{ "metadata": { "total_parameters": 2750007840, "total_size": 5500015680 }, "weight_map": { "model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.final_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.0.gla.b_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.gla.k_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.0.gla.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.gla.o_norm.weight": "model-00001-of-00002.safetensors", "model.layers.0.gla.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.gla.q_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.0.gla.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.gla.v_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.0.gla.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.pre_ffn_layernorm.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.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.pre_ffn_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.pre_ffn_layernorm.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.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.pre_ffn_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.gla.b_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.gla.k_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.16.gla.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.gla.o_norm.weight": "model-00001-of-00002.safetensors", "model.layers.16.gla.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.gla.q_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.16.gla.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.gla.v_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.16.gla.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.pre_ffn_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.18.mamba.D": "model-00001-of-00002.safetensors", "model.layers.18.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.18.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.18.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.18.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.pre_ffn_layernorm.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.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.pre_ffn_layernorm.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.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.pre_ffn_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.24.gla.b_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.gla.k_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.24.gla.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.gla.o_norm.weight": "model-00001-of-00002.safetensors", "model.layers.24.gla.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.gla.q_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.24.gla.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.gla.v_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.24.gla.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.25.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.pre_ffn_layernorm.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.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.pre_ffn_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.28.gla.b_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.gla.k_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.28.gla.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.gla.o_norm.weight": "model-00001-of-00002.safetensors", "model.layers.28.gla.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.gla.q_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.28.gla.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.gla.v_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.28.gla.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.29.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.29.pre_ffn_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.pre_ffn_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.30.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.30.mamba.D": "model-00001-of-00002.safetensors", "model.layers.30.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.30.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.30.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.30.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.30.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.30.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.31.pre_ffn_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.32.gla.b_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.gla.k_conv1d.weight": "model-00002-of-00002.safetensors", "model.layers.32.gla.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.gla.o_norm.weight": "model-00002-of-00002.safetensors", "model.layers.32.gla.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.gla.q_conv1d.weight": "model-00002-of-00002.safetensors", "model.layers.32.gla.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.32.gla.v_conv1d.weight": "model-00002-of-00002.safetensors", "model.layers.32.gla.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.33.ffn.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.ffn.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.ffn.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.pre_ffn_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.34.mamba.A_log": "model-00002-of-00002.safetensors", "model.layers.34.mamba.D": "model-00002-of-00002.safetensors", "model.layers.34.mamba.conv1d.bias": "model-00002-of-00002.safetensors", "model.layers.34.mamba.conv1d.weight": "model-00002-of-00002.safetensors", "model.layers.34.mamba.dt_bias": "model-00002-of-00002.safetensors", "model.layers.34.mamba.in_proj.weight": "model-00002-of-00002.safetensors", "model.layers.34.mamba.norm.weight": "model-00002-of-00002.safetensors", "model.layers.34.mamba.out_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.ffn.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.ffn.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.ffn.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.pre_ffn_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.pre_ffn_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.mamba.A_log": "model-00001-of-00002.safetensors", "model.layers.6.mamba.D": "model-00001-of-00002.safetensors", "model.layers.6.mamba.conv1d.bias": "model-00001-of-00002.safetensors", "model.layers.6.mamba.conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.6.mamba.dt_bias": "model-00001-of-00002.safetensors", "model.layers.6.mamba.in_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mamba.norm.weight": "model-00001-of-00002.safetensors", "model.layers.6.mamba.out_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.pre_ffn_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.gla.b_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.gla.k_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.8.gla.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.gla.o_norm.weight": "model-00001-of-00002.safetensors", "model.layers.8.gla.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.gla.q_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.8.gla.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.gla.v_conv1d.weight": "model-00001-of-00002.safetensors", "model.layers.8.gla.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.ffn.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.ffn.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.ffn.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.pre_ffn_layernorm.weight": "model-00001-of-00002.safetensors", "model.memory_tokens": "model-00001-of-00002.safetensors" } }