{ "metadata": { "total_size": 14820847264 }, "weight_map": { "model.layers.6.shared_transformer.feed_forward.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.0.0.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.10.0.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.12.0.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.2.0.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.4.0.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.6.0.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.8.0.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.0.1.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.10.1.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.12.1.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.2.1.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.4.1.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.6.1.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.8.1.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.pre_ff_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.shared_transformer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.1.0.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.11.0.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.3.0.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.5.0.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.7.0.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.9.0.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.1.1.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.11.1.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.3.1.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.5.1.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.7.1.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.9.1.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.pre_ff_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.shared_transformer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.final_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.linear.weight": "model-00003-of-00003.safetensors", "model.layers.11.linear.weight": "model-00003-of-00003.safetensors", "model.layers.65.linear.weight": "model-00003-of-00003.safetensors", "model.layers.71.linear.weight": "model-00003-of-00003.safetensors", "model.layers.77.linear.weight": "model-00003-of-00003.safetensors", "model.layers.17.linear.weight": "model-00003-of-00003.safetensors", "model.layers.23.linear.weight": "model-00003-of-00003.safetensors", "model.layers.29.linear.weight": "model-00003-of-00003.safetensors", "model.layers.35.linear.weight": "model-00003-of-00003.safetensors", "model.layers.41.linear.weight": "model-00003-of-00003.safetensors", "model.layers.47.linear.weight": "model-00003-of-00003.safetensors", "model.layers.53.linear.weight": "model-00003-of-00003.safetensors", "model.layers.59.linear.weight": "model-00003-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.0.mamba.D": "model-00001-of-00003.safetensors", "model.layers.0.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.0.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.0.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.0.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.0.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.1.mamba.D": "model-00001-of-00003.safetensors", "model.layers.1.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.1.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.1.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.1.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.1.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.10.mamba.D": "model-00001-of-00003.safetensors", "model.layers.10.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.10.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.10.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.10.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.10.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mamba_decoder.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.mamba_decoder.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.11.mamba_decoder.mamba.D": "model-00001-of-00003.safetensors", "model.layers.11.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.11.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.11.mamba_decoder.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.11.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mamba_decoder.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.11.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.12.mamba.D": "model-00001-of-00003.safetensors", "model.layers.12.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.12.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.12.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.12.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.12.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.13.mamba.D": "model-00001-of-00003.safetensors", "model.layers.13.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.13.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.13.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.13.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.13.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.14.mamba.D": "model-00001-of-00003.safetensors", "model.layers.14.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.14.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.14.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.14.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.14.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.15.mamba.D": "model-00001-of-00003.safetensors", "model.layers.15.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.15.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.15.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.15.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.15.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.16.mamba.D": "model-00001-of-00003.safetensors", "model.layers.16.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.16.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.16.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.16.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.16.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mamba_decoder.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.mamba_decoder.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.17.mamba_decoder.mamba.D": "model-00001-of-00003.safetensors", "model.layers.17.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.17.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.17.mamba_decoder.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.17.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mamba_decoder.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.17.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.18.mamba.D": "model-00001-of-00003.safetensors", "model.layers.18.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.18.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.18.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.18.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.18.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.19.mamba.D": "model-00001-of-00003.safetensors", "model.layers.19.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.19.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.19.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.19.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.19.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.2.mamba.D": "model-00001-of-00003.safetensors", "model.layers.2.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.2.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.2.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.2.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.2.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.20.mamba.D": "model-00001-of-00003.safetensors", "model.layers.20.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.20.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.20.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.20.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.20.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.21.mamba.D": "model-00002-of-00003.safetensors", "model.layers.21.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.21.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.21.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.21.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.21.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.22.mamba.D": "model-00002-of-00003.safetensors", "model.layers.22.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.22.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.22.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.22.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.22.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.mamba_decoder.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.mamba_decoder.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.23.mamba_decoder.mamba.D": "model-00002-of-00003.safetensors", "model.layers.23.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.23.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.23.mamba_decoder.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.23.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.mamba_decoder.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.23.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.24.mamba.D": "model-00002-of-00003.safetensors", "model.layers.24.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.24.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.24.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.24.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.24.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.25.mamba.D": "model-00002-of-00003.safetensors", "model.layers.25.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.25.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.25.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.25.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.25.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.26.mamba.D": "model-00002-of-00003.safetensors", "model.layers.26.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.26.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.26.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.26.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.26.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.27.mamba.D": "model-00002-of-00003.safetensors", "model.layers.27.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.27.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.27.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.27.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.27.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.28.mamba.D": "model-00002-of-00003.safetensors", "model.layers.28.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.28.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.28.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.28.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.28.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mamba_decoder.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.mamba_decoder.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.29.mamba_decoder.mamba.D": "model-00002-of-00003.safetensors", "model.layers.29.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.29.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.29.mamba_decoder.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.29.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mamba_decoder.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.29.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.3.mamba.D": "model-00001-of-00003.safetensors", "model.layers.3.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.3.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.3.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.3.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.3.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.30.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.30.mamba.D": "model-00002-of-00003.safetensors", "model.layers.30.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.30.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.30.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.30.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.30.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.31.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.31.mamba.D": "model-00002-of-00003.safetensors", "model.layers.31.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.31.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.31.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.31.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.31.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.32.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.32.mamba.D": "model-00002-of-00003.safetensors", "model.layers.32.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.32.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.32.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.32.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.32.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.33.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.33.mamba.D": "model-00002-of-00003.safetensors", "model.layers.33.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.33.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.33.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.33.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.33.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.34.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.34.mamba.D": "model-00002-of-00003.safetensors", "model.layers.34.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.34.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.34.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.34.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.34.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.mamba_decoder.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.35.mamba_decoder.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.35.mamba_decoder.mamba.D": "model-00002-of-00003.safetensors", "model.layers.35.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.35.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.35.mamba_decoder.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.35.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.mamba_decoder.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.35.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.36.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.36.mamba.D": "model-00002-of-00003.safetensors", "model.layers.36.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.36.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.36.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.36.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.36.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.37.mamba.D": "model-00002-of-00003.safetensors", "model.layers.37.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.37.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.37.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.37.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.37.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.38.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.38.mamba.D": "model-00002-of-00003.safetensors", "model.layers.38.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.38.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.38.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.38.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.38.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.39.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.39.mamba.D": "model-00002-of-00003.safetensors", "model.layers.39.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.39.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.39.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.39.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.39.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.4.mamba.D": "model-00001-of-00003.safetensors", "model.layers.4.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.4.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.4.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.4.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.4.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.40.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.40.mamba.D": "model-00002-of-00003.safetensors", "model.layers.40.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.40.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.40.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.40.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.40.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.mamba_decoder.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.41.mamba_decoder.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.41.mamba_decoder.mamba.D": "model-00002-of-00003.safetensors", "model.layers.41.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.41.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.41.mamba_decoder.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.41.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.mamba_decoder.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.41.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.42.mamba.D": "model-00002-of-00003.safetensors", "model.layers.42.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.42.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.42.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.42.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.42.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.43.mamba.D": "model-00002-of-00003.safetensors", "model.layers.43.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.43.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.43.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.43.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.43.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.44.mamba.D": "model-00002-of-00003.safetensors", "model.layers.44.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.44.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.44.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.44.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.44.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.45.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.45.mamba.D": "model-00002-of-00003.safetensors", "model.layers.45.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.45.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.45.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.45.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.45.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.46.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.46.mamba.D": "model-00002-of-00003.safetensors", "model.layers.46.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.46.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.46.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.46.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.46.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.mamba_decoder.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.47.mamba_decoder.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.47.mamba_decoder.mamba.D": "model-00002-of-00003.safetensors", "model.layers.47.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.47.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.47.mamba_decoder.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.47.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.mamba_decoder.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.47.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.48.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.48.mamba.D": "model-00002-of-00003.safetensors", "model.layers.48.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.48.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.48.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.48.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.48.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.49.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.49.mamba.D": "model-00002-of-00003.safetensors", "model.layers.49.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.49.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.49.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.49.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.49.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.5.mamba.D": "model-00001-of-00003.safetensors", "model.layers.5.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.5.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.5.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.5.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.5.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.50.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.50.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.50.mamba.D": "model-00002-of-00003.safetensors", "model.layers.50.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.50.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.50.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.50.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.50.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.50.mamba.out_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.51.mamba.A_log": "model-00002-of-00003.safetensors", "model.layers.51.mamba.D": "model-00002-of-00003.safetensors", "model.layers.51.mamba.conv1d.bias": "model-00002-of-00003.safetensors", "model.layers.51.mamba.conv1d.weight": "model-00002-of-00003.safetensors", "model.layers.51.mamba.dt_bias": "model-00002-of-00003.safetensors", "model.layers.51.mamba.in_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.mamba.norm.weight": "model-00002-of-00003.safetensors", "model.layers.51.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.52.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.52.mamba.D": "model-00003-of-00003.safetensors", "model.layers.52.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.52.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.52.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.52.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.52.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.52.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.53.mamba_decoder.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.53.mamba_decoder.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.53.mamba_decoder.mamba.D": "model-00003-of-00003.safetensors", "model.layers.53.mamba_decoder.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.53.mamba_decoder.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.53.mamba_decoder.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.53.mamba_decoder.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.53.mamba_decoder.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.53.mamba_decoder.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.54.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.54.mamba.D": "model-00003-of-00003.safetensors", "model.layers.54.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.54.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.54.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.54.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.54.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.54.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.55.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.55.mamba.D": "model-00003-of-00003.safetensors", "model.layers.55.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.55.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.55.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.55.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.55.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.56.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.56.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.56.mamba.D": "model-00003-of-00003.safetensors", "model.layers.56.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.56.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.56.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.56.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.56.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.56.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.57.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.57.mamba.D": "model-00003-of-00003.safetensors", "model.layers.57.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.57.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.57.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.57.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.57.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.58.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.58.mamba.D": "model-00003-of-00003.safetensors", "model.layers.58.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.58.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.58.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.58.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.58.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.mamba_decoder.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.59.mamba_decoder.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.59.mamba_decoder.mamba.D": "model-00003-of-00003.safetensors", "model.layers.59.mamba_decoder.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.59.mamba_decoder.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.59.mamba_decoder.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.59.mamba_decoder.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.mamba_decoder.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.59.mamba_decoder.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.mamba_decoder.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.mamba_decoder.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.6.mamba_decoder.mamba.D": "model-00001-of-00003.safetensors", "model.layers.6.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.6.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.6.mamba_decoder.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.6.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mamba_decoder.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.6.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.60.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.60.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.60.mamba.D": "model-00003-of-00003.safetensors", "model.layers.60.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.60.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.60.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.60.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.60.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.60.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.61.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.61.mamba.D": "model-00003-of-00003.safetensors", "model.layers.61.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.61.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.61.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.61.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.61.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.62.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.62.mamba.D": "model-00003-of-00003.safetensors", "model.layers.62.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.62.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.62.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.62.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.62.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.62.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.63.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.63.mamba.D": "model-00003-of-00003.safetensors", "model.layers.63.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.63.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.63.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.63.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.63.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.63.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.64.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.64.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.64.mamba.D": "model-00003-of-00003.safetensors", "model.layers.64.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.64.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.64.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.64.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.64.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.64.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.65.mamba_decoder.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.65.mamba_decoder.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.65.mamba_decoder.mamba.D": "model-00003-of-00003.safetensors", "model.layers.65.mamba_decoder.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.65.mamba_decoder.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.65.mamba_decoder.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.65.mamba_decoder.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.65.mamba_decoder.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.65.mamba_decoder.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.66.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.66.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.66.mamba.D": "model-00003-of-00003.safetensors", "model.layers.66.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.66.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.66.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.66.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.66.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.66.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.67.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.67.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.67.mamba.D": "model-00003-of-00003.safetensors", "model.layers.67.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.67.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.67.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.67.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.67.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.67.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.68.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.68.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.68.mamba.D": "model-00003-of-00003.safetensors", "model.layers.68.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.68.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.68.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.68.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.68.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.68.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.69.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.69.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.69.mamba.D": "model-00003-of-00003.safetensors", "model.layers.69.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.69.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.69.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.69.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.69.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.69.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.7.mamba.D": "model-00001-of-00003.safetensors", "model.layers.7.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.7.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.7.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.7.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.7.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.70.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.70.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.70.mamba.D": "model-00003-of-00003.safetensors", "model.layers.70.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.70.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.70.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.70.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.70.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.70.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.71.mamba_decoder.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.71.mamba_decoder.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.71.mamba_decoder.mamba.D": "model-00003-of-00003.safetensors", "model.layers.71.mamba_decoder.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.71.mamba_decoder.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.71.mamba_decoder.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.71.mamba_decoder.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.71.mamba_decoder.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.71.mamba_decoder.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.72.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.72.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.72.mamba.D": "model-00003-of-00003.safetensors", "model.layers.72.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.72.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.72.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.72.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.72.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.72.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.73.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.73.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.73.mamba.D": "model-00003-of-00003.safetensors", "model.layers.73.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.73.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.73.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.73.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.73.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.73.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.74.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.74.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.74.mamba.D": "model-00003-of-00003.safetensors", "model.layers.74.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.74.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.74.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.74.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.74.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.74.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.75.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.75.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.75.mamba.D": "model-00003-of-00003.safetensors", "model.layers.75.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.75.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.75.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.75.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.75.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.75.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.76.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.76.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.76.mamba.D": "model-00003-of-00003.safetensors", "model.layers.76.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.76.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.76.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.76.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.76.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.76.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.77.mamba_decoder.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.77.mamba_decoder.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.77.mamba_decoder.mamba.D": "model-00003-of-00003.safetensors", "model.layers.77.mamba_decoder.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.77.mamba_decoder.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.77.mamba_decoder.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.77.mamba_decoder.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.77.mamba_decoder.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.77.mamba_decoder.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.78.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.78.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.78.mamba.D": "model-00003-of-00003.safetensors", "model.layers.78.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.78.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.78.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.78.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.78.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.78.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.79.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.79.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.79.mamba.D": "model-00003-of-00003.safetensors", "model.layers.79.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.79.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.79.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.79.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.79.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.79.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.8.mamba.D": "model-00001-of-00003.safetensors", "model.layers.8.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.8.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.8.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.8.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.8.mamba.out_proj.weight": "model-00001-of-00003.safetensors", "model.layers.80.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.80.mamba.A_log": "model-00003-of-00003.safetensors", "model.layers.80.mamba.D": "model-00003-of-00003.safetensors", "model.layers.80.mamba.conv1d.bias": "model-00003-of-00003.safetensors", "model.layers.80.mamba.conv1d.weight": "model-00003-of-00003.safetensors", "model.layers.80.mamba.dt_bias": "model-00003-of-00003.safetensors", "model.layers.80.mamba.in_proj.weight": "model-00003-of-00003.safetensors", "model.layers.80.mamba.norm.weight": "model-00003-of-00003.safetensors", "model.layers.80.mamba.out_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.mamba.A_log": "model-00001-of-00003.safetensors", "model.layers.9.mamba.D": "model-00001-of-00003.safetensors", "model.layers.9.mamba.conv1d.bias": "model-00001-of-00003.safetensors", "model.layers.9.mamba.conv1d.weight": "model-00001-of-00003.safetensors", "model.layers.9.mamba.dt_bias": "model-00001-of-00003.safetensors", "model.layers.9.mamba.in_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mamba.norm.weight": "model-00001-of-00003.safetensors", "model.layers.9.mamba.out_proj.weight": "model-00001-of-00003.safetensors" } }