{ "metadata": { "total_size": 5377513280 }, "weight_map": { "model.layers.6.shared_transformer.feed_forward.gate_up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.0.0.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.2.0.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.4.0.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.6.0.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.8.0.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.0.1.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.2.1.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.4.1.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.6.1.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.8.1.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.shared_transformer.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.feed_forward.gate_up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.1.0.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.3.0.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.5.0.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.7.0.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.1.1.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.3.1.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.5.1.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.7.1.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.shared_transformer.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.final_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.linear.weight": "model-00002-of-00002.safetensors", "model.layers.12.linear.weight": "model-00002-of-00002.safetensors", "model.layers.18.linear.weight": "model-00002-of-00002.safetensors", "model.layers.24.linear.weight": "model-00002-of-00002.safetensors", "model.layers.30.linear.weight": "model-00002-of-00002.safetensors", "model.layers.36.linear.weight": "model-00002-of-00002.safetensors", "model.layers.42.linear.weight": "model-00002-of-00002.safetensors", "model.layers.47.linear.weight": "model-00002-of-00002.safetensors", "model.layers.51.linear.weight": "model-00002-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.0.mamba.D": "model-00001-of-00002.safetensors", "model.layers.0.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.0.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.0.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.0.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.0.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.1.mamba.D": "model-00001-of-00002.safetensors", "model.layers.1.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.1.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.1.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.1.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.1.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.10.mamba.D": "model-00001-of-00002.safetensors", "model.layers.10.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.10.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.10.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.10.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.10.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.11.mamba.D": "model-00001-of-00002.safetensors", "model.layers.11.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.11.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.11.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.11.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.11.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.12.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors", "model.layers.12.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.12.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.12.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.12.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.12.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.13.mamba.D": "model-00001-of-00002.safetensors", "model.layers.13.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.13.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.13.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.13.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.13.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.14.mamba.D": "model-00001-of-00002.safetensors", "model.layers.14.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.14.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.14.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.14.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.14.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.15.mamba.D": "model-00001-of-00002.safetensors", "model.layers.15.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.15.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.15.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.15.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.15.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.16.mamba.D": "model-00001-of-00002.safetensors", "model.layers.16.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.16.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.16.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.16.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.16.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.17.mamba.D": "model-00001-of-00002.safetensors", "model.layers.17.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.17.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.17.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.17.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.17.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.18.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors", "model.layers.18.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.18.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.18.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.18.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.19.mamba.D": "model-00001-of-00002.safetensors", "model.layers.19.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.19.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.19.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.19.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.19.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.2.mamba.D": "model-00001-of-00002.safetensors", "model.layers.2.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.2.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.2.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.2.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.2.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.20.mamba.D": "model-00001-of-00002.safetensors", "model.layers.20.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.20.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.20.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.20.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.20.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.21.mamba.D": "model-00001-of-00002.safetensors", "model.layers.21.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.21.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.21.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.21.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.21.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.22.mamba.D": "model-00001-of-00002.safetensors", "model.layers.22.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.22.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.22.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.22.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.22.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.23.mamba.D": "model-00001-of-00002.safetensors", "model.layers.23.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.23.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.23.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.23.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.23.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.24.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.24.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors", "model.layers.24.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.24.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.24.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.24.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.24.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.25.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.25.mamba.D": "model-00001-of-00002.safetensors", "model.layers.25.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.25.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.25.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.25.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.25.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.26.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.26.mamba.D": "model-00001-of-00002.safetensors", "model.layers.26.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.26.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.26.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.26.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.26.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.27.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.27.mamba.D": "model-00001-of-00002.safetensors", "model.layers.27.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.27.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.27.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.27.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.27.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.28.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.28.mamba.D": "model-00001-of-00002.safetensors", "model.layers.28.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.28.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.28.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.28.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.28.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.29.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.29.mamba.D": "model-00001-of-00002.safetensors", "model.layers.29.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.29.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.29.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.29.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.29.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.3.mamba.D": "model-00001-of-00002.safetensors", "model.layers.3.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.3.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.3.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.3.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.3.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.30.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.30.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors", "model.layers.30.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.30.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.30.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.30.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.30.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.31.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.31.mamba.D": "model-00001-of-00002.safetensors", "model.layers.31.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.31.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.31.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.31.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.31.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.32.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.32.mamba.D": "model-00001-of-00002.safetensors", "model.layers.32.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.32.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.32.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.32.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.32.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.32.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.33.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.33.mamba.D": "model-00001-of-00002.safetensors", "model.layers.33.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.33.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.33.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.33.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.33.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.33.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.34.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.34.mamba.D": "model-00001-of-00002.safetensors", "model.layers.34.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.34.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.34.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.34.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.34.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.34.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.35.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.35.mamba.D": "model-00001-of-00002.safetensors", "model.layers.35.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.35.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.35.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.35.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.35.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.35.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.36.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.36.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.36.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors", "model.layers.36.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.36.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.36.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.36.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.36.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.36.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.37.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.37.mamba.D": "model-00001-of-00002.safetensors", "model.layers.37.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.37.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.37.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.37.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.37.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.37.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.38.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.38.mamba.D": "model-00001-of-00002.safetensors", "model.layers.38.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.38.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.38.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.38.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.38.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.38.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.39.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.39.mamba.D": "model-00001-of-00002.safetensors", "model.layers.39.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.39.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.39.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.39.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.39.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.39.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.4.mamba.D": "model-00001-of-00002.safetensors", "model.layers.4.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.4.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.4.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.4.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.4.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.40.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.40.mamba.D": "model-00001-of-00002.safetensors", "model.layers.40.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.40.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.40.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.40.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.40.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.40.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.41.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.41.mamba.D": "model-00001-of-00002.safetensors", "model.layers.41.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.41.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.41.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.41.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.41.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.41.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.42.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.42.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.42.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors", "model.layers.42.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.42.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.42.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.42.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.42.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.42.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.43.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.43.mamba.D": "model-00001-of-00002.safetensors", "model.layers.43.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.43.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.43.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.43.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.43.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.43.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.44.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.44.mamba.D": "model-00001-of-00002.safetensors", "model.layers.44.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.44.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.44.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.44.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.44.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.44.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.45.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.45.mamba.D": "model-00001-of-00002.safetensors", "model.layers.45.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.45.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.45.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.45.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.45.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.45.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.46.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.46.mamba.D": "model-00001-of-00002.safetensors", "model.layers.46.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.46.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.46.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.46.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.46.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.46.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.47.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.47.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.47.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors", "model.layers.47.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.47.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.47.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.47.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.47.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.47.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.48.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.48.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.48.mamba.D": "model-00001-of-00002.safetensors", "model.layers.48.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.48.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.48.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.48.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.48.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.48.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.49.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.49.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.49.mamba.D": "model-00001-of-00002.safetensors", "model.layers.49.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.49.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.49.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.49.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.49.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.49.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.5.mamba.D": "model-00001-of-00002.safetensors", "model.layers.5.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.5.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.5.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.5.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.5.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.50.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.50.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.50.mamba.D": "model-00001-of-00002.safetensors", "model.layers.50.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.50.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.50.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.50.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.50.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.50.mamba.out_proj.weight": "model-00002-of-00002.safetensors", "model.layers.51.mamba_decoder.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.51.mamba_decoder.mamba.A_log": "model-00002-of-00002.safetensors", "model.layers.51.mamba_decoder.mamba.D": "model-00002-of-00002.safetensors", "model.layers.51.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00002.safetensors", "model.layers.51.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00002.safetensors", "model.layers.51.mamba_decoder.mamba.dt_bias": "model-00002-of-00002.safetensors", "model.layers.51.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00002.safetensors", "model.layers.51.mamba_decoder.mamba.norm.weight": "model-00002-of-00002.safetensors", "model.layers.51.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00002.safetensors", "model.layers.52.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.52.mamba.A_log": "model-00002-of-00002.safetensors", "model.layers.52.mamba.D": "model-00002-of-00002.safetensors", "model.layers.52.mamba.conv1d.bias": "model-00002-of-00002.safetensors", "model.layers.52.mamba.conv1d.weight": "model-00002-of-00002.safetensors", "model.layers.52.mamba.dt_bias": "model-00002-of-00002.safetensors", "model.layers.52.mamba.in_proj.weight": "model-00002-of-00002.safetensors", "model.layers.52.mamba.norm.weight": "model-00002-of-00002.safetensors", "model.layers.52.mamba.out_proj.weight": "model-00002-of-00002.safetensors", "model.layers.53.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.53.mamba.A_log": "model-00002-of-00002.safetensors", "model.layers.53.mamba.D": "model-00002-of-00002.safetensors", "model.layers.53.mamba.conv1d.bias": "model-00002-of-00002.safetensors", "model.layers.53.mamba.conv1d.weight": "model-00002-of-00002.safetensors", "model.layers.53.mamba.dt_bias": "model-00002-of-00002.safetensors", "model.layers.53.mamba.in_proj.weight": "model-00002-of-00002.safetensors", "model.layers.53.mamba.norm.weight": "model-00002-of-00002.safetensors", "model.layers.53.mamba.out_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.6.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors", "model.layers.6.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.6.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.6.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.6.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.6.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.7.mamba.D": "model-00001-of-00002.safetensors", "model.layers.7.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.7.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.7.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.7.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.7.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.8.mamba.D": "model-00001-of-00002.safetensors", "model.layers.8.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.8.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.8.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.8.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.8.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.9.mamba.D": "model-00001-of-00002.safetensors", "model.layers.9.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.9.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.9.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.9.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.9.mamba.out_proj.weight": "model-00001-of-00002.safetensors" } }