{ "metadata": { "total_size": 1234013744 }, "weight_map": { "audio_tower.layers.0.feed_forward1.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.0.feed_forward1.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.0.feed_forward1.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.0.feed_forward1.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.0.feed_forward1.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.0.feed_forward1.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.0.feed_forward1.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.0.feed_forward1.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.0.feed_forward1.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.0.feed_forward1.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.0.feed_forward1.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.0.feed_forward1.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.0.feed_forward2.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.0.feed_forward2.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.0.feed_forward2.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.0.feed_forward2.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.0.feed_forward2.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.0.feed_forward2.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.0.feed_forward2.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.0.feed_forward2.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.0.feed_forward2.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.0.feed_forward2.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.0.feed_forward2.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.0.feed_forward2.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.0.lconv1d.conv_norm.weight": "model.safetensors", "audio_tower.layers.0.lconv1d.depthwise_conv1d.weight": "model.safetensors", "audio_tower.layers.0.lconv1d.linear_end.input_max": "model.safetensors", "audio_tower.layers.0.lconv1d.linear_end.input_min": "model.safetensors", "audio_tower.layers.0.lconv1d.linear_end.linear.weight": "model.safetensors", "audio_tower.layers.0.lconv1d.linear_end.output_max": "model.safetensors", "audio_tower.layers.0.lconv1d.linear_end.output_min": "model.safetensors", "audio_tower.layers.0.lconv1d.linear_start.input_max": "model.safetensors", "audio_tower.layers.0.lconv1d.linear_start.input_min": "model.safetensors", "audio_tower.layers.0.lconv1d.linear_start.linear.weight": "model.safetensors", "audio_tower.layers.0.lconv1d.linear_start.output_max": "model.safetensors", "audio_tower.layers.0.lconv1d.linear_start.output_min": "model.safetensors", "audio_tower.layers.0.lconv1d.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.0.norm_out.weight": "model.safetensors", "audio_tower.layers.0.norm_post_attn.weight": "model.safetensors", "audio_tower.layers.0.norm_pre_attn.weight": "model.safetensors", "audio_tower.layers.0.self_attn.k_proj.input_max": "model.safetensors", "audio_tower.layers.0.self_attn.k_proj.input_min": "model.safetensors", "audio_tower.layers.0.self_attn.k_proj.linear.weight": "model.safetensors", "audio_tower.layers.0.self_attn.k_proj.output_max": "model.safetensors", "audio_tower.layers.0.self_attn.k_proj.output_min": "model.safetensors", "audio_tower.layers.0.self_attn.per_dim_scale": "model.safetensors", "audio_tower.layers.0.self_attn.post.input_max": "model.safetensors", "audio_tower.layers.0.self_attn.post.input_min": "model.safetensors", "audio_tower.layers.0.self_attn.post.linear.weight": "model.safetensors", "audio_tower.layers.0.self_attn.post.output_max": "model.safetensors", "audio_tower.layers.0.self_attn.post.output_min": "model.safetensors", "audio_tower.layers.0.self_attn.q_proj.input_max": "model.safetensors", "audio_tower.layers.0.self_attn.q_proj.input_min": "model.safetensors", "audio_tower.layers.0.self_attn.q_proj.linear.weight": "model.safetensors", "audio_tower.layers.0.self_attn.q_proj.output_max": "model.safetensors", "audio_tower.layers.0.self_attn.q_proj.output_min": "model.safetensors", "audio_tower.layers.0.self_attn.relative_k_proj.weight": "model.safetensors", "audio_tower.layers.0.self_attn.v_proj.input_max": "model.safetensors", "audio_tower.layers.0.self_attn.v_proj.input_min": "model.safetensors", "audio_tower.layers.0.self_attn.v_proj.linear.weight": "model.safetensors", "audio_tower.layers.0.self_attn.v_proj.output_max": "model.safetensors", "audio_tower.layers.0.self_attn.v_proj.output_min": "model.safetensors", "audio_tower.layers.1.feed_forward1.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.1.feed_forward1.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.1.feed_forward1.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.1.feed_forward1.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.1.feed_forward1.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.1.feed_forward1.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.1.feed_forward1.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.1.feed_forward1.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.1.feed_forward1.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.1.feed_forward1.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.1.feed_forward1.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.1.feed_forward1.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.1.feed_forward2.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.1.feed_forward2.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.1.feed_forward2.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.1.feed_forward2.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.1.feed_forward2.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.1.feed_forward2.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.1.feed_forward2.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.1.feed_forward2.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.1.feed_forward2.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.1.feed_forward2.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.1.feed_forward2.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.1.feed_forward2.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.1.lconv1d.conv_norm.weight": "model.safetensors", "audio_tower.layers.1.lconv1d.depthwise_conv1d.weight": "model.safetensors", "audio_tower.layers.1.lconv1d.linear_end.input_max": "model.safetensors", "audio_tower.layers.1.lconv1d.linear_end.input_min": "model.safetensors", "audio_tower.layers.1.lconv1d.linear_end.linear.weight": "model.safetensors", "audio_tower.layers.1.lconv1d.linear_end.output_max": "model.safetensors", "audio_tower.layers.1.lconv1d.linear_end.output_min": "model.safetensors", "audio_tower.layers.1.lconv1d.linear_start.input_max": "model.safetensors", "audio_tower.layers.1.lconv1d.linear_start.input_min": "model.safetensors", "audio_tower.layers.1.lconv1d.linear_start.linear.weight": "model.safetensors", "audio_tower.layers.1.lconv1d.linear_start.output_max": "model.safetensors", "audio_tower.layers.1.lconv1d.linear_start.output_min": "model.safetensors", "audio_tower.layers.1.lconv1d.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.1.norm_out.weight": "model.safetensors", "audio_tower.layers.1.norm_post_attn.weight": "model.safetensors", "audio_tower.layers.1.norm_pre_attn.weight": "model.safetensors", "audio_tower.layers.1.self_attn.k_proj.input_max": "model.safetensors", "audio_tower.layers.1.self_attn.k_proj.input_min": "model.safetensors", "audio_tower.layers.1.self_attn.k_proj.linear.weight": "model.safetensors", "audio_tower.layers.1.self_attn.k_proj.output_max": "model.safetensors", "audio_tower.layers.1.self_attn.k_proj.output_min": "model.safetensors", "audio_tower.layers.1.self_attn.per_dim_scale": "model.safetensors", "audio_tower.layers.1.self_attn.post.input_max": "model.safetensors", "audio_tower.layers.1.self_attn.post.input_min": "model.safetensors", "audio_tower.layers.1.self_attn.post.linear.weight": "model.safetensors", "audio_tower.layers.1.self_attn.post.output_max": "model.safetensors", "audio_tower.layers.1.self_attn.post.output_min": "model.safetensors", "audio_tower.layers.1.self_attn.q_proj.input_max": "model.safetensors", "audio_tower.layers.1.self_attn.q_proj.input_min": "model.safetensors", "audio_tower.layers.1.self_attn.q_proj.linear.weight": "model.safetensors", "audio_tower.layers.1.self_attn.q_proj.output_max": "model.safetensors", "audio_tower.layers.1.self_attn.q_proj.output_min": "model.safetensors", "audio_tower.layers.1.self_attn.relative_k_proj.weight": "model.safetensors", "audio_tower.layers.1.self_attn.v_proj.input_max": "model.safetensors", "audio_tower.layers.1.self_attn.v_proj.input_min": "model.safetensors", "audio_tower.layers.1.self_attn.v_proj.linear.weight": "model.safetensors", "audio_tower.layers.1.self_attn.v_proj.output_max": "model.safetensors", "audio_tower.layers.1.self_attn.v_proj.output_min": "model.safetensors", "audio_tower.layers.10.feed_forward1.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.10.feed_forward1.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.10.feed_forward1.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.10.feed_forward1.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.10.feed_forward1.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.10.feed_forward1.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.10.feed_forward1.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.10.feed_forward1.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.10.feed_forward1.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.10.feed_forward1.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.10.feed_forward1.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.10.feed_forward1.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.10.feed_forward2.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.10.feed_forward2.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.10.feed_forward2.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.10.feed_forward2.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.10.feed_forward2.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.10.feed_forward2.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.10.feed_forward2.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.10.feed_forward2.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.10.feed_forward2.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.10.feed_forward2.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.10.feed_forward2.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.10.feed_forward2.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.10.lconv1d.conv_norm.weight": "model.safetensors", "audio_tower.layers.10.lconv1d.depthwise_conv1d.weight": "model.safetensors", "audio_tower.layers.10.lconv1d.linear_end.input_max": "model.safetensors", "audio_tower.layers.10.lconv1d.linear_end.input_min": "model.safetensors", "audio_tower.layers.10.lconv1d.linear_end.linear.weight": "model.safetensors", "audio_tower.layers.10.lconv1d.linear_end.output_max": "model.safetensors", "audio_tower.layers.10.lconv1d.linear_end.output_min": "model.safetensors", "audio_tower.layers.10.lconv1d.linear_start.input_max": "model.safetensors", "audio_tower.layers.10.lconv1d.linear_start.input_min": "model.safetensors", "audio_tower.layers.10.lconv1d.linear_start.linear.weight": "model.safetensors", "audio_tower.layers.10.lconv1d.linear_start.output_max": "model.safetensors", "audio_tower.layers.10.lconv1d.linear_start.output_min": "model.safetensors", "audio_tower.layers.10.lconv1d.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.10.norm_out.weight": "model.safetensors", "audio_tower.layers.10.norm_post_attn.weight": "model.safetensors", "audio_tower.layers.10.norm_pre_attn.weight": "model.safetensors", "audio_tower.layers.10.self_attn.k_proj.input_max": "model.safetensors", "audio_tower.layers.10.self_attn.k_proj.input_min": "model.safetensors", "audio_tower.layers.10.self_attn.k_proj.linear.weight": "model.safetensors", "audio_tower.layers.10.self_attn.k_proj.output_max": "model.safetensors", "audio_tower.layers.10.self_attn.k_proj.output_min": "model.safetensors", "audio_tower.layers.10.self_attn.per_dim_scale": "model.safetensors", "audio_tower.layers.10.self_attn.post.input_max": "model.safetensors", "audio_tower.layers.10.self_attn.post.input_min": "model.safetensors", "audio_tower.layers.10.self_attn.post.linear.weight": "model.safetensors", "audio_tower.layers.10.self_attn.post.output_max": "model.safetensors", "audio_tower.layers.10.self_attn.post.output_min": "model.safetensors", "audio_tower.layers.10.self_attn.q_proj.input_max": "model.safetensors", "audio_tower.layers.10.self_attn.q_proj.input_min": "model.safetensors", "audio_tower.layers.10.self_attn.q_proj.linear.weight": "model.safetensors", "audio_tower.layers.10.self_attn.q_proj.output_max": "model.safetensors", "audio_tower.layers.10.self_attn.q_proj.output_min": "model.safetensors", "audio_tower.layers.10.self_attn.relative_k_proj.weight": "model.safetensors", "audio_tower.layers.10.self_attn.v_proj.input_max": "model.safetensors", "audio_tower.layers.10.self_attn.v_proj.input_min": "model.safetensors", "audio_tower.layers.10.self_attn.v_proj.linear.weight": "model.safetensors", "audio_tower.layers.10.self_attn.v_proj.output_max": "model.safetensors", "audio_tower.layers.10.self_attn.v_proj.output_min": "model.safetensors", "audio_tower.layers.11.feed_forward1.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.11.feed_forward1.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.11.feed_forward1.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.11.feed_forward1.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.11.feed_forward1.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.11.feed_forward1.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.11.feed_forward1.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.11.feed_forward1.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.11.feed_forward1.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.11.feed_forward1.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.11.feed_forward1.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.11.feed_forward1.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.11.feed_forward2.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.11.feed_forward2.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.11.feed_forward2.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.11.feed_forward2.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.11.feed_forward2.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.11.feed_forward2.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.11.feed_forward2.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.11.feed_forward2.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.11.feed_forward2.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.11.feed_forward2.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.11.feed_forward2.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.11.feed_forward2.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.11.lconv1d.conv_norm.weight": "model.safetensors", "audio_tower.layers.11.lconv1d.depthwise_conv1d.weight": "model.safetensors", "audio_tower.layers.11.lconv1d.linear_end.input_max": "model.safetensors", "audio_tower.layers.11.lconv1d.linear_end.input_min": "model.safetensors", "audio_tower.layers.11.lconv1d.linear_end.linear.weight": "model.safetensors", "audio_tower.layers.11.lconv1d.linear_end.output_max": "model.safetensors", "audio_tower.layers.11.lconv1d.linear_end.output_min": "model.safetensors", "audio_tower.layers.11.lconv1d.linear_start.input_max": "model.safetensors", "audio_tower.layers.11.lconv1d.linear_start.input_min": "model.safetensors", "audio_tower.layers.11.lconv1d.linear_start.linear.weight": "model.safetensors", "audio_tower.layers.11.lconv1d.linear_start.output_max": "model.safetensors", "audio_tower.layers.11.lconv1d.linear_start.output_min": "model.safetensors", "audio_tower.layers.11.lconv1d.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.11.norm_out.weight": "model.safetensors", "audio_tower.layers.11.norm_post_attn.weight": "model.safetensors", "audio_tower.layers.11.norm_pre_attn.weight": "model.safetensors", "audio_tower.layers.11.self_attn.k_proj.input_max": "model.safetensors", "audio_tower.layers.11.self_attn.k_proj.input_min": "model.safetensors", "audio_tower.layers.11.self_attn.k_proj.linear.weight": "model.safetensors", "audio_tower.layers.11.self_attn.k_proj.output_max": "model.safetensors", "audio_tower.layers.11.self_attn.k_proj.output_min": "model.safetensors", "audio_tower.layers.11.self_attn.per_dim_scale": "model.safetensors", "audio_tower.layers.11.self_attn.post.input_max": "model.safetensors", "audio_tower.layers.11.self_attn.post.input_min": "model.safetensors", "audio_tower.layers.11.self_attn.post.linear.weight": "model.safetensors", "audio_tower.layers.11.self_attn.post.output_max": "model.safetensors", "audio_tower.layers.11.self_attn.post.output_min": "model.safetensors", "audio_tower.layers.11.self_attn.q_proj.input_max": "model.safetensors", "audio_tower.layers.11.self_attn.q_proj.input_min": "model.safetensors", "audio_tower.layers.11.self_attn.q_proj.linear.weight": "model.safetensors", "audio_tower.layers.11.self_attn.q_proj.output_max": "model.safetensors", "audio_tower.layers.11.self_attn.q_proj.output_min": "model.safetensors", "audio_tower.layers.11.self_attn.relative_k_proj.weight": "model.safetensors", "audio_tower.layers.11.self_attn.v_proj.input_max": "model.safetensors", "audio_tower.layers.11.self_attn.v_proj.input_min": "model.safetensors", "audio_tower.layers.11.self_attn.v_proj.linear.weight": "model.safetensors", "audio_tower.layers.11.self_attn.v_proj.output_max": "model.safetensors", "audio_tower.layers.11.self_attn.v_proj.output_min": "model.safetensors", "audio_tower.layers.2.feed_forward1.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.2.feed_forward1.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.2.feed_forward1.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.2.feed_forward1.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.2.feed_forward1.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.2.feed_forward1.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.2.feed_forward1.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.2.feed_forward1.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.2.feed_forward1.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.2.feed_forward1.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.2.feed_forward1.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.2.feed_forward1.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.2.feed_forward2.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.2.feed_forward2.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.2.feed_forward2.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.2.feed_forward2.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.2.feed_forward2.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.2.feed_forward2.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.2.feed_forward2.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.2.feed_forward2.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.2.feed_forward2.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.2.feed_forward2.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.2.feed_forward2.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.2.feed_forward2.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.2.lconv1d.conv_norm.weight": "model.safetensors", "audio_tower.layers.2.lconv1d.depthwise_conv1d.weight": "model.safetensors", "audio_tower.layers.2.lconv1d.linear_end.input_max": "model.safetensors", "audio_tower.layers.2.lconv1d.linear_end.input_min": "model.safetensors", "audio_tower.layers.2.lconv1d.linear_end.linear.weight": "model.safetensors", "audio_tower.layers.2.lconv1d.linear_end.output_max": "model.safetensors", "audio_tower.layers.2.lconv1d.linear_end.output_min": "model.safetensors", "audio_tower.layers.2.lconv1d.linear_start.input_max": "model.safetensors", "audio_tower.layers.2.lconv1d.linear_start.input_min": "model.safetensors", "audio_tower.layers.2.lconv1d.linear_start.linear.weight": "model.safetensors", "audio_tower.layers.2.lconv1d.linear_start.output_max": "model.safetensors", "audio_tower.layers.2.lconv1d.linear_start.output_min": "model.safetensors", "audio_tower.layers.2.lconv1d.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.2.norm_out.weight": "model.safetensors", "audio_tower.layers.2.norm_post_attn.weight": "model.safetensors", "audio_tower.layers.2.norm_pre_attn.weight": "model.safetensors", "audio_tower.layers.2.self_attn.k_proj.input_max": "model.safetensors", "audio_tower.layers.2.self_attn.k_proj.input_min": "model.safetensors", "audio_tower.layers.2.self_attn.k_proj.linear.weight": "model.safetensors", "audio_tower.layers.2.self_attn.k_proj.output_max": "model.safetensors", "audio_tower.layers.2.self_attn.k_proj.output_min": "model.safetensors", "audio_tower.layers.2.self_attn.per_dim_scale": "model.safetensors", "audio_tower.layers.2.self_attn.post.input_max": "model.safetensors", "audio_tower.layers.2.self_attn.post.input_min": "model.safetensors", "audio_tower.layers.2.self_attn.post.linear.weight": "model.safetensors", "audio_tower.layers.2.self_attn.post.output_max": "model.safetensors", "audio_tower.layers.2.self_attn.post.output_min": "model.safetensors", "audio_tower.layers.2.self_attn.q_proj.input_max": "model.safetensors", "audio_tower.layers.2.self_attn.q_proj.input_min": "model.safetensors", "audio_tower.layers.2.self_attn.q_proj.linear.weight": "model.safetensors", "audio_tower.layers.2.self_attn.q_proj.output_max": "model.safetensors", "audio_tower.layers.2.self_attn.q_proj.output_min": "model.safetensors", "audio_tower.layers.2.self_attn.relative_k_proj.weight": "model.safetensors", "audio_tower.layers.2.self_attn.v_proj.input_max": "model.safetensors", "audio_tower.layers.2.self_attn.v_proj.input_min": "model.safetensors", "audio_tower.layers.2.self_attn.v_proj.linear.weight": "model.safetensors", "audio_tower.layers.2.self_attn.v_proj.output_max": "model.safetensors", "audio_tower.layers.2.self_attn.v_proj.output_min": "model.safetensors", "audio_tower.layers.3.feed_forward1.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.3.feed_forward1.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.3.feed_forward1.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.3.feed_forward1.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.3.feed_forward1.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.3.feed_forward1.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.3.feed_forward1.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.3.feed_forward1.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.3.feed_forward1.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.3.feed_forward1.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.3.feed_forward1.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.3.feed_forward1.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.3.feed_forward2.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.3.feed_forward2.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.3.feed_forward2.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.3.feed_forward2.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.3.feed_forward2.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.3.feed_forward2.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.3.feed_forward2.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.3.feed_forward2.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.3.feed_forward2.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.3.feed_forward2.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.3.feed_forward2.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.3.feed_forward2.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.3.lconv1d.conv_norm.weight": "model.safetensors", "audio_tower.layers.3.lconv1d.depthwise_conv1d.weight": "model.safetensors", "audio_tower.layers.3.lconv1d.linear_end.input_max": "model.safetensors", "audio_tower.layers.3.lconv1d.linear_end.input_min": "model.safetensors", "audio_tower.layers.3.lconv1d.linear_end.linear.weight": "model.safetensors", "audio_tower.layers.3.lconv1d.linear_end.output_max": "model.safetensors", "audio_tower.layers.3.lconv1d.linear_end.output_min": "model.safetensors", "audio_tower.layers.3.lconv1d.linear_start.input_max": "model.safetensors", "audio_tower.layers.3.lconv1d.linear_start.input_min": "model.safetensors", "audio_tower.layers.3.lconv1d.linear_start.linear.weight": "model.safetensors", "audio_tower.layers.3.lconv1d.linear_start.output_max": "model.safetensors", "audio_tower.layers.3.lconv1d.linear_start.output_min": "model.safetensors", "audio_tower.layers.3.lconv1d.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.3.norm_out.weight": "model.safetensors", "audio_tower.layers.3.norm_post_attn.weight": "model.safetensors", "audio_tower.layers.3.norm_pre_attn.weight": "model.safetensors", "audio_tower.layers.3.self_attn.k_proj.input_max": "model.safetensors", "audio_tower.layers.3.self_attn.k_proj.input_min": "model.safetensors", "audio_tower.layers.3.self_attn.k_proj.linear.weight": "model.safetensors", "audio_tower.layers.3.self_attn.k_proj.output_max": "model.safetensors", "audio_tower.layers.3.self_attn.k_proj.output_min": "model.safetensors", "audio_tower.layers.3.self_attn.per_dim_scale": "model.safetensors", "audio_tower.layers.3.self_attn.post.input_max": "model.safetensors", "audio_tower.layers.3.self_attn.post.input_min": "model.safetensors", "audio_tower.layers.3.self_attn.post.linear.weight": "model.safetensors", "audio_tower.layers.3.self_attn.post.output_max": "model.safetensors", "audio_tower.layers.3.self_attn.post.output_min": "model.safetensors", "audio_tower.layers.3.self_attn.q_proj.input_max": "model.safetensors", "audio_tower.layers.3.self_attn.q_proj.input_min": "model.safetensors", "audio_tower.layers.3.self_attn.q_proj.linear.weight": "model.safetensors", "audio_tower.layers.3.self_attn.q_proj.output_max": "model.safetensors", "audio_tower.layers.3.self_attn.q_proj.output_min": "model.safetensors", "audio_tower.layers.3.self_attn.relative_k_proj.weight": "model.safetensors", "audio_tower.layers.3.self_attn.v_proj.input_max": "model.safetensors", "audio_tower.layers.3.self_attn.v_proj.input_min": "model.safetensors", "audio_tower.layers.3.self_attn.v_proj.linear.weight": "model.safetensors", "audio_tower.layers.3.self_attn.v_proj.output_max": "model.safetensors", "audio_tower.layers.3.self_attn.v_proj.output_min": "model.safetensors", "audio_tower.layers.4.feed_forward1.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.4.feed_forward1.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.4.feed_forward1.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.4.feed_forward1.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.4.feed_forward1.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.4.feed_forward1.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.4.feed_forward1.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.4.feed_forward1.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.4.feed_forward1.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.4.feed_forward1.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.4.feed_forward1.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.4.feed_forward1.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.4.feed_forward2.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.4.feed_forward2.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.4.feed_forward2.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.4.feed_forward2.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.4.feed_forward2.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.4.feed_forward2.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.4.feed_forward2.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.4.feed_forward2.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.4.feed_forward2.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.4.feed_forward2.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.4.feed_forward2.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.4.feed_forward2.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.4.lconv1d.conv_norm.weight": "model.safetensors", "audio_tower.layers.4.lconv1d.depthwise_conv1d.weight": "model.safetensors", "audio_tower.layers.4.lconv1d.linear_end.input_max": "model.safetensors", "audio_tower.layers.4.lconv1d.linear_end.input_min": "model.safetensors", "audio_tower.layers.4.lconv1d.linear_end.linear.weight": "model.safetensors", "audio_tower.layers.4.lconv1d.linear_end.output_max": "model.safetensors", "audio_tower.layers.4.lconv1d.linear_end.output_min": "model.safetensors", "audio_tower.layers.4.lconv1d.linear_start.input_max": "model.safetensors", "audio_tower.layers.4.lconv1d.linear_start.input_min": "model.safetensors", "audio_tower.layers.4.lconv1d.linear_start.linear.weight": "model.safetensors", "audio_tower.layers.4.lconv1d.linear_start.output_max": "model.safetensors", "audio_tower.layers.4.lconv1d.linear_start.output_min": "model.safetensors", "audio_tower.layers.4.lconv1d.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.4.norm_out.weight": "model.safetensors", "audio_tower.layers.4.norm_post_attn.weight": "model.safetensors", "audio_tower.layers.4.norm_pre_attn.weight": "model.safetensors", "audio_tower.layers.4.self_attn.k_proj.input_max": "model.safetensors", "audio_tower.layers.4.self_attn.k_proj.input_min": "model.safetensors", "audio_tower.layers.4.self_attn.k_proj.linear.weight": "model.safetensors", "audio_tower.layers.4.self_attn.k_proj.output_max": "model.safetensors", "audio_tower.layers.4.self_attn.k_proj.output_min": "model.safetensors", "audio_tower.layers.4.self_attn.per_dim_scale": "model.safetensors", "audio_tower.layers.4.self_attn.post.input_max": "model.safetensors", "audio_tower.layers.4.self_attn.post.input_min": "model.safetensors", "audio_tower.layers.4.self_attn.post.linear.weight": "model.safetensors", "audio_tower.layers.4.self_attn.post.output_max": "model.safetensors", "audio_tower.layers.4.self_attn.post.output_min": "model.safetensors", "audio_tower.layers.4.self_attn.q_proj.input_max": "model.safetensors", "audio_tower.layers.4.self_attn.q_proj.input_min": "model.safetensors", "audio_tower.layers.4.self_attn.q_proj.linear.weight": "model.safetensors", "audio_tower.layers.4.self_attn.q_proj.output_max": "model.safetensors", "audio_tower.layers.4.self_attn.q_proj.output_min": "model.safetensors", "audio_tower.layers.4.self_attn.relative_k_proj.weight": "model.safetensors", "audio_tower.layers.4.self_attn.v_proj.input_max": "model.safetensors", "audio_tower.layers.4.self_attn.v_proj.input_min": "model.safetensors", "audio_tower.layers.4.self_attn.v_proj.linear.weight": "model.safetensors", "audio_tower.layers.4.self_attn.v_proj.output_max": "model.safetensors", "audio_tower.layers.4.self_attn.v_proj.output_min": "model.safetensors", "audio_tower.layers.5.feed_forward1.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.5.feed_forward1.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.5.feed_forward1.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.5.feed_forward1.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.5.feed_forward1.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.5.feed_forward1.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.5.feed_forward1.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.5.feed_forward1.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.5.feed_forward1.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.5.feed_forward1.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.5.feed_forward1.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.5.feed_forward1.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.5.feed_forward2.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.5.feed_forward2.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.5.feed_forward2.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.5.feed_forward2.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.5.feed_forward2.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.5.feed_forward2.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.5.feed_forward2.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.5.feed_forward2.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.5.feed_forward2.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.5.feed_forward2.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.5.feed_forward2.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.5.feed_forward2.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.5.lconv1d.conv_norm.weight": "model.safetensors", "audio_tower.layers.5.lconv1d.depthwise_conv1d.weight": "model.safetensors", "audio_tower.layers.5.lconv1d.linear_end.input_max": "model.safetensors", "audio_tower.layers.5.lconv1d.linear_end.input_min": "model.safetensors", "audio_tower.layers.5.lconv1d.linear_end.linear.weight": "model.safetensors", "audio_tower.layers.5.lconv1d.linear_end.output_max": "model.safetensors", "audio_tower.layers.5.lconv1d.linear_end.output_min": "model.safetensors", "audio_tower.layers.5.lconv1d.linear_start.input_max": "model.safetensors", "audio_tower.layers.5.lconv1d.linear_start.input_min": "model.safetensors", "audio_tower.layers.5.lconv1d.linear_start.linear.weight": "model.safetensors", "audio_tower.layers.5.lconv1d.linear_start.output_max": "model.safetensors", "audio_tower.layers.5.lconv1d.linear_start.output_min": "model.safetensors", "audio_tower.layers.5.lconv1d.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.5.norm_out.weight": "model.safetensors", "audio_tower.layers.5.norm_post_attn.weight": "model.safetensors", "audio_tower.layers.5.norm_pre_attn.weight": "model.safetensors", "audio_tower.layers.5.self_attn.k_proj.input_max": "model.safetensors", "audio_tower.layers.5.self_attn.k_proj.input_min": "model.safetensors", "audio_tower.layers.5.self_attn.k_proj.linear.weight": "model.safetensors", "audio_tower.layers.5.self_attn.k_proj.output_max": "model.safetensors", "audio_tower.layers.5.self_attn.k_proj.output_min": "model.safetensors", "audio_tower.layers.5.self_attn.per_dim_scale": "model.safetensors", "audio_tower.layers.5.self_attn.post.input_max": "model.safetensors", "audio_tower.layers.5.self_attn.post.input_min": "model.safetensors", "audio_tower.layers.5.self_attn.post.linear.weight": "model.safetensors", "audio_tower.layers.5.self_attn.post.output_max": "model.safetensors", "audio_tower.layers.5.self_attn.post.output_min": "model.safetensors", "audio_tower.layers.5.self_attn.q_proj.input_max": "model.safetensors", "audio_tower.layers.5.self_attn.q_proj.input_min": "model.safetensors", "audio_tower.layers.5.self_attn.q_proj.linear.weight": "model.safetensors", "audio_tower.layers.5.self_attn.q_proj.output_max": "model.safetensors", "audio_tower.layers.5.self_attn.q_proj.output_min": "model.safetensors", "audio_tower.layers.5.self_attn.relative_k_proj.weight": "model.safetensors", "audio_tower.layers.5.self_attn.v_proj.input_max": "model.safetensors", "audio_tower.layers.5.self_attn.v_proj.input_min": "model.safetensors", "audio_tower.layers.5.self_attn.v_proj.linear.weight": "model.safetensors", "audio_tower.layers.5.self_attn.v_proj.output_max": "model.safetensors", "audio_tower.layers.5.self_attn.v_proj.output_min": "model.safetensors", "audio_tower.layers.6.feed_forward1.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.6.feed_forward1.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.6.feed_forward1.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.6.feed_forward1.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.6.feed_forward1.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.6.feed_forward1.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.6.feed_forward1.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.6.feed_forward1.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.6.feed_forward1.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.6.feed_forward1.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.6.feed_forward1.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.6.feed_forward1.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.6.feed_forward2.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.6.feed_forward2.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.6.feed_forward2.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.6.feed_forward2.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.6.feed_forward2.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.6.feed_forward2.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.6.feed_forward2.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.6.feed_forward2.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.6.feed_forward2.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.6.feed_forward2.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.6.feed_forward2.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.6.feed_forward2.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.6.lconv1d.conv_norm.weight": "model.safetensors", "audio_tower.layers.6.lconv1d.depthwise_conv1d.weight": "model.safetensors", "audio_tower.layers.6.lconv1d.linear_end.input_max": "model.safetensors", "audio_tower.layers.6.lconv1d.linear_end.input_min": "model.safetensors", "audio_tower.layers.6.lconv1d.linear_end.linear.weight": "model.safetensors", "audio_tower.layers.6.lconv1d.linear_end.output_max": "model.safetensors", "audio_tower.layers.6.lconv1d.linear_end.output_min": "model.safetensors", "audio_tower.layers.6.lconv1d.linear_start.input_max": "model.safetensors", "audio_tower.layers.6.lconv1d.linear_start.input_min": "model.safetensors", "audio_tower.layers.6.lconv1d.linear_start.linear.weight": "model.safetensors", "audio_tower.layers.6.lconv1d.linear_start.output_max": "model.safetensors", "audio_tower.layers.6.lconv1d.linear_start.output_min": "model.safetensors", "audio_tower.layers.6.lconv1d.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.6.norm_out.weight": "model.safetensors", "audio_tower.layers.6.norm_post_attn.weight": "model.safetensors", "audio_tower.layers.6.norm_pre_attn.weight": "model.safetensors", "audio_tower.layers.6.self_attn.k_proj.input_max": "model.safetensors", "audio_tower.layers.6.self_attn.k_proj.input_min": "model.safetensors", "audio_tower.layers.6.self_attn.k_proj.linear.weight": "model.safetensors", "audio_tower.layers.6.self_attn.k_proj.output_max": "model.safetensors", "audio_tower.layers.6.self_attn.k_proj.output_min": "model.safetensors", "audio_tower.layers.6.self_attn.per_dim_scale": "model.safetensors", "audio_tower.layers.6.self_attn.post.input_max": "model.safetensors", "audio_tower.layers.6.self_attn.post.input_min": "model.safetensors", "audio_tower.layers.6.self_attn.post.linear.weight": "model.safetensors", "audio_tower.layers.6.self_attn.post.output_max": "model.safetensors", "audio_tower.layers.6.self_attn.post.output_min": "model.safetensors", "audio_tower.layers.6.self_attn.q_proj.input_max": "model.safetensors", "audio_tower.layers.6.self_attn.q_proj.input_min": "model.safetensors", "audio_tower.layers.6.self_attn.q_proj.linear.weight": "model.safetensors", "audio_tower.layers.6.self_attn.q_proj.output_max": "model.safetensors", "audio_tower.layers.6.self_attn.q_proj.output_min": "model.safetensors", "audio_tower.layers.6.self_attn.relative_k_proj.weight": "model.safetensors", "audio_tower.layers.6.self_attn.v_proj.input_max": "model.safetensors", "audio_tower.layers.6.self_attn.v_proj.input_min": "model.safetensors", "audio_tower.layers.6.self_attn.v_proj.linear.weight": "model.safetensors", "audio_tower.layers.6.self_attn.v_proj.output_max": "model.safetensors", "audio_tower.layers.6.self_attn.v_proj.output_min": "model.safetensors", "audio_tower.layers.7.feed_forward1.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.7.feed_forward1.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.7.feed_forward1.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.7.feed_forward1.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.7.feed_forward1.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.7.feed_forward1.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.7.feed_forward1.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.7.feed_forward1.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.7.feed_forward1.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.7.feed_forward1.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.7.feed_forward1.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.7.feed_forward1.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.7.feed_forward2.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.7.feed_forward2.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.7.feed_forward2.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.7.feed_forward2.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.7.feed_forward2.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.7.feed_forward2.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.7.feed_forward2.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.7.feed_forward2.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.7.feed_forward2.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.7.feed_forward2.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.7.feed_forward2.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.7.feed_forward2.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.7.lconv1d.conv_norm.weight": "model.safetensors", "audio_tower.layers.7.lconv1d.depthwise_conv1d.weight": "model.safetensors", "audio_tower.layers.7.lconv1d.linear_end.input_max": "model.safetensors", "audio_tower.layers.7.lconv1d.linear_end.input_min": "model.safetensors", "audio_tower.layers.7.lconv1d.linear_end.linear.weight": "model.safetensors", "audio_tower.layers.7.lconv1d.linear_end.output_max": "model.safetensors", "audio_tower.layers.7.lconv1d.linear_end.output_min": "model.safetensors", "audio_tower.layers.7.lconv1d.linear_start.input_max": "model.safetensors", "audio_tower.layers.7.lconv1d.linear_start.input_min": "model.safetensors", "audio_tower.layers.7.lconv1d.linear_start.linear.weight": "model.safetensors", "audio_tower.layers.7.lconv1d.linear_start.output_max": "model.safetensors", "audio_tower.layers.7.lconv1d.linear_start.output_min": "model.safetensors", "audio_tower.layers.7.lconv1d.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.7.norm_out.weight": "model.safetensors", "audio_tower.layers.7.norm_post_attn.weight": "model.safetensors", "audio_tower.layers.7.norm_pre_attn.weight": "model.safetensors", "audio_tower.layers.7.self_attn.k_proj.input_max": "model.safetensors", "audio_tower.layers.7.self_attn.k_proj.input_min": "model.safetensors", "audio_tower.layers.7.self_attn.k_proj.linear.weight": "model.safetensors", "audio_tower.layers.7.self_attn.k_proj.output_max": "model.safetensors", "audio_tower.layers.7.self_attn.k_proj.output_min": "model.safetensors", "audio_tower.layers.7.self_attn.per_dim_scale": "model.safetensors", "audio_tower.layers.7.self_attn.post.input_max": "model.safetensors", "audio_tower.layers.7.self_attn.post.input_min": "model.safetensors", "audio_tower.layers.7.self_attn.post.linear.weight": "model.safetensors", "audio_tower.layers.7.self_attn.post.output_max": "model.safetensors", "audio_tower.layers.7.self_attn.post.output_min": "model.safetensors", "audio_tower.layers.7.self_attn.q_proj.input_max": "model.safetensors", "audio_tower.layers.7.self_attn.q_proj.input_min": "model.safetensors", "audio_tower.layers.7.self_attn.q_proj.linear.weight": "model.safetensors", "audio_tower.layers.7.self_attn.q_proj.output_max": "model.safetensors", "audio_tower.layers.7.self_attn.q_proj.output_min": "model.safetensors", "audio_tower.layers.7.self_attn.relative_k_proj.weight": "model.safetensors", "audio_tower.layers.7.self_attn.v_proj.input_max": "model.safetensors", "audio_tower.layers.7.self_attn.v_proj.input_min": "model.safetensors", "audio_tower.layers.7.self_attn.v_proj.linear.weight": "model.safetensors", "audio_tower.layers.7.self_attn.v_proj.output_max": "model.safetensors", "audio_tower.layers.7.self_attn.v_proj.output_min": "model.safetensors", "audio_tower.layers.8.feed_forward1.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.8.feed_forward1.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.8.feed_forward1.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.8.feed_forward1.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.8.feed_forward1.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.8.feed_forward1.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.8.feed_forward1.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.8.feed_forward1.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.8.feed_forward1.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.8.feed_forward1.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.8.feed_forward1.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.8.feed_forward1.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.8.feed_forward2.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.8.feed_forward2.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.8.feed_forward2.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.8.feed_forward2.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.8.feed_forward2.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.8.feed_forward2.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.8.feed_forward2.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.8.feed_forward2.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.8.feed_forward2.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.8.feed_forward2.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.8.feed_forward2.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.8.feed_forward2.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.8.lconv1d.conv_norm.weight": "model.safetensors", "audio_tower.layers.8.lconv1d.depthwise_conv1d.weight": "model.safetensors", "audio_tower.layers.8.lconv1d.linear_end.input_max": "model.safetensors", "audio_tower.layers.8.lconv1d.linear_end.input_min": "model.safetensors", "audio_tower.layers.8.lconv1d.linear_end.linear.weight": "model.safetensors", "audio_tower.layers.8.lconv1d.linear_end.output_max": "model.safetensors", "audio_tower.layers.8.lconv1d.linear_end.output_min": "model.safetensors", "audio_tower.layers.8.lconv1d.linear_start.input_max": "model.safetensors", "audio_tower.layers.8.lconv1d.linear_start.input_min": "model.safetensors", "audio_tower.layers.8.lconv1d.linear_start.linear.weight": "model.safetensors", "audio_tower.layers.8.lconv1d.linear_start.output_max": "model.safetensors", "audio_tower.layers.8.lconv1d.linear_start.output_min": "model.safetensors", "audio_tower.layers.8.lconv1d.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.8.norm_out.weight": "model.safetensors", "audio_tower.layers.8.norm_post_attn.weight": "model.safetensors", "audio_tower.layers.8.norm_pre_attn.weight": "model.safetensors", "audio_tower.layers.8.self_attn.k_proj.input_max": "model.safetensors", "audio_tower.layers.8.self_attn.k_proj.input_min": "model.safetensors", "audio_tower.layers.8.self_attn.k_proj.linear.weight": "model.safetensors", "audio_tower.layers.8.self_attn.k_proj.output_max": "model.safetensors", "audio_tower.layers.8.self_attn.k_proj.output_min": "model.safetensors", "audio_tower.layers.8.self_attn.per_dim_scale": "model.safetensors", "audio_tower.layers.8.self_attn.post.input_max": "model.safetensors", "audio_tower.layers.8.self_attn.post.input_min": "model.safetensors", "audio_tower.layers.8.self_attn.post.linear.weight": "model.safetensors", "audio_tower.layers.8.self_attn.post.output_max": "model.safetensors", "audio_tower.layers.8.self_attn.post.output_min": "model.safetensors", "audio_tower.layers.8.self_attn.q_proj.input_max": "model.safetensors", "audio_tower.layers.8.self_attn.q_proj.input_min": "model.safetensors", "audio_tower.layers.8.self_attn.q_proj.linear.weight": "model.safetensors", "audio_tower.layers.8.self_attn.q_proj.output_max": "model.safetensors", "audio_tower.layers.8.self_attn.q_proj.output_min": "model.safetensors", "audio_tower.layers.8.self_attn.relative_k_proj.weight": "model.safetensors", "audio_tower.layers.8.self_attn.v_proj.input_max": "model.safetensors", "audio_tower.layers.8.self_attn.v_proj.input_min": "model.safetensors", "audio_tower.layers.8.self_attn.v_proj.linear.weight": "model.safetensors", "audio_tower.layers.8.self_attn.v_proj.output_max": "model.safetensors", "audio_tower.layers.8.self_attn.v_proj.output_min": "model.safetensors", "audio_tower.layers.9.feed_forward1.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.9.feed_forward1.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.9.feed_forward1.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.9.feed_forward1.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.9.feed_forward1.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.9.feed_forward1.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.9.feed_forward1.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.9.feed_forward1.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.9.feed_forward1.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.9.feed_forward1.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.9.feed_forward1.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.9.feed_forward1.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.9.feed_forward2.ffw_layer_1.input_max": "model.safetensors", "audio_tower.layers.9.feed_forward2.ffw_layer_1.input_min": "model.safetensors", "audio_tower.layers.9.feed_forward2.ffw_layer_1.linear.weight": "model.safetensors", "audio_tower.layers.9.feed_forward2.ffw_layer_1.output_max": "model.safetensors", "audio_tower.layers.9.feed_forward2.ffw_layer_1.output_min": "model.safetensors", "audio_tower.layers.9.feed_forward2.ffw_layer_2.input_max": "model.safetensors", "audio_tower.layers.9.feed_forward2.ffw_layer_2.input_min": "model.safetensors", "audio_tower.layers.9.feed_forward2.ffw_layer_2.linear.weight": "model.safetensors", "audio_tower.layers.9.feed_forward2.ffw_layer_2.output_max": "model.safetensors", "audio_tower.layers.9.feed_forward2.ffw_layer_2.output_min": "model.safetensors", "audio_tower.layers.9.feed_forward2.post_layer_norm.weight": "model.safetensors", "audio_tower.layers.9.feed_forward2.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.9.lconv1d.conv_norm.weight": "model.safetensors", "audio_tower.layers.9.lconv1d.depthwise_conv1d.weight": "model.safetensors", "audio_tower.layers.9.lconv1d.linear_end.input_max": "model.safetensors", "audio_tower.layers.9.lconv1d.linear_end.input_min": "model.safetensors", "audio_tower.layers.9.lconv1d.linear_end.linear.weight": "model.safetensors", "audio_tower.layers.9.lconv1d.linear_end.output_max": "model.safetensors", "audio_tower.layers.9.lconv1d.linear_end.output_min": "model.safetensors", "audio_tower.layers.9.lconv1d.linear_start.input_max": "model.safetensors", "audio_tower.layers.9.lconv1d.linear_start.input_min": "model.safetensors", "audio_tower.layers.9.lconv1d.linear_start.linear.weight": "model.safetensors", "audio_tower.layers.9.lconv1d.linear_start.output_max": "model.safetensors", "audio_tower.layers.9.lconv1d.linear_start.output_min": "model.safetensors", "audio_tower.layers.9.lconv1d.pre_layer_norm.weight": "model.safetensors", "audio_tower.layers.9.norm_out.weight": "model.safetensors", "audio_tower.layers.9.norm_post_attn.weight": "model.safetensors", "audio_tower.layers.9.norm_pre_attn.weight": "model.safetensors", "audio_tower.layers.9.self_attn.k_proj.input_max": "model.safetensors", "audio_tower.layers.9.self_attn.k_proj.input_min": "model.safetensors", "audio_tower.layers.9.self_attn.k_proj.linear.weight": "model.safetensors", "audio_tower.layers.9.self_attn.k_proj.output_max": "model.safetensors", "audio_tower.layers.9.self_attn.k_proj.output_min": "model.safetensors", "audio_tower.layers.9.self_attn.per_dim_scale": "model.safetensors", "audio_tower.layers.9.self_attn.post.input_max": "model.safetensors", "audio_tower.layers.9.self_attn.post.input_min": "model.safetensors", "audio_tower.layers.9.self_attn.post.linear.weight": "model.safetensors", "audio_tower.layers.9.self_attn.post.output_max": "model.safetensors", "audio_tower.layers.9.self_attn.post.output_min": "model.safetensors", "audio_tower.layers.9.self_attn.q_proj.input_max": "model.safetensors", "audio_tower.layers.9.self_attn.q_proj.input_min": "model.safetensors", "audio_tower.layers.9.self_attn.q_proj.linear.weight": "model.safetensors", "audio_tower.layers.9.self_attn.q_proj.output_max": "model.safetensors", "audio_tower.layers.9.self_attn.q_proj.output_min": "model.safetensors", "audio_tower.layers.9.self_attn.relative_k_proj.weight": "model.safetensors", "audio_tower.layers.9.self_attn.v_proj.input_max": "model.safetensors", "audio_tower.layers.9.self_attn.v_proj.input_min": "model.safetensors", "audio_tower.layers.9.self_attn.v_proj.linear.weight": "model.safetensors", "audio_tower.layers.9.self_attn.v_proj.output_max": "model.safetensors", "audio_tower.layers.9.self_attn.v_proj.output_min": "model.safetensors", "audio_tower.output_proj.bias": "model.safetensors", "audio_tower.output_proj.weight": "model.safetensors", "audio_tower.subsample_conv_projection.input_proj_linear.weight": "model.safetensors", "audio_tower.subsample_conv_projection.layer0.conv.weight": "model.safetensors", "audio_tower.subsample_conv_projection.layer0.norm.weight": "model.safetensors", "audio_tower.subsample_conv_projection.layer1.conv.weight": "model.safetensors", "audio_tower.subsample_conv_projection.layer1.norm.weight": "model.safetensors", "embed_audio.embedding_projection.biases": "model.safetensors", "embed_audio.embedding_projection.scales": "model.safetensors", "embed_audio.embedding_projection.weight": "model.safetensors", "embed_vision.embedding_projection.weight": "model.safetensors", "language_model.embed_tokens.biases": "model.safetensors", "language_model.embed_tokens.scales": "model.safetensors", "language_model.embed_tokens.weight": "model.safetensors", "language_model.embedding_projection.biases": "model.safetensors", "language_model.embedding_projection.scales": "model.safetensors", "language_model.embedding_projection.weight": "model.safetensors", "language_model.layers.0.input_layernorm.weight": "model.safetensors", "language_model.layers.0.layer_scalar": "model.safetensors", "language_model.layers.0.mlp.down_proj.biases": "model.safetensors", "language_model.layers.0.mlp.down_proj.scales": "model.safetensors", "language_model.layers.0.mlp.down_proj.weight": "model.safetensors", "language_model.layers.0.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.0.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.0.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.0.mlp.up_proj.biases": "model.safetensors", "language_model.layers.0.mlp.up_proj.scales": "model.safetensors", "language_model.layers.0.mlp.up_proj.weight": "model.safetensors", "language_model.layers.0.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.0.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.0.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.0.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.0.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.0.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.0.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.0.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.0.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.0.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.0.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.0.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.0.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.0.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.0.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.0.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.0.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.0.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.0.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.0.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.0.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.0.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.0.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.0.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.1.input_layernorm.weight": "model.safetensors", "language_model.layers.1.layer_scalar": "model.safetensors", "language_model.layers.1.mlp.down_proj.biases": "model.safetensors", "language_model.layers.1.mlp.down_proj.scales": "model.safetensors", "language_model.layers.1.mlp.down_proj.weight": "model.safetensors", "language_model.layers.1.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.1.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.1.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.1.mlp.up_proj.biases": "model.safetensors", "language_model.layers.1.mlp.up_proj.scales": "model.safetensors", "language_model.layers.1.mlp.up_proj.weight": "model.safetensors", "language_model.layers.1.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.1.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.1.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.1.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.1.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.1.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.1.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.1.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.1.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.1.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.1.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.1.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.1.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.1.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.1.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.1.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.1.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.1.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.1.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.1.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.1.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.1.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.1.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.1.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.10.input_layernorm.weight": "model.safetensors", "language_model.layers.10.layer_scalar": "model.safetensors", "language_model.layers.10.mlp.down_proj.biases": "model.safetensors", "language_model.layers.10.mlp.down_proj.scales": "model.safetensors", "language_model.layers.10.mlp.down_proj.weight": "model.safetensors", "language_model.layers.10.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.10.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.10.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.10.mlp.up_proj.biases": "model.safetensors", "language_model.layers.10.mlp.up_proj.scales": "model.safetensors", "language_model.layers.10.mlp.up_proj.weight": "model.safetensors", "language_model.layers.10.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.10.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.10.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.10.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.10.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.10.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.10.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.10.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.10.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.10.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.10.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.10.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.10.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.10.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.10.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.10.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.10.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.10.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.10.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.10.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.10.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.10.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.10.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.10.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.11.input_layernorm.weight": "model.safetensors", "language_model.layers.11.layer_scalar": "model.safetensors", "language_model.layers.11.mlp.down_proj.biases": "model.safetensors", "language_model.layers.11.mlp.down_proj.scales": "model.safetensors", "language_model.layers.11.mlp.down_proj.weight": "model.safetensors", "language_model.layers.11.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.11.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.11.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.11.mlp.up_proj.biases": "model.safetensors", "language_model.layers.11.mlp.up_proj.scales": "model.safetensors", "language_model.layers.11.mlp.up_proj.weight": "model.safetensors", "language_model.layers.11.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.11.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.11.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.11.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.11.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.11.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.11.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.11.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.11.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.11.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.11.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.11.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.11.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.11.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.11.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.11.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.11.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.11.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.11.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.11.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.11.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.11.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.11.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.11.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.12.input_layernorm.weight": "model.safetensors", "language_model.layers.12.layer_scalar": "model.safetensors", "language_model.layers.12.mlp.down_proj.biases": "model.safetensors", "language_model.layers.12.mlp.down_proj.scales": "model.safetensors", "language_model.layers.12.mlp.down_proj.weight": "model.safetensors", "language_model.layers.12.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.12.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.12.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.12.mlp.up_proj.biases": "model.safetensors", "language_model.layers.12.mlp.up_proj.scales": "model.safetensors", "language_model.layers.12.mlp.up_proj.weight": "model.safetensors", "language_model.layers.12.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.12.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.12.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.12.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.12.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.12.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.12.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.12.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.12.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.12.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.12.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.12.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.12.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.12.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.12.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.12.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.12.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.12.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.12.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.12.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.12.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.12.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.12.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.12.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.13.input_layernorm.weight": "model.safetensors", "language_model.layers.13.layer_scalar": "model.safetensors", "language_model.layers.13.mlp.down_proj.biases": "model.safetensors", "language_model.layers.13.mlp.down_proj.scales": "model.safetensors", "language_model.layers.13.mlp.down_proj.weight": "model.safetensors", "language_model.layers.13.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.13.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.13.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.13.mlp.up_proj.biases": "model.safetensors", "language_model.layers.13.mlp.up_proj.scales": "model.safetensors", "language_model.layers.13.mlp.up_proj.weight": "model.safetensors", "language_model.layers.13.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.13.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.13.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.13.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.13.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.13.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.13.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.13.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.13.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.13.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.13.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.13.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.13.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.13.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.13.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.13.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.13.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.13.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.13.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.13.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.13.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.13.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.13.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.13.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.14.input_layernorm.weight": "model.safetensors", "language_model.layers.14.layer_scalar": "model.safetensors", "language_model.layers.14.mlp.down_proj.biases": "model.safetensors", "language_model.layers.14.mlp.down_proj.scales": "model.safetensors", "language_model.layers.14.mlp.down_proj.weight": "model.safetensors", "language_model.layers.14.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.14.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.14.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.14.mlp.up_proj.biases": "model.safetensors", "language_model.layers.14.mlp.up_proj.scales": "model.safetensors", "language_model.layers.14.mlp.up_proj.weight": "model.safetensors", "language_model.layers.14.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.14.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.14.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.14.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.14.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.14.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.14.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.14.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.14.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.14.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.14.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.14.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.14.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.14.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.14.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.14.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.14.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.14.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.14.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.14.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.14.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.14.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.14.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.14.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.15.input_layernorm.weight": "model.safetensors", "language_model.layers.15.layer_scalar": "model.safetensors", "language_model.layers.15.mlp.down_proj.biases": "model.safetensors", "language_model.layers.15.mlp.down_proj.scales": "model.safetensors", "language_model.layers.15.mlp.down_proj.weight": "model.safetensors", "language_model.layers.15.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.15.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.15.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.15.mlp.up_proj.biases": "model.safetensors", "language_model.layers.15.mlp.up_proj.scales": "model.safetensors", "language_model.layers.15.mlp.up_proj.weight": "model.safetensors", "language_model.layers.15.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.15.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.15.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.15.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.15.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.15.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.15.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.15.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.15.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.15.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.15.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.15.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.15.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.15.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.15.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.15.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.15.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.15.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.15.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.15.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.15.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.15.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.15.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.15.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.16.input_layernorm.weight": "model.safetensors", "language_model.layers.16.layer_scalar": "model.safetensors", "language_model.layers.16.mlp.down_proj.biases": "model.safetensors", "language_model.layers.16.mlp.down_proj.scales": "model.safetensors", "language_model.layers.16.mlp.down_proj.weight": "model.safetensors", "language_model.layers.16.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.16.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.16.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.16.mlp.up_proj.biases": "model.safetensors", "language_model.layers.16.mlp.up_proj.scales": "model.safetensors", "language_model.layers.16.mlp.up_proj.weight": "model.safetensors", "language_model.layers.16.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.16.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.16.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.16.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.16.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.16.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.16.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.16.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.16.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.16.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.16.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.16.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.16.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.16.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.16.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.16.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.16.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.16.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.16.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.16.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.16.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.16.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.16.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.16.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.17.input_layernorm.weight": "model.safetensors", "language_model.layers.17.layer_scalar": "model.safetensors", "language_model.layers.17.mlp.down_proj.biases": "model.safetensors", "language_model.layers.17.mlp.down_proj.scales": "model.safetensors", "language_model.layers.17.mlp.down_proj.weight": "model.safetensors", "language_model.layers.17.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.17.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.17.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.17.mlp.up_proj.biases": "model.safetensors", "language_model.layers.17.mlp.up_proj.scales": "model.safetensors", "language_model.layers.17.mlp.up_proj.weight": "model.safetensors", "language_model.layers.17.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.17.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.17.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.17.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.17.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.17.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.17.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.17.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.17.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.17.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.17.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.17.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.17.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.17.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.17.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.17.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.17.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.17.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.17.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.17.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.17.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.17.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.17.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.17.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.18.input_layernorm.weight": "model.safetensors", "language_model.layers.18.layer_scalar": "model.safetensors", "language_model.layers.18.mlp.down_proj.biases": "model.safetensors", "language_model.layers.18.mlp.down_proj.scales": "model.safetensors", "language_model.layers.18.mlp.down_proj.weight": "model.safetensors", "language_model.layers.18.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.18.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.18.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.18.mlp.up_proj.biases": "model.safetensors", "language_model.layers.18.mlp.up_proj.scales": "model.safetensors", "language_model.layers.18.mlp.up_proj.weight": "model.safetensors", "language_model.layers.18.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.18.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.18.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.18.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.18.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.18.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.18.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.18.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.18.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.18.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.18.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.18.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.18.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.18.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.18.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.18.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.18.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.18.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.18.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.18.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.18.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.18.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.18.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.18.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.19.input_layernorm.weight": "model.safetensors", "language_model.layers.19.layer_scalar": "model.safetensors", "language_model.layers.19.mlp.down_proj.biases": "model.safetensors", "language_model.layers.19.mlp.down_proj.scales": "model.safetensors", "language_model.layers.19.mlp.down_proj.weight": "model.safetensors", "language_model.layers.19.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.19.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.19.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.19.mlp.up_proj.biases": "model.safetensors", "language_model.layers.19.mlp.up_proj.scales": "model.safetensors", "language_model.layers.19.mlp.up_proj.weight": "model.safetensors", "language_model.layers.19.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.19.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.19.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.19.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.19.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.19.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.19.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.19.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.19.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.19.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.19.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.19.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.19.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.19.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.19.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.19.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.19.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.19.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.19.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.19.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.19.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.19.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.19.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.19.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.2.input_layernorm.weight": "model.safetensors", "language_model.layers.2.layer_scalar": "model.safetensors", "language_model.layers.2.mlp.down_proj.biases": "model.safetensors", "language_model.layers.2.mlp.down_proj.scales": "model.safetensors", "language_model.layers.2.mlp.down_proj.weight": "model.safetensors", "language_model.layers.2.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.2.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.2.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.2.mlp.up_proj.biases": "model.safetensors", "language_model.layers.2.mlp.up_proj.scales": "model.safetensors", "language_model.layers.2.mlp.up_proj.weight": "model.safetensors", "language_model.layers.2.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.2.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.2.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.2.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.2.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.2.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.2.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.2.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.2.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.2.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.2.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.2.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.2.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.2.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.2.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.2.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.2.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.2.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.2.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.2.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.2.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.2.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.2.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.2.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.20.input_layernorm.weight": "model.safetensors", "language_model.layers.20.layer_scalar": "model.safetensors", "language_model.layers.20.mlp.down_proj.biases": "model.safetensors", "language_model.layers.20.mlp.down_proj.scales": "model.safetensors", "language_model.layers.20.mlp.down_proj.weight": "model.safetensors", "language_model.layers.20.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.20.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.20.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.20.mlp.up_proj.biases": "model.safetensors", "language_model.layers.20.mlp.up_proj.scales": "model.safetensors", "language_model.layers.20.mlp.up_proj.weight": "model.safetensors", "language_model.layers.20.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.20.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.20.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.20.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.20.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.20.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.20.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.20.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.20.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.20.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.20.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.20.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.20.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.20.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.20.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.20.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.20.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.20.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.20.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.20.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.20.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.20.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.20.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.20.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.21.input_layernorm.weight": "model.safetensors", "language_model.layers.21.layer_scalar": "model.safetensors", "language_model.layers.21.mlp.down_proj.biases": "model.safetensors", "language_model.layers.21.mlp.down_proj.scales": "model.safetensors", "language_model.layers.21.mlp.down_proj.weight": "model.safetensors", "language_model.layers.21.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.21.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.21.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.21.mlp.up_proj.biases": "model.safetensors", "language_model.layers.21.mlp.up_proj.scales": "model.safetensors", "language_model.layers.21.mlp.up_proj.weight": "model.safetensors", "language_model.layers.21.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.21.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.21.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.21.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.21.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.21.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.21.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.21.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.21.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.21.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.21.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.21.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.21.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.21.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.21.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.21.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.21.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.21.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.21.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.21.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.21.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.21.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.21.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.21.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.22.input_layernorm.weight": "model.safetensors", "language_model.layers.22.layer_scalar": "model.safetensors", "language_model.layers.22.mlp.down_proj.biases": "model.safetensors", "language_model.layers.22.mlp.down_proj.scales": "model.safetensors", "language_model.layers.22.mlp.down_proj.weight": "model.safetensors", "language_model.layers.22.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.22.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.22.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.22.mlp.up_proj.biases": "model.safetensors", "language_model.layers.22.mlp.up_proj.scales": "model.safetensors", "language_model.layers.22.mlp.up_proj.weight": "model.safetensors", "language_model.layers.22.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.22.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.22.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.22.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.22.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.22.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.22.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.22.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.22.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.22.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.22.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.22.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.22.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.22.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.22.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.22.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.22.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.22.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.22.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.22.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.22.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.22.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.22.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.22.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.23.input_layernorm.weight": "model.safetensors", "language_model.layers.23.layer_scalar": "model.safetensors", "language_model.layers.23.mlp.down_proj.biases": "model.safetensors", "language_model.layers.23.mlp.down_proj.scales": "model.safetensors", "language_model.layers.23.mlp.down_proj.weight": "model.safetensors", "language_model.layers.23.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.23.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.23.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.23.mlp.up_proj.biases": "model.safetensors", "language_model.layers.23.mlp.up_proj.scales": "model.safetensors", "language_model.layers.23.mlp.up_proj.weight": "model.safetensors", "language_model.layers.23.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.23.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.23.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.23.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.23.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.23.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.23.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.23.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.23.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.23.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.23.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.23.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.23.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.23.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.23.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.23.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.23.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.23.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.23.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.23.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.23.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.23.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.23.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.23.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.3.input_layernorm.weight": "model.safetensors", "language_model.layers.3.layer_scalar": "model.safetensors", "language_model.layers.3.mlp.down_proj.biases": "model.safetensors", "language_model.layers.3.mlp.down_proj.scales": "model.safetensors", "language_model.layers.3.mlp.down_proj.weight": "model.safetensors", "language_model.layers.3.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.3.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.3.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.3.mlp.up_proj.biases": "model.safetensors", "language_model.layers.3.mlp.up_proj.scales": "model.safetensors", "language_model.layers.3.mlp.up_proj.weight": "model.safetensors", "language_model.layers.3.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.3.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.3.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.3.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.3.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.3.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.3.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.3.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.3.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.3.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.3.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.3.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.3.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.3.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.3.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.3.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.3.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.3.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.3.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.3.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.3.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.3.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.3.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.3.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.4.input_layernorm.weight": "model.safetensors", "language_model.layers.4.layer_scalar": "model.safetensors", "language_model.layers.4.mlp.down_proj.biases": "model.safetensors", "language_model.layers.4.mlp.down_proj.scales": "model.safetensors", "language_model.layers.4.mlp.down_proj.weight": "model.safetensors", "language_model.layers.4.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.4.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.4.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.4.mlp.up_proj.biases": "model.safetensors", "language_model.layers.4.mlp.up_proj.scales": "model.safetensors", "language_model.layers.4.mlp.up_proj.weight": "model.safetensors", "language_model.layers.4.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.4.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.4.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.4.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.4.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.4.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.4.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.4.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.4.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.4.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.4.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.4.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.4.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.4.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.4.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.4.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.4.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.4.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.4.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.4.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.4.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.4.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.4.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.4.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.5.input_layernorm.weight": "model.safetensors", "language_model.layers.5.layer_scalar": "model.safetensors", "language_model.layers.5.mlp.down_proj.biases": "model.safetensors", "language_model.layers.5.mlp.down_proj.scales": "model.safetensors", "language_model.layers.5.mlp.down_proj.weight": "model.safetensors", "language_model.layers.5.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.5.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.5.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.5.mlp.up_proj.biases": "model.safetensors", "language_model.layers.5.mlp.up_proj.scales": "model.safetensors", "language_model.layers.5.mlp.up_proj.weight": "model.safetensors", "language_model.layers.5.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.5.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.5.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.5.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.5.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.5.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.5.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.5.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.5.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.5.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.5.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.5.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.5.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.5.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.5.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.5.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.5.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.5.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.5.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.5.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.5.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.5.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.5.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.5.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.6.input_layernorm.weight": "model.safetensors", "language_model.layers.6.layer_scalar": "model.safetensors", "language_model.layers.6.mlp.down_proj.biases": "model.safetensors", "language_model.layers.6.mlp.down_proj.scales": "model.safetensors", "language_model.layers.6.mlp.down_proj.weight": "model.safetensors", "language_model.layers.6.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.6.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.6.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.6.mlp.up_proj.biases": "model.safetensors", "language_model.layers.6.mlp.up_proj.scales": "model.safetensors", "language_model.layers.6.mlp.up_proj.weight": "model.safetensors", "language_model.layers.6.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.6.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.6.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.6.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.6.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.6.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.6.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.6.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.6.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.6.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.6.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.6.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.6.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.6.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.6.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.6.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.6.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.6.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.6.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.6.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.6.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.6.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.6.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.6.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.7.input_layernorm.weight": "model.safetensors", "language_model.layers.7.layer_scalar": "model.safetensors", "language_model.layers.7.mlp.down_proj.biases": "model.safetensors", "language_model.layers.7.mlp.down_proj.scales": "model.safetensors", "language_model.layers.7.mlp.down_proj.weight": "model.safetensors", "language_model.layers.7.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.7.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.7.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.7.mlp.up_proj.biases": "model.safetensors", "language_model.layers.7.mlp.up_proj.scales": "model.safetensors", "language_model.layers.7.mlp.up_proj.weight": "model.safetensors", "language_model.layers.7.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.7.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.7.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.7.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.7.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.7.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.7.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.7.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.7.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.7.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.7.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.7.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.7.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.7.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.7.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.7.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.7.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.7.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.7.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.7.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.7.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.7.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.7.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.7.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.8.input_layernorm.weight": "model.safetensors", "language_model.layers.8.layer_scalar": "model.safetensors", "language_model.layers.8.mlp.down_proj.biases": "model.safetensors", "language_model.layers.8.mlp.down_proj.scales": "model.safetensors", "language_model.layers.8.mlp.down_proj.weight": "model.safetensors", "language_model.layers.8.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.8.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.8.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.8.mlp.up_proj.biases": "model.safetensors", "language_model.layers.8.mlp.up_proj.scales": "model.safetensors", "language_model.layers.8.mlp.up_proj.weight": "model.safetensors", "language_model.layers.8.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.8.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.8.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.8.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.8.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.8.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.8.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.8.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.8.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.8.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.8.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.8.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.8.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.8.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.8.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.8.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.8.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.8.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.8.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.8.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.8.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.8.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.8.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.8.self_attn.v_proj.weight": "model.safetensors", "language_model.layers.9.input_layernorm.weight": "model.safetensors", "language_model.layers.9.layer_scalar": "model.safetensors", "language_model.layers.9.mlp.down_proj.biases": "model.safetensors", "language_model.layers.9.mlp.down_proj.scales": "model.safetensors", "language_model.layers.9.mlp.down_proj.weight": "model.safetensors", "language_model.layers.9.mlp.gate_proj.biases": "model.safetensors", "language_model.layers.9.mlp.gate_proj.scales": "model.safetensors", "language_model.layers.9.mlp.gate_proj.weight": "model.safetensors", "language_model.layers.9.mlp.up_proj.biases": "model.safetensors", "language_model.layers.9.mlp.up_proj.scales": "model.safetensors", "language_model.layers.9.mlp.up_proj.weight": "model.safetensors", "language_model.layers.9.ple_block.per_layer_input_gate.biases": "model.safetensors", "language_model.layers.9.ple_block.per_layer_input_gate.scales": "model.safetensors", "language_model.layers.9.ple_block.per_layer_input_gate.weight": "model.safetensors", "language_model.layers.9.ple_block.per_layer_projection.biases": "model.safetensors", "language_model.layers.9.ple_block.per_layer_projection.scales": "model.safetensors", "language_model.layers.9.ple_block.per_layer_projection.weight": "model.safetensors", "language_model.layers.9.ple_block.post_per_layer_input_norm.weight": "model.safetensors", "language_model.layers.9.post_attention_layernorm.weight": "model.safetensors", "language_model.layers.9.post_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.9.pre_feedforward_layernorm.weight": "model.safetensors", "language_model.layers.9.self_attn.k_norm.weight": "model.safetensors", "language_model.layers.9.self_attn.k_proj.biases": "model.safetensors", "language_model.layers.9.self_attn.k_proj.scales": "model.safetensors", "language_model.layers.9.self_attn.k_proj.weight": "model.safetensors", "language_model.layers.9.self_attn.o_proj.biases": "model.safetensors", "language_model.layers.9.self_attn.o_proj.scales": "model.safetensors", "language_model.layers.9.self_attn.o_proj.weight": "model.safetensors", "language_model.layers.9.self_attn.q_norm.weight": "model.safetensors", "language_model.layers.9.self_attn.q_proj.biases": "model.safetensors", "language_model.layers.9.self_attn.q_proj.scales": "model.safetensors", "language_model.layers.9.self_attn.q_proj.weight": "model.safetensors", "language_model.layers.9.self_attn.v_proj.biases": "model.safetensors", "language_model.layers.9.self_attn.v_proj.scales": "model.safetensors", "language_model.layers.9.self_attn.v_proj.weight": "model.safetensors", "language_model.norm.weight": "model.safetensors", "language_model.ple.per_layer_model_projection.biases": "model.safetensors", "language_model.ple.per_layer_model_projection.scales": "model.safetensors", "language_model.ple.per_layer_model_projection.weight": "model.safetensors", "language_model.ple.per_layer_projection_norm.weight": "model.safetensors", "vision_tower.encoder.layers.0.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.0.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.0.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.0.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.0.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.0.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.0.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.0.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.0.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.0.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.0.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.0.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.0.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.1.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.1.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.1.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.1.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.1.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.1.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.1.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.1.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.1.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.1.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.1.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.1.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.1.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.10.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.10.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.10.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.10.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.10.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.10.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.10.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.10.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.10.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.10.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.10.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.10.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.10.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.11.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.11.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.11.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.11.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.11.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.11.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.11.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.11.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.11.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.11.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.11.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.11.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.11.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.12.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.12.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.12.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.12.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.12.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.12.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.12.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.12.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.12.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.12.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.12.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.12.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.12.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.13.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.13.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.13.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.13.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.13.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.13.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.13.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.13.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.13.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.13.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.13.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.13.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.13.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.14.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.14.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.14.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.14.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.14.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.14.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.14.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.14.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.14.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.14.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.14.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.14.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.14.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.15.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.15.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.15.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.15.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.15.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.15.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.15.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.15.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.15.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.15.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.15.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.15.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.15.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.2.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.2.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.2.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.2.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.2.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.2.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.2.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.2.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.2.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.2.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.2.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.2.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.2.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.3.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.3.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.3.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.3.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.3.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.3.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.3.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.3.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.3.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.3.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.3.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.3.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.3.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.4.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.4.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.4.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.4.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.4.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.4.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.4.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.4.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.4.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.4.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.4.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.4.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.4.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.5.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.5.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.5.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.5.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.5.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.5.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.5.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.5.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.5.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.5.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.5.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.5.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.5.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.6.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.6.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.6.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.6.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.6.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.6.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.6.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.6.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.6.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.6.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.6.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.6.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.6.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.7.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.7.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.7.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.7.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.7.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.7.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.7.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.7.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.7.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.7.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.7.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.7.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.7.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.8.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.8.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.8.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.8.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.8.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.8.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.8.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.8.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.8.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.8.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.8.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.8.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.8.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.9.input_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.9.mlp.down_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.9.mlp.gate_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.9.mlp.up_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.9.post_attention_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.9.post_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.9.pre_feedforward_layernorm.weight": "model.safetensors", "vision_tower.encoder.layers.9.self_attn.k_norm.weight": "model.safetensors", "vision_tower.encoder.layers.9.self_attn.k_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.9.self_attn.o_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.9.self_attn.q_norm.weight": "model.safetensors", "vision_tower.encoder.layers.9.self_attn.q_proj.linear.weight": "model.safetensors", "vision_tower.encoder.layers.9.self_attn.v_proj.linear.weight": "model.safetensors", "vision_tower.patch_embedder.input_proj.weight": "model.safetensors", "vision_tower.patch_embedder.position_embedding_table": "model.safetensors" } }