{ "metadata": { "total_parameters": 2031710851, "total_size": 4115059978 }, "weight_map": { "align.gate": "model-00001-of-00003.safetensors", "align.norm.bias": "model-00001-of-00003.safetensors", "align.norm.weight": "model-00001-of-00003.safetensors", "align.out_scale": "model-00001-of-00003.safetensors", "align.proj.bias": "model-00001-of-00003.safetensors", "align.proj.weight": "model-00001-of-00003.safetensors", "align.proj2.bias": "model-00001-of-00003.safetensors", "align.proj2.weight": "model-00001-of-00003.safetensors", "audio_special.weight": "model-00001-of-00003.safetensors", "audio_tower.conv2d1.bias": "model-00001-of-00003.safetensors", "audio_tower.conv2d1.weight": "model-00001-of-00003.safetensors", "audio_tower.conv2d2.bias": "model-00001-of-00003.safetensors", "audio_tower.conv2d2.weight": "model-00001-of-00003.safetensors", "audio_tower.conv2d3.bias": "model-00001-of-00003.safetensors", "audio_tower.conv2d3.weight": "model-00001-of-00003.safetensors", "audio_tower.conv_out.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.0.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.0.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.0.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.0.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.1.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.1.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.1.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.1.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.10.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.10.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.10.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.10.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.11.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.11.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.11.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.11.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.11.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.11.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.12.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.12.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.12.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.12.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.12.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.12.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.12.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.12.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.13.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.13.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.13.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.13.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.13.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.13.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.13.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.13.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.14.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.14.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.14.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.14.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.14.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.14.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.14.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.14.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.15.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.15.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.15.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.15.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.15.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.15.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.15.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.15.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.15.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.15.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.16.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.16.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.16.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.16.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.16.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.16.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.16.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.16.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.16.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.16.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.17.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.17.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.17.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.17.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.17.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.17.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.17.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.17.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.17.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.17.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.18.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.18.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.18.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.18.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.18.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.18.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.18.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.18.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.18.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.18.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.19.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.19.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.19.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.19.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.19.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.19.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.19.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.19.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.19.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.19.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.2.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.2.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.2.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.2.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.20.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.20.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.20.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.20.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.20.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.20.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.20.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.20.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.20.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.21.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.21.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.21.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.21.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.21.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.21.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.21.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.21.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.21.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.21.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.22.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.22.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.22.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.22.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.22.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.22.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.22.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.22.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.22.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.22.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.23.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.23.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.23.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.23.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.23.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.23.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.23.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.23.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.23.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.23.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.3.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.3.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.3.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.3.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.4.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.4.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.4.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.4.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.5.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.5.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.5.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.5.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.6.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.6.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.6.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.6.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.7.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.7.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.7.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.7.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.8.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.8.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.8.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.8.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.9.fc1.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.9.fc1.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.9.fc2.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.9.fc2.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "audio_tower.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors", "audio_tower.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors", "audio_tower.ln_post.bias": "model-00001-of-00003.safetensors", "audio_tower.ln_post.weight": "model-00001-of-00003.safetensors", "audio_tower.proj1.bias": "model-00001-of-00003.safetensors", "audio_tower.proj1.weight": "model-00001-of-00003.safetensors", "audio_tower.proj2.bias": "model-00001-of-00003.safetensors", "audio_tower.proj2.weight": "model-00001-of-00003.safetensors", "codec.decoder.0.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.0.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.1.block.0.alpha": "model-00001-of-00003.safetensors", "codec.decoder.1.block.0.beta": "model-00001-of-00003.safetensors", "codec.decoder.1.block.1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.1.block.1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.1.block.2.act1.alpha": "model-00001-of-00003.safetensors", "codec.decoder.1.block.2.act1.beta": "model-00001-of-00003.safetensors", "codec.decoder.1.block.2.act2.alpha": "model-00001-of-00003.safetensors", "codec.decoder.1.block.2.act2.beta": "model-00001-of-00003.safetensors", "codec.decoder.1.block.2.conv1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.1.block.2.conv1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.1.block.2.conv2.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.1.block.2.conv2.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.1.block.3.act1.alpha": "model-00001-of-00003.safetensors", "codec.decoder.1.block.3.act1.beta": "model-00001-of-00003.safetensors", "codec.decoder.1.block.3.act2.alpha": "model-00001-of-00003.safetensors", "codec.decoder.1.block.3.act2.beta": "model-00001-of-00003.safetensors", "codec.decoder.1.block.3.conv1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.1.block.3.conv1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.1.block.3.conv2.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.1.block.3.conv2.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.1.block.4.act1.alpha": "model-00001-of-00003.safetensors", "codec.decoder.1.block.4.act1.beta": "model-00001-of-00003.safetensors", "codec.decoder.1.block.4.act2.alpha": "model-00001-of-00003.safetensors", "codec.decoder.1.block.4.act2.beta": "model-00001-of-00003.safetensors", "codec.decoder.1.block.4.conv1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.1.block.4.conv1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.1.block.4.conv2.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.1.block.4.conv2.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.2.block.0.alpha": "model-00001-of-00003.safetensors", "codec.decoder.2.block.0.beta": "model-00001-of-00003.safetensors", "codec.decoder.2.block.1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.2.block.1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.2.block.2.act1.alpha": "model-00001-of-00003.safetensors", "codec.decoder.2.block.2.act1.beta": "model-00001-of-00003.safetensors", "codec.decoder.2.block.2.act2.alpha": "model-00001-of-00003.safetensors", "codec.decoder.2.block.2.act2.beta": "model-00001-of-00003.safetensors", "codec.decoder.2.block.2.conv1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.2.block.2.conv1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.2.block.2.conv2.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.2.block.2.conv2.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.2.block.3.act1.alpha": "model-00001-of-00003.safetensors", "codec.decoder.2.block.3.act1.beta": "model-00001-of-00003.safetensors", "codec.decoder.2.block.3.act2.alpha": "model-00001-of-00003.safetensors", "codec.decoder.2.block.3.act2.beta": "model-00001-of-00003.safetensors", "codec.decoder.2.block.3.conv1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.2.block.3.conv1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.2.block.3.conv2.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.2.block.3.conv2.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.2.block.4.act1.alpha": "model-00001-of-00003.safetensors", "codec.decoder.2.block.4.act1.beta": "model-00001-of-00003.safetensors", "codec.decoder.2.block.4.act2.alpha": "model-00001-of-00003.safetensors", "codec.decoder.2.block.4.act2.beta": "model-00001-of-00003.safetensors", "codec.decoder.2.block.4.conv1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.2.block.4.conv1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.2.block.4.conv2.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.2.block.4.conv2.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.3.block.0.alpha": "model-00001-of-00003.safetensors", "codec.decoder.3.block.0.beta": "model-00001-of-00003.safetensors", "codec.decoder.3.block.1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.3.block.1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.3.block.2.act1.alpha": "model-00001-of-00003.safetensors", "codec.decoder.3.block.2.act1.beta": "model-00001-of-00003.safetensors", "codec.decoder.3.block.2.act2.alpha": "model-00001-of-00003.safetensors", "codec.decoder.3.block.2.act2.beta": "model-00001-of-00003.safetensors", "codec.decoder.3.block.2.conv1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.3.block.2.conv1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.3.block.2.conv2.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.3.block.2.conv2.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.3.block.3.act1.alpha": "model-00001-of-00003.safetensors", "codec.decoder.3.block.3.act1.beta": "model-00001-of-00003.safetensors", "codec.decoder.3.block.3.act2.alpha": "model-00001-of-00003.safetensors", "codec.decoder.3.block.3.act2.beta": "model-00001-of-00003.safetensors", "codec.decoder.3.block.3.conv1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.3.block.3.conv1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.3.block.3.conv2.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.3.block.3.conv2.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.3.block.4.act1.alpha": "model-00001-of-00003.safetensors", "codec.decoder.3.block.4.act1.beta": "model-00001-of-00003.safetensors", "codec.decoder.3.block.4.act2.alpha": "model-00001-of-00003.safetensors", "codec.decoder.3.block.4.act2.beta": "model-00001-of-00003.safetensors", "codec.decoder.3.block.4.conv1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.3.block.4.conv1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.3.block.4.conv2.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.3.block.4.conv2.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.4.block.0.alpha": "model-00001-of-00003.safetensors", "codec.decoder.4.block.0.beta": "model-00001-of-00003.safetensors", "codec.decoder.4.block.1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.4.block.1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.4.block.2.act1.alpha": "model-00001-of-00003.safetensors", "codec.decoder.4.block.2.act1.beta": "model-00001-of-00003.safetensors", "codec.decoder.4.block.2.act2.alpha": "model-00001-of-00003.safetensors", "codec.decoder.4.block.2.act2.beta": "model-00001-of-00003.safetensors", "codec.decoder.4.block.2.conv1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.4.block.2.conv1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.4.block.2.conv2.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.4.block.2.conv2.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.4.block.3.act1.alpha": "model-00001-of-00003.safetensors", "codec.decoder.4.block.3.act1.beta": "model-00001-of-00003.safetensors", "codec.decoder.4.block.3.act2.alpha": "model-00001-of-00003.safetensors", "codec.decoder.4.block.3.act2.beta": "model-00001-of-00003.safetensors", "codec.decoder.4.block.3.conv1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.4.block.3.conv1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.4.block.3.conv2.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.4.block.3.conv2.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.4.block.4.act1.alpha": "model-00001-of-00003.safetensors", "codec.decoder.4.block.4.act1.beta": "model-00001-of-00003.safetensors", "codec.decoder.4.block.4.act2.alpha": "model-00001-of-00003.safetensors", "codec.decoder.4.block.4.act2.beta": "model-00001-of-00003.safetensors", "codec.decoder.4.block.4.conv1.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.4.block.4.conv1.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.4.block.4.conv2.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.4.block.4.conv2.conv.weight": "model-00001-of-00003.safetensors", "codec.decoder.5.alpha": "model-00001-of-00003.safetensors", "codec.decoder.5.beta": "model-00001-of-00003.safetensors", "codec.decoder.6.conv.bias": "model-00001-of-00003.safetensors", "codec.decoder.6.conv.weight": "model-00001-of-00003.safetensors", "codec.pre_conv.conv.bias": "model-00001-of-00003.safetensors", "codec.pre_conv.conv.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.input_proj.bias": "model-00001-of-00003.safetensors", "codec.pre_transformer.input_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.0.mlp_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.0.self_attn_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.1.mlp_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.1.self_attn_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.2.mlp_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.2.self_attn_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.3.mlp_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.3.self_attn_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.4.mlp_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.4.self_attn_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.5.mlp_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.5.self_attn_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.6.mlp_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.6.self_attn_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.7.mlp_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.layers.7.self_attn_layer_scale.scale": "model-00001-of-00003.safetensors", "codec.pre_transformer.norm.weight": "model-00001-of-00003.safetensors", "codec.pre_transformer.output_proj.bias": "model-00001-of-00003.safetensors", "codec.pre_transformer.output_proj.weight": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_first.output_proj.weight": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_first.vq.layers.0._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_first.vq.layers.0._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.output_proj.weight": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.0._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.0._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.1._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.1._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.10._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.10._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.11._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.11._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.12._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.12._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.13._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.13._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.14._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.14._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.2._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.2._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.3._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.3._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.4._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.4._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.5._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.5._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.6._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.6._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.7._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.7._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.8._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.8._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.9._codebook.cluster_usage": "model-00001-of-00003.safetensors", "codec.quantizer.rvq_rest.vq.layers.9._codebook.embedding_sum": "model-00001-of-00003.safetensors", "codec.upsample.0.0.conv.bias": "model-00001-of-00003.safetensors", "codec.upsample.0.0.conv.weight": "model-00001-of-00003.safetensors", "codec.upsample.0.1.dwconv.conv.bias": "model-00001-of-00003.safetensors", "codec.upsample.0.1.dwconv.conv.weight": "model-00001-of-00003.safetensors", "codec.upsample.0.1.gamma": "model-00001-of-00003.safetensors", "codec.upsample.0.1.norm.bias": "model-00001-of-00003.safetensors", "codec.upsample.0.1.norm.weight": "model-00001-of-00003.safetensors", "codec.upsample.0.1.pwconv1.bias": "model-00001-of-00003.safetensors", "codec.upsample.0.1.pwconv1.weight": "model-00001-of-00003.safetensors", "codec.upsample.0.1.pwconv2.bias": "model-00001-of-00003.safetensors", "codec.upsample.0.1.pwconv2.weight": "model-00001-of-00003.safetensors", "codec.upsample.1.0.conv.bias": "model-00001-of-00003.safetensors", "codec.upsample.1.0.conv.weight": "model-00001-of-00003.safetensors", "codec.upsample.1.1.dwconv.conv.bias": "model-00001-of-00003.safetensors", "codec.upsample.1.1.dwconv.conv.weight": "model-00001-of-00003.safetensors", "codec.upsample.1.1.gamma": "model-00001-of-00003.safetensors", "codec.upsample.1.1.norm.bias": "model-00001-of-00003.safetensors", "codec.upsample.1.1.norm.weight": "model-00001-of-00003.safetensors", "codec.upsample.1.1.pwconv1.bias": "model-00001-of-00003.safetensors", "codec.upsample.1.1.pwconv1.weight": "model-00001-of-00003.safetensors", "codec.upsample.1.1.pwconv2.bias": "model-00001-of-00003.safetensors", "codec.upsample.1.1.pwconv2.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.16.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.16.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.17.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.17.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.18.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.18.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.19.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.19.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.20.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.20.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.21.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.21.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.22.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.22.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.23.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.23.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.23.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.24.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.24.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.24.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.25.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.25.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.25.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.26.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.26.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.26.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.26.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.26.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.26.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.26.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.27.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.27.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.27.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.27.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.27.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.27.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.27.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.27.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.27.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.27.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.backbone.norm.weight": "model-00001-of-00003.safetensors", "talker.backbone.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "talker.backbone.rotary_emb.original_inv_freq": "model-00001-of-00003.safetensors", "talker.codec_bos": "model-00001-of-00003.safetensors", "talker.codec_eos_head.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.0.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.1.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.10.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.11.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.12.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.13.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.14.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.15.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.2.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.3.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.4.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.5.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.6.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.7.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.8.weight": "model-00001-of-00003.safetensors", "talker.codec_history_embeddings.9.weight": "model-00001-of-00003.safetensors", "talker.prefix": "model-00001-of-00003.safetensors", "talker.prefix_auto": "model-00001-of-00003.safetensors", "talker.prefix_english": "model-00001-of-00003.safetensors", "talker.q0_head.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", "talker.residual_predictor.backbone.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.2.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.3.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.3.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.4.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.4.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.norm.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "talker.residual_predictor.backbone.rotary_emb.original_inv_freq": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.0.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.1.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.10.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.11.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.12.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.13.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.14.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.2.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.3.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.4.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.5.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.6.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.7.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.8.weight": "model-00002-of-00003.safetensors", "talker.residual_predictor.heads.9.weight": "model-00002-of-00003.safetensors", "talker.text_embedding.embedding.weight": "model-00002-of-00003.safetensors", "talker.text_embedding.teacher_to_row": "model-00002-of-00003.safetensors", "talker.tts_eos": "model-00002-of-00003.safetensors", "talker.tts_pad": "model-00002-of-00003.safetensors", "thinker.model.language_model.embed_tokens.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "thinker.model.language_model.norm.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.0.attn.proj.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.0.attn.proj.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.0.norm1.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.0.norm1.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.0.norm2.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.0.norm2.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.1.attn.proj.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.1.attn.proj.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.1.norm1.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.1.norm1.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.1.norm2.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.1.norm2.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.10.attn.proj.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.10.attn.proj.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.10.attn.qkv.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.10.attn.qkv.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.10.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.10.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.10.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.10.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.10.norm1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.10.norm1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.10.norm2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.10.norm2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.11.attn.proj.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.11.attn.proj.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.11.attn.qkv.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.11.attn.qkv.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.11.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.11.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.11.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.11.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.11.norm1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.11.norm1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.11.norm2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.11.norm2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.2.attn.proj.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.2.attn.proj.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.2.norm1.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.2.norm1.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.2.norm2.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.2.norm2.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.3.attn.proj.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.3.attn.proj.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.3.norm1.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.3.norm1.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.3.norm2.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.3.norm2.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.4.attn.proj.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.4.attn.proj.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.4.norm1.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.4.norm1.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.4.norm2.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.4.norm2.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.5.attn.proj.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.5.attn.proj.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", "thinker.model.visual.blocks.5.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.5.norm1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.5.norm1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.5.norm2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.5.norm2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.6.attn.proj.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.6.attn.proj.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.6.attn.qkv.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.6.attn.qkv.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.6.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.6.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.6.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.6.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.6.norm1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.6.norm1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.6.norm2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.6.norm2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.7.attn.proj.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.7.attn.proj.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.7.attn.qkv.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.7.attn.qkv.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.7.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.7.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.7.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.7.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.7.norm1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.7.norm1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.7.norm2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.7.norm2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.8.attn.proj.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.8.attn.proj.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.8.attn.qkv.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.8.attn.qkv.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.8.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.8.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.8.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.8.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.8.norm1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.8.norm1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.8.norm2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.8.norm2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.9.attn.proj.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.9.attn.proj.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.9.attn.qkv.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.9.attn.qkv.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.9.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.9.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.9.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.9.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.9.norm1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.9.norm1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.9.norm2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.blocks.9.norm2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.merger.linear_fc1.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.merger.linear_fc1.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.merger.linear_fc2.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.merger.linear_fc2.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.merger.norm.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.merger.norm.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.patch_embed.proj.bias": "model-00003-of-00003.safetensors", "thinker.model.visual.patch_embed.proj.weight": "model-00003-of-00003.safetensors", "thinker.model.visual.pos_embed.weight": "model-00003-of-00003.safetensors" } }