.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.17.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.17.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.17.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.18.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.18.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.18.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.18.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.18.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.18.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.18.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.18.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.18.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.18.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.18.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.18.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.19.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.19.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.19.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.19.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.19.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.19.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.19.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.19.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.19.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.19.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.19.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.19.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.2.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.2.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.2.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.2.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.2.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.2.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.2.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.2.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.2.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.2.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.2.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.2.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.20.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.20.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.20.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.20.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.20.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.20.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.20.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.20.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.20.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.20.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.20.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.20.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.21.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.21.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.21.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.21.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.21.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.21.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.21.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.21.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.21.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.21.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.21.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.21.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.22.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.22.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.22.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.22.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.22.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.22.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.22.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.22.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.22.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.22.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.22.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.22.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.23.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.23.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.23.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.23.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.23.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.23.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.23.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.23.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.23.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.23.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.23.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.23.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.24.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.24.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.24.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.24.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.24.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.24.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.24.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.24.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.24.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.24.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.24.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.24.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.25.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.25.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.25.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.25.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.25.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.25.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.25.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.25.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.25.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.25.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.25.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.25.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.26.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.26.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.26.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.26.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.26.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.26.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.26.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.26.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.26.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.26.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.26.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.26.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.27.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.27.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.27.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.27.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.27.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.27.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.27.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.27.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.27.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.27.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.27.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.27.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.28.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.28.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.28.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.28.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.28.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.28.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.28.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.28.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.28.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.28.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.28.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.28.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.29.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.29.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.29.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.29.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.29.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.29.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.29.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.29.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.29.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.29.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.29.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.29.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.3.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.3.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.3.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.3.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.3.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.3.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.3.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.3.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.3.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.3.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.3.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.3.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.30.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.30.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.30.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.30.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.30.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.30.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.30.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.30.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.30.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.30.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.30.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.30.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.31.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.31.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.31.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.31.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.31.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.31.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.31.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.31.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.31.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.31.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.31.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.31.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.4.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.4.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.4.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.4.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.4.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.4.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.4.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.4.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.4.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.4.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.4.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.4.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.5.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.5.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.5.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.5.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.5.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.5.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.5.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.5.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.5.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.5.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.5.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.5.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.6.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.6.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.6.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.6.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.6.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.6.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.6.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.6.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.6.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.6.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.6.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.6.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.7.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.7.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.7.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.7.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.7.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.7.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.7.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.7.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.7.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.7.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.7.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.7.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.8.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.8.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.8.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.8.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.8.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.8.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.8.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.8.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.8.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.8.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.8.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.8.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.9.attn.proj.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.9.attn.proj.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.9.attn.qkv.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.9.attn.qkv.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.9.mlp.fc1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.9.mlp.fc1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.9.mlp.fc2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.9.mlp.fc2.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.9.norm1.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.9.norm1.weight": "model-00001-of-00005.safetensors", "model.visual_model.blocks.9.norm2.bias": "model-00001-of-00005.safetensors", "model.visual_model.blocks.9.norm2.weight": "model-00001-of-00005.safetensors", "model.visual_model.patch_embed.proj.weight": "model-00001-of-00005.safetensors" } }