{ "n_compressed": 136, "n_exact": 156, "n_from_original": 114, "n_total_keys": 814, "output_bytes": 1415555032, "output_mb": 1350.0, "compressed_modules": [ "model.layers.0.mamba.in_proj", "model.layers.0.mamba.out_proj", "model.layers.10.mamba.in_proj", "model.layers.10.mamba.out_proj", "model.layers.11.linear", "model.layers.11.mamba_decoder.mamba.in_proj", "model.layers.11.mamba_decoder.mamba.out_proj", "model.layers.12.mamba.in_proj", "model.layers.12.mamba.out_proj", "model.layers.13.mamba.in_proj", "model.layers.13.mamba.out_proj", "model.layers.14.mamba.in_proj", "model.layers.14.mamba.out_proj", "model.layers.15.mamba.in_proj", "model.layers.15.mamba.out_proj", "model.layers.16.mamba.in_proj", "model.layers.16.mamba.out_proj", "model.layers.17.linear", "model.layers.17.mamba_decoder.mamba.in_proj", "model.layers.17.mamba_decoder.mamba.out_proj", "model.layers.18.mamba.in_proj", "model.layers.18.mamba.out_proj", "model.layers.19.mamba.in_proj", "model.layers.19.mamba.out_proj", "model.layers.1.mamba.in_proj", "model.layers.1.mamba.out_proj", "model.layers.20.mamba.in_proj", "model.layers.20.mamba.out_proj", "model.layers.21.mamba.in_proj", "model.layers.21.mamba.out_proj", "model.layers.22.mamba.in_proj", "model.layers.22.mamba.out_proj", "model.layers.23.linear", "model.layers.23.mamba_decoder.mamba.in_proj", "model.layers.23.mamba_decoder.mamba.out_proj", "model.layers.24.mamba.in_proj", "model.layers.24.mamba.out_proj", "model.layers.25.mamba.in_proj", "model.layers.25.mamba.out_proj", "model.layers.26.mamba.in_proj", "model.layers.26.mamba.out_proj", "model.layers.27.mamba.in_proj", "model.layers.27.mamba.out_proj", "model.layers.28.mamba.in_proj", "model.layers.28.mamba.out_proj", "model.layers.29.linear", "model.layers.29.mamba_decoder.mamba.in_proj", "model.layers.29.mamba_decoder.mamba.out_proj", "model.layers.2.mamba.in_proj", "model.layers.2.mamba.out_proj", "model.layers.30.mamba.in_proj", "model.layers.30.mamba.out_proj", "model.layers.31.mamba.in_proj", "model.layers.31.mamba.out_proj", "model.layers.32.mamba.in_proj", "model.layers.32.mamba.out_proj", "model.layers.33.mamba.in_proj", "model.layers.33.mamba.out_proj", "model.layers.34.mamba.in_proj", "model.layers.34.mamba.out_proj", "model.layers.35.linear", "model.layers.35.mamba_decoder.mamba.in_proj", "model.layers.35.mamba_decoder.mamba.out_proj", "model.layers.36.mamba.in_proj", "model.layers.36.mamba.out_proj", "model.layers.37.mamba.in_proj", "model.layers.37.mamba.out_proj", "model.layers.3.mamba.in_proj", "model.layers.3.mamba.out_proj", "model.layers.4.mamba.in_proj", "model.layers.4.mamba.out_proj", "model.layers.5.linear", "model.layers.5.mamba_decoder.mamba.in_proj", "model.layers.5.mamba_decoder.mamba.out_proj", "model.layers.5.shared_transformer.feed_forward.down_proj", "model.layers.5.shared_transformer.feed_forward.gate_up_proj_adapter_list.0.0", "model.layers.5.shared_transformer.feed_forward.gate_up_proj_adapter_list.0.1", "model.layers.5.shared_transformer.feed_forward.gate_up_proj_adapter_list.1.0", "model.layers.5.shared_transformer.feed_forward.gate_up_proj_adapter_list.1.1", "model.layers.5.shared_transformer.feed_forward.gate_up_proj_adapter_list.2.0", "model.layers.5.shared_transformer.feed_forward.gate_up_proj_adapter_list.2.1", "model.layers.5.shared_transformer.feed_forward.gate_up_proj_adapter_list.3.0", "model.layers.5.shared_transformer.feed_forward.gate_up_proj_adapter_list.3.1", "model.layers.5.shared_transformer.feed_forward.gate_up_proj_adapter_list.4.0", "model.layers.5.shared_transformer.feed_forward.gate_up_proj_adapter_list.4.1", "model.layers.5.shared_transformer.feed_forward.gate_up_proj_adapter_list.5.0", "model.layers.5.shared_transformer.feed_forward.gate_up_proj_adapter_list.5.1", "model.layers.5.shared_transformer.feed_forward.gate_up_proj", "model.layers.5.shared_transformer.self_attn.k_proj", "model.layers.5.shared_transformer.self_attn.linear_k_adapter_list.0.0", "model.layers.5.shared_transformer.self_attn.linear_k_adapter_list.0.1", "model.layers.5.shared_transformer.self_attn.linear_k_adapter_list.1.0", "model.layers.5.shared_transformer.self_attn.linear_k_adapter_list.1.1", "model.layers.5.shared_transformer.self_attn.linear_k_adapter_list.2.0", "model.layers.5.shared_transformer.self_attn.linear_k_adapter_list.2.1", "model.layers.5.shared_transformer.self_attn.linear_k_adapter_list.3.0", "model.layers.5.shared_transformer.self_attn.linear_k_adapter_list.3.1", "model.layers.5.shared_transformer.self_attn.linear_k_adapter_list.4.0", "model.layers.5.shared_transformer.self_attn.linear_k_adapter_list.4.1", "model.layers.5.shared_transformer.self_attn.linear_k_adapter_list.5.0", "model.layers.5.shared_transformer.self_attn.linear_k_adapter_list.5.1", "model.layers.5.shared_transformer.self_attn.linear_q_adapter_list.0.0", "model.layers.5.shared_transformer.self_attn.linear_q_adapter_list.0.1", "model.layers.5.shared_transformer.self_attn.linear_q_adapter_list.1.0", "model.layers.5.shared_transformer.self_attn.linear_q_adapter_list.1.1", "model.layers.5.shared_transformer.self_attn.linear_q_adapter_list.2.0", "model.layers.5.shared_transformer.self_attn.linear_q_adapter_list.2.1", "model.layers.5.shared_transformer.self_attn.linear_q_adapter_list.3.0", "model.layers.5.shared_transformer.self_attn.linear_q_adapter_list.3.1", "model.layers.5.shared_transformer.self_attn.linear_q_adapter_list.4.0", "model.layers.5.shared_transformer.self_attn.linear_q_adapter_list.4.1", "model.layers.5.shared_transformer.self_attn.linear_q_adapter_list.5.0", "model.layers.5.shared_transformer.self_attn.linear_q_adapter_list.5.1", "model.layers.5.shared_transformer.self_attn.linear_v_adapter_list.0.0", "model.layers.5.shared_transformer.self_attn.linear_v_adapter_list.0.1", "model.layers.5.shared_transformer.self_attn.linear_v_adapter_list.1.0", "model.layers.5.shared_transformer.self_attn.linear_v_adapter_list.1.1", "model.layers.5.shared_transformer.self_attn.linear_v_adapter_list.2.0", "model.layers.5.shared_transformer.self_attn.linear_v_adapter_list.2.1", "model.layers.5.shared_transformer.self_attn.linear_v_adapter_list.3.0", "model.layers.5.shared_transformer.self_attn.linear_v_adapter_list.3.1", "model.layers.5.shared_transformer.self_attn.linear_v_adapter_list.4.0", "model.layers.5.shared_transformer.self_attn.linear_v_adapter_list.4.1", "model.layers.5.shared_transformer.self_attn.linear_v_adapter_list.5.0", "model.layers.5.shared_transformer.self_attn.linear_v_adapter_list.5.1", "model.layers.5.shared_transformer.self_attn.o_proj", "model.layers.5.shared_transformer.self_attn.q_proj", "model.layers.5.shared_transformer.self_attn.v_proj", "model.layers.6.mamba.in_proj", "model.layers.6.mamba.out_proj", "model.layers.7.mamba.in_proj", "model.layers.7.mamba.out_proj", "model.layers.8.mamba.in_proj", "model.layers.8.mamba.out_proj", "model.layers.9.mamba.in_proj", "model.layers.9.mamba.out_proj" ], "wall_time_s": 2.2, "output_dir": "/home/voidstr3m33/models/zamba2-1.2b-helix" }