{ "metadata": { "total_size": 68000765952, "total_parameters": 120668692480 }, "weight_map": { "backbone.embeddings.biases": "model-00001-of-00007.safetensors", "backbone.embeddings.scales": "model-00001-of-00007.safetensors", "backbone.embeddings.weight": "model-00001-of-00007.safetensors", "backbone.layers.0.mixer.A_log": "model-00001-of-00007.safetensors", "backbone.layers.0.mixer.D": "model-00001-of-00007.safetensors", "backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00007.safetensors", "backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "backbone.layers.0.mixer.dt_bias": "model-00001-of-00007.safetensors", "backbone.layers.0.mixer.in_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.0.mixer.in_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.0.mixer.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.0.mixer.out_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.0.mixer.out_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.0.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.fc1_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.fc1_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.fc1_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.fc2_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.fc2_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.fc2_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.gate.e_score_correction_bias": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.gate.weight": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.switch_mlp.fc1.biases": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.switch_mlp.fc1.scales": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.switch_mlp.fc1.weight": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.switch_mlp.fc2.biases": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.switch_mlp.fc2.scales": "model-00001-of-00007.safetensors", "backbone.layers.1.mixer.switch_mlp.fc2.weight": "model-00001-of-00007.safetensors", "backbone.layers.1.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.fc1_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.fc1_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.fc1_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.fc2_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.fc2_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.fc2_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.gate.e_score_correction_bias": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.gate.weight": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.switch_mlp.fc1.biases": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.switch_mlp.fc1.scales": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.switch_mlp.fc1.weight": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.switch_mlp.fc2.biases": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.switch_mlp.fc2.scales": "model-00001-of-00007.safetensors", "backbone.layers.10.mixer.switch_mlp.fc2.weight": "model-00001-of-00007.safetensors", "backbone.layers.10.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.11.mixer.A_log": "model-00001-of-00007.safetensors", "backbone.layers.11.mixer.D": "model-00001-of-00007.safetensors", "backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00007.safetensors", "backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "backbone.layers.11.mixer.dt_bias": "model-00001-of-00007.safetensors", "backbone.layers.11.mixer.in_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.11.mixer.in_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.11.mixer.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.11.mixer.out_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.11.mixer.out_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.11.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.fc1_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.fc1_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.fc1_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.fc2_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.fc2_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.fc2_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.gate.e_score_correction_bias": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.gate.weight": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.switch_mlp.fc1.biases": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.switch_mlp.fc1.scales": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.switch_mlp.fc1.weight": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.switch_mlp.fc2.biases": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.switch_mlp.fc2.scales": "model-00001-of-00007.safetensors", "backbone.layers.12.mixer.switch_mlp.fc2.weight": "model-00001-of-00007.safetensors", "backbone.layers.12.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.13.mixer.A_log": "model-00001-of-00007.safetensors", "backbone.layers.13.mixer.D": "model-00001-of-00007.safetensors", "backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00007.safetensors", "backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "backbone.layers.13.mixer.dt_bias": "model-00001-of-00007.safetensors", "backbone.layers.13.mixer.in_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.13.mixer.in_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.13.mixer.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.13.mixer.out_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.13.mixer.out_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.13.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.14.mixer.fc1_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.14.mixer.fc1_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.14.mixer.fc1_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.14.mixer.fc2_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.14.mixer.fc2_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.14.mixer.fc2_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.14.mixer.gate.e_score_correction_bias": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.gate.weight": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.switch_mlp.fc1.biases": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.switch_mlp.fc1.scales": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.switch_mlp.fc1.weight": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.switch_mlp.fc2.biases": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.switch_mlp.fc2.scales": "model-00002-of-00007.safetensors", "backbone.layers.14.mixer.switch_mlp.fc2.weight": "model-00002-of-00007.safetensors", "backbone.layers.14.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.15.mixer.A_log": "model-00002-of-00007.safetensors", "backbone.layers.15.mixer.D": "model-00002-of-00007.safetensors", "backbone.layers.15.mixer.conv1d.bias": "model-00002-of-00007.safetensors", "backbone.layers.15.mixer.conv1d.weight": "model-00002-of-00007.safetensors", "backbone.layers.15.mixer.dt_bias": "model-00002-of-00007.safetensors", "backbone.layers.15.mixer.in_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.15.mixer.in_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.15.mixer.in_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.15.mixer.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.15.mixer.out_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.15.mixer.out_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.15.mixer.out_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.15.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.16.mixer.k_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.16.mixer.k_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.16.mixer.k_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.16.mixer.o_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.16.mixer.o_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.16.mixer.o_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.16.mixer.q_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.16.mixer.q_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.16.mixer.q_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.16.mixer.v_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.16.mixer.v_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.16.mixer.v_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.16.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.fc1_latent_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.fc1_latent_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.fc1_latent_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.fc2_latent_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.fc2_latent_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.fc2_latent_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.gate.e_score_correction_bias": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.gate.weight": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.switch_mlp.fc1.biases": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.switch_mlp.fc1.scales": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.switch_mlp.fc1.weight": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.switch_mlp.fc2.biases": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.switch_mlp.fc2.scales": "model-00002-of-00007.safetensors", "backbone.layers.17.mixer.switch_mlp.fc2.weight": "model-00002-of-00007.safetensors", "backbone.layers.17.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.18.mixer.A_log": "model-00002-of-00007.safetensors", "backbone.layers.18.mixer.D": "model-00002-of-00007.safetensors", "backbone.layers.18.mixer.conv1d.bias": "model-00002-of-00007.safetensors", "backbone.layers.18.mixer.conv1d.weight": "model-00002-of-00007.safetensors", "backbone.layers.18.mixer.dt_bias": "model-00002-of-00007.safetensors", "backbone.layers.18.mixer.in_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.18.mixer.in_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.18.mixer.in_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.18.mixer.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.18.mixer.out_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.18.mixer.out_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.18.mixer.out_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.18.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.fc1_latent_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.fc1_latent_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.fc1_latent_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.fc2_latent_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.fc2_latent_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.fc2_latent_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.gate.e_score_correction_bias": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.gate.weight": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.switch_mlp.fc1.biases": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.switch_mlp.fc1.scales": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.switch_mlp.fc1.weight": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.switch_mlp.fc2.biases": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.switch_mlp.fc2.scales": "model-00002-of-00007.safetensors", "backbone.layers.19.mixer.switch_mlp.fc2.weight": "model-00002-of-00007.safetensors", "backbone.layers.19.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.2.mixer.A_log": "model-00001-of-00007.safetensors", "backbone.layers.2.mixer.D": "model-00001-of-00007.safetensors", "backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00007.safetensors", "backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "backbone.layers.2.mixer.dt_bias": "model-00001-of-00007.safetensors", "backbone.layers.2.mixer.in_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.2.mixer.in_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.2.mixer.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.2.mixer.out_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.2.mixer.out_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.2.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.20.mixer.A_log": "model-00002-of-00007.safetensors", "backbone.layers.20.mixer.D": "model-00002-of-00007.safetensors", "backbone.layers.20.mixer.conv1d.bias": "model-00002-of-00007.safetensors", "backbone.layers.20.mixer.conv1d.weight": "model-00002-of-00007.safetensors", "backbone.layers.20.mixer.dt_bias": "model-00002-of-00007.safetensors", "backbone.layers.20.mixer.in_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.20.mixer.in_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.20.mixer.in_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.20.mixer.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.20.mixer.out_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.20.mixer.out_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.20.mixer.out_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.20.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.fc1_latent_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.fc1_latent_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.fc1_latent_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.fc2_latent_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.fc2_latent_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.fc2_latent_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.gate.e_score_correction_bias": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.gate.weight": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.switch_mlp.fc1.biases": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.switch_mlp.fc1.scales": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.switch_mlp.fc1.weight": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.switch_mlp.fc2.biases": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.switch_mlp.fc2.scales": "model-00002-of-00007.safetensors", "backbone.layers.21.mixer.switch_mlp.fc2.weight": "model-00002-of-00007.safetensors", "backbone.layers.21.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.22.mixer.A_log": "model-00002-of-00007.safetensors", "backbone.layers.22.mixer.D": "model-00002-of-00007.safetensors", "backbone.layers.22.mixer.conv1d.bias": "model-00002-of-00007.safetensors", "backbone.layers.22.mixer.conv1d.weight": "model-00002-of-00007.safetensors", "backbone.layers.22.mixer.dt_bias": "model-00002-of-00007.safetensors", "backbone.layers.22.mixer.in_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.22.mixer.in_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.22.mixer.in_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.22.mixer.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.22.mixer.out_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.22.mixer.out_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.22.mixer.out_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.22.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.fc1_latent_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.fc1_latent_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.fc1_latent_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.fc2_latent_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.fc2_latent_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.fc2_latent_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.gate.e_score_correction_bias": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.gate.weight": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.switch_mlp.fc1.biases": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.switch_mlp.fc1.scales": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.switch_mlp.fc1.weight": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.switch_mlp.fc2.biases": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.switch_mlp.fc2.scales": "model-00002-of-00007.safetensors", "backbone.layers.23.mixer.switch_mlp.fc2.weight": "model-00002-of-00007.safetensors", "backbone.layers.23.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.24.mixer.A_log": "model-00002-of-00007.safetensors", "backbone.layers.24.mixer.D": "model-00002-of-00007.safetensors", "backbone.layers.24.mixer.conv1d.bias": "model-00002-of-00007.safetensors", "backbone.layers.24.mixer.conv1d.weight": "model-00002-of-00007.safetensors", "backbone.layers.24.mixer.dt_bias": "model-00002-of-00007.safetensors", "backbone.layers.24.mixer.in_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.24.mixer.in_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.24.mixer.in_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.24.mixer.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.24.mixer.out_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.24.mixer.out_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.24.mixer.out_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.24.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.25.mixer.k_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.25.mixer.k_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.25.mixer.k_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.25.mixer.o_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.25.mixer.o_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.25.mixer.o_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.25.mixer.q_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.25.mixer.q_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.25.mixer.q_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.25.mixer.v_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.25.mixer.v_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.25.mixer.v_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.25.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.fc1_latent_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.fc1_latent_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.fc1_latent_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.fc2_latent_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.fc2_latent_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.fc2_latent_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.gate.e_score_correction_bias": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.gate.weight": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.switch_mlp.fc1.biases": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.switch_mlp.fc1.scales": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.switch_mlp.fc1.weight": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.switch_mlp.fc2.biases": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.switch_mlp.fc2.scales": "model-00002-of-00007.safetensors", "backbone.layers.26.mixer.switch_mlp.fc2.weight": "model-00002-of-00007.safetensors", "backbone.layers.26.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.27.mixer.A_log": "model-00002-of-00007.safetensors", "backbone.layers.27.mixer.D": "model-00002-of-00007.safetensors", "backbone.layers.27.mixer.conv1d.bias": "model-00002-of-00007.safetensors", "backbone.layers.27.mixer.conv1d.weight": "model-00002-of-00007.safetensors", "backbone.layers.27.mixer.dt_bias": "model-00002-of-00007.safetensors", "backbone.layers.27.mixer.in_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.27.mixer.in_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.27.mixer.in_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.27.mixer.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.27.mixer.out_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.27.mixer.out_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.27.mixer.out_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.27.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.28.mixer.fc1_latent_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.28.mixer.fc1_latent_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.28.mixer.fc1_latent_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.28.mixer.fc2_latent_proj.biases": "model-00002-of-00007.safetensors", "backbone.layers.28.mixer.fc2_latent_proj.scales": "model-00002-of-00007.safetensors", "backbone.layers.28.mixer.fc2_latent_proj.weight": "model-00002-of-00007.safetensors", "backbone.layers.28.mixer.gate.e_score_correction_bias": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.gate.weight": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.switch_mlp.fc1.biases": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.switch_mlp.fc1.scales": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.switch_mlp.fc1.weight": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.switch_mlp.fc2.biases": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.switch_mlp.fc2.scales": "model-00003-of-00007.safetensors", "backbone.layers.28.mixer.switch_mlp.fc2.weight": "model-00003-of-00007.safetensors", "backbone.layers.28.norm.weight": "model-00002-of-00007.safetensors", "backbone.layers.29.mixer.A_log": "model-00003-of-00007.safetensors", "backbone.layers.29.mixer.D": "model-00003-of-00007.safetensors", "backbone.layers.29.mixer.conv1d.bias": "model-00003-of-00007.safetensors", "backbone.layers.29.mixer.conv1d.weight": "model-00003-of-00007.safetensors", "backbone.layers.29.mixer.dt_bias": "model-00003-of-00007.safetensors", "backbone.layers.29.mixer.in_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.29.mixer.in_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.29.mixer.in_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.29.mixer.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.29.mixer.out_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.29.mixer.out_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.29.mixer.out_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.29.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.3.mixer.fc1_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.fc1_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.fc1_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.fc2_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.fc2_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.fc2_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.gate.e_score_correction_bias": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.gate.weight": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.switch_mlp.fc1.biases": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.switch_mlp.fc1.scales": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.switch_mlp.fc1.weight": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.switch_mlp.fc2.biases": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.switch_mlp.fc2.scales": "model-00001-of-00007.safetensors", "backbone.layers.3.mixer.switch_mlp.fc2.weight": "model-00001-of-00007.safetensors", "backbone.layers.3.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.30.mixer.fc1_latent_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.fc1_latent_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.fc1_latent_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.fc2_latent_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.fc2_latent_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.fc2_latent_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.gate.e_score_correction_bias": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.gate.weight": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.switch_mlp.fc1.biases": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.switch_mlp.fc1.scales": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.switch_mlp.fc1.weight": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.switch_mlp.fc2.biases": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.switch_mlp.fc2.scales": "model-00003-of-00007.safetensors", "backbone.layers.30.mixer.switch_mlp.fc2.weight": "model-00003-of-00007.safetensors", "backbone.layers.30.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.31.mixer.A_log": "model-00003-of-00007.safetensors", "backbone.layers.31.mixer.D": "model-00003-of-00007.safetensors", "backbone.layers.31.mixer.conv1d.bias": "model-00003-of-00007.safetensors", "backbone.layers.31.mixer.conv1d.weight": "model-00003-of-00007.safetensors", "backbone.layers.31.mixer.dt_bias": "model-00003-of-00007.safetensors", "backbone.layers.31.mixer.in_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.31.mixer.in_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.31.mixer.in_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.31.mixer.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.31.mixer.out_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.31.mixer.out_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.31.mixer.out_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.31.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.fc1_latent_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.fc1_latent_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.fc1_latent_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.fc2_latent_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.fc2_latent_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.fc2_latent_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.gate.e_score_correction_bias": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.gate.weight": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.switch_mlp.fc1.biases": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.switch_mlp.fc1.scales": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.switch_mlp.fc1.weight": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.switch_mlp.fc2.biases": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.switch_mlp.fc2.scales": "model-00003-of-00007.safetensors", "backbone.layers.32.mixer.switch_mlp.fc2.weight": "model-00003-of-00007.safetensors", "backbone.layers.32.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.33.mixer.A_log": "model-00003-of-00007.safetensors", "backbone.layers.33.mixer.D": "model-00003-of-00007.safetensors", "backbone.layers.33.mixer.conv1d.bias": "model-00003-of-00007.safetensors", "backbone.layers.33.mixer.conv1d.weight": "model-00003-of-00007.safetensors", "backbone.layers.33.mixer.dt_bias": "model-00003-of-00007.safetensors", "backbone.layers.33.mixer.in_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.33.mixer.in_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.33.mixer.in_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.33.mixer.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.33.mixer.out_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.33.mixer.out_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.33.mixer.out_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.33.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.fc1_latent_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.fc1_latent_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.fc1_latent_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.fc2_latent_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.fc2_latent_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.fc2_latent_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.gate.e_score_correction_bias": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.gate.weight": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.switch_mlp.fc1.biases": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.switch_mlp.fc1.scales": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.switch_mlp.fc1.weight": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.switch_mlp.fc2.biases": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.switch_mlp.fc2.scales": "model-00003-of-00007.safetensors", "backbone.layers.34.mixer.switch_mlp.fc2.weight": "model-00003-of-00007.safetensors", "backbone.layers.34.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.35.mixer.A_log": "model-00003-of-00007.safetensors", "backbone.layers.35.mixer.D": "model-00003-of-00007.safetensors", "backbone.layers.35.mixer.conv1d.bias": "model-00003-of-00007.safetensors", "backbone.layers.35.mixer.conv1d.weight": "model-00003-of-00007.safetensors", "backbone.layers.35.mixer.dt_bias": "model-00003-of-00007.safetensors", "backbone.layers.35.mixer.in_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.35.mixer.in_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.35.mixer.in_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.35.mixer.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.35.mixer.out_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.35.mixer.out_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.35.mixer.out_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.35.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.36.mixer.k_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.36.mixer.k_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.36.mixer.k_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.36.mixer.o_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.36.mixer.o_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.36.mixer.o_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.36.mixer.q_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.36.mixer.q_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.36.mixer.q_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.36.mixer.v_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.36.mixer.v_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.36.mixer.v_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.36.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.fc1_latent_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.fc1_latent_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.fc1_latent_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.fc2_latent_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.fc2_latent_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.fc2_latent_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.gate.e_score_correction_bias": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.gate.weight": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.switch_mlp.fc1.biases": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.switch_mlp.fc1.scales": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.switch_mlp.fc1.weight": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.switch_mlp.fc2.biases": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.switch_mlp.fc2.scales": "model-00003-of-00007.safetensors", "backbone.layers.37.mixer.switch_mlp.fc2.weight": "model-00003-of-00007.safetensors", "backbone.layers.37.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.38.mixer.A_log": "model-00003-of-00007.safetensors", "backbone.layers.38.mixer.D": "model-00003-of-00007.safetensors", "backbone.layers.38.mixer.conv1d.bias": "model-00003-of-00007.safetensors", "backbone.layers.38.mixer.conv1d.weight": "model-00003-of-00007.safetensors", "backbone.layers.38.mixer.dt_bias": "model-00003-of-00007.safetensors", "backbone.layers.38.mixer.in_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.38.mixer.in_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.38.mixer.in_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.38.mixer.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.38.mixer.out_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.38.mixer.out_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.38.mixer.out_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.38.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.fc1_latent_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.fc1_latent_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.fc1_latent_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.fc2_latent_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.fc2_latent_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.fc2_latent_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.gate.e_score_correction_bias": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.gate.weight": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.switch_mlp.fc1.biases": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.switch_mlp.fc1.scales": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.switch_mlp.fc1.weight": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.switch_mlp.fc2.biases": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.switch_mlp.fc2.scales": "model-00003-of-00007.safetensors", "backbone.layers.39.mixer.switch_mlp.fc2.weight": "model-00003-of-00007.safetensors", "backbone.layers.39.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.4.mixer.A_log": "model-00001-of-00007.safetensors", "backbone.layers.4.mixer.D": "model-00001-of-00007.safetensors", "backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00007.safetensors", "backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "backbone.layers.4.mixer.dt_bias": "model-00001-of-00007.safetensors", "backbone.layers.4.mixer.in_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.4.mixer.in_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.4.mixer.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.4.mixer.out_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.4.mixer.out_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.4.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.40.mixer.A_log": "model-00003-of-00007.safetensors", "backbone.layers.40.mixer.D": "model-00003-of-00007.safetensors", "backbone.layers.40.mixer.conv1d.bias": "model-00003-of-00007.safetensors", "backbone.layers.40.mixer.conv1d.weight": "model-00003-of-00007.safetensors", "backbone.layers.40.mixer.dt_bias": "model-00003-of-00007.safetensors", "backbone.layers.40.mixer.in_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.40.mixer.in_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.40.mixer.in_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.40.mixer.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.40.mixer.out_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.40.mixer.out_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.40.mixer.out_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.40.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.41.mixer.fc1_latent_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.41.mixer.fc1_latent_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.41.mixer.fc1_latent_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.41.mixer.fc2_latent_proj.biases": "model-00003-of-00007.safetensors", "backbone.layers.41.mixer.fc2_latent_proj.scales": "model-00003-of-00007.safetensors", "backbone.layers.41.mixer.fc2_latent_proj.weight": "model-00003-of-00007.safetensors", "backbone.layers.41.mixer.gate.e_score_correction_bias": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.gate.weight": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.switch_mlp.fc1.biases": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.switch_mlp.fc1.scales": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.switch_mlp.fc1.weight": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.switch_mlp.fc2.biases": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.switch_mlp.fc2.scales": "model-00004-of-00007.safetensors", "backbone.layers.41.mixer.switch_mlp.fc2.weight": "model-00004-of-00007.safetensors", "backbone.layers.41.norm.weight": "model-00003-of-00007.safetensors", "backbone.layers.42.mixer.A_log": "model-00004-of-00007.safetensors", "backbone.layers.42.mixer.D": "model-00004-of-00007.safetensors", "backbone.layers.42.mixer.conv1d.bias": "model-00004-of-00007.safetensors", "backbone.layers.42.mixer.conv1d.weight": "model-00004-of-00007.safetensors", "backbone.layers.42.mixer.dt_bias": "model-00004-of-00007.safetensors", "backbone.layers.42.mixer.in_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.42.mixer.in_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.42.mixer.in_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.42.mixer.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.42.mixer.out_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.42.mixer.out_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.42.mixer.out_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.42.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.fc1_latent_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.fc1_latent_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.fc1_latent_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.fc2_latent_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.fc2_latent_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.fc2_latent_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.gate.e_score_correction_bias": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.gate.weight": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.switch_mlp.fc1.biases": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.switch_mlp.fc1.scales": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.switch_mlp.fc1.weight": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.switch_mlp.fc2.biases": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.switch_mlp.fc2.scales": "model-00004-of-00007.safetensors", "backbone.layers.43.mixer.switch_mlp.fc2.weight": "model-00004-of-00007.safetensors", "backbone.layers.43.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.44.mixer.A_log": "model-00004-of-00007.safetensors", "backbone.layers.44.mixer.D": "model-00004-of-00007.safetensors", "backbone.layers.44.mixer.conv1d.bias": "model-00004-of-00007.safetensors", "backbone.layers.44.mixer.conv1d.weight": "model-00004-of-00007.safetensors", "backbone.layers.44.mixer.dt_bias": "model-00004-of-00007.safetensors", "backbone.layers.44.mixer.in_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.44.mixer.in_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.44.mixer.in_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.44.mixer.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.44.mixer.out_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.44.mixer.out_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.44.mixer.out_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.44.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.fc1_latent_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.fc1_latent_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.fc1_latent_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.fc2_latent_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.fc2_latent_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.fc2_latent_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.gate.e_score_correction_bias": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.gate.weight": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.switch_mlp.fc1.biases": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.switch_mlp.fc1.scales": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.switch_mlp.fc1.weight": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.switch_mlp.fc2.biases": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.switch_mlp.fc2.scales": "model-00004-of-00007.safetensors", "backbone.layers.45.mixer.switch_mlp.fc2.weight": "model-00004-of-00007.safetensors", "backbone.layers.45.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.46.mixer.A_log": "model-00004-of-00007.safetensors", "backbone.layers.46.mixer.D": "model-00004-of-00007.safetensors", "backbone.layers.46.mixer.conv1d.bias": "model-00004-of-00007.safetensors", "backbone.layers.46.mixer.conv1d.weight": "model-00004-of-00007.safetensors", "backbone.layers.46.mixer.dt_bias": "model-00004-of-00007.safetensors", "backbone.layers.46.mixer.in_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.46.mixer.in_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.46.mixer.in_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.46.mixer.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.46.mixer.out_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.46.mixer.out_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.46.mixer.out_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.46.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.47.mixer.k_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.47.mixer.k_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.47.mixer.k_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.47.mixer.o_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.47.mixer.o_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.47.mixer.o_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.47.mixer.q_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.47.mixer.q_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.47.mixer.q_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.47.mixer.v_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.47.mixer.v_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.47.mixer.v_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.47.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.fc1_latent_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.fc1_latent_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.fc1_latent_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.fc2_latent_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.fc2_latent_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.fc2_latent_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.gate.e_score_correction_bias": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.gate.weight": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.switch_mlp.fc1.biases": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.switch_mlp.fc1.scales": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.switch_mlp.fc1.weight": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.switch_mlp.fc2.biases": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.switch_mlp.fc2.scales": "model-00004-of-00007.safetensors", "backbone.layers.48.mixer.switch_mlp.fc2.weight": "model-00004-of-00007.safetensors", "backbone.layers.48.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.49.mixer.A_log": "model-00004-of-00007.safetensors", "backbone.layers.49.mixer.D": "model-00004-of-00007.safetensors", "backbone.layers.49.mixer.conv1d.bias": "model-00004-of-00007.safetensors", "backbone.layers.49.mixer.conv1d.weight": "model-00004-of-00007.safetensors", "backbone.layers.49.mixer.dt_bias": "model-00004-of-00007.safetensors", "backbone.layers.49.mixer.in_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.49.mixer.in_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.49.mixer.in_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.49.mixer.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.49.mixer.out_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.49.mixer.out_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.49.mixer.out_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.49.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.5.mixer.fc1_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.fc1_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.fc1_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.fc2_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.fc2_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.fc2_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.gate.e_score_correction_bias": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.gate.weight": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.switch_mlp.fc1.biases": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.switch_mlp.fc1.scales": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.switch_mlp.fc1.weight": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.switch_mlp.fc2.biases": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.switch_mlp.fc2.scales": "model-00001-of-00007.safetensors", "backbone.layers.5.mixer.switch_mlp.fc2.weight": "model-00001-of-00007.safetensors", "backbone.layers.5.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.50.mixer.fc1_latent_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.fc1_latent_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.fc1_latent_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.fc2_latent_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.fc2_latent_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.fc2_latent_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.gate.e_score_correction_bias": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.gate.weight": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.switch_mlp.fc1.biases": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.switch_mlp.fc1.scales": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.switch_mlp.fc1.weight": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.switch_mlp.fc2.biases": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.switch_mlp.fc2.scales": "model-00004-of-00007.safetensors", "backbone.layers.50.mixer.switch_mlp.fc2.weight": "model-00004-of-00007.safetensors", "backbone.layers.50.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.51.mixer.A_log": "model-00004-of-00007.safetensors", "backbone.layers.51.mixer.D": "model-00004-of-00007.safetensors", "backbone.layers.51.mixer.conv1d.bias": "model-00004-of-00007.safetensors", "backbone.layers.51.mixer.conv1d.weight": "model-00004-of-00007.safetensors", "backbone.layers.51.mixer.dt_bias": "model-00004-of-00007.safetensors", "backbone.layers.51.mixer.in_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.51.mixer.in_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.51.mixer.in_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.51.mixer.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.51.mixer.out_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.51.mixer.out_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.51.mixer.out_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.51.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.fc1_latent_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.fc1_latent_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.fc1_latent_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.fc2_latent_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.fc2_latent_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.fc2_latent_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.gate.e_score_correction_bias": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.gate.weight": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.switch_mlp.fc1.biases": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.switch_mlp.fc1.scales": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.switch_mlp.fc1.weight": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.switch_mlp.fc2.biases": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.switch_mlp.fc2.scales": "model-00004-of-00007.safetensors", "backbone.layers.52.mixer.switch_mlp.fc2.weight": "model-00004-of-00007.safetensors", "backbone.layers.52.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.53.mixer.A_log": "model-00004-of-00007.safetensors", "backbone.layers.53.mixer.D": "model-00004-of-00007.safetensors", "backbone.layers.53.mixer.conv1d.bias": "model-00004-of-00007.safetensors", "backbone.layers.53.mixer.conv1d.weight": "model-00004-of-00007.safetensors", "backbone.layers.53.mixer.dt_bias": "model-00004-of-00007.safetensors", "backbone.layers.53.mixer.in_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.53.mixer.in_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.53.mixer.in_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.53.mixer.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.53.mixer.out_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.53.mixer.out_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.53.mixer.out_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.53.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.54.mixer.fc1_latent_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.54.mixer.fc1_latent_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.54.mixer.fc1_latent_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.54.mixer.fc2_latent_proj.biases": "model-00004-of-00007.safetensors", "backbone.layers.54.mixer.fc2_latent_proj.scales": "model-00004-of-00007.safetensors", "backbone.layers.54.mixer.fc2_latent_proj.weight": "model-00004-of-00007.safetensors", "backbone.layers.54.mixer.gate.e_score_correction_bias": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.gate.weight": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.switch_mlp.fc1.biases": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.switch_mlp.fc1.scales": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.switch_mlp.fc1.weight": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.switch_mlp.fc2.biases": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.switch_mlp.fc2.scales": "model-00005-of-00007.safetensors", "backbone.layers.54.mixer.switch_mlp.fc2.weight": "model-00005-of-00007.safetensors", "backbone.layers.54.norm.weight": "model-00004-of-00007.safetensors", "backbone.layers.55.mixer.A_log": "model-00005-of-00007.safetensors", "backbone.layers.55.mixer.D": "model-00005-of-00007.safetensors", "backbone.layers.55.mixer.conv1d.bias": "model-00005-of-00007.safetensors", "backbone.layers.55.mixer.conv1d.weight": "model-00005-of-00007.safetensors", "backbone.layers.55.mixer.dt_bias": "model-00005-of-00007.safetensors", "backbone.layers.55.mixer.in_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.55.mixer.in_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.55.mixer.in_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.55.mixer.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.55.mixer.out_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.55.mixer.out_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.55.mixer.out_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.55.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.fc1_latent_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.fc1_latent_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.fc1_latent_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.fc2_latent_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.fc2_latent_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.fc2_latent_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.gate.e_score_correction_bias": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.gate.weight": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.switch_mlp.fc1.biases": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.switch_mlp.fc1.scales": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.switch_mlp.fc1.weight": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.switch_mlp.fc2.biases": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.switch_mlp.fc2.scales": "model-00005-of-00007.safetensors", "backbone.layers.56.mixer.switch_mlp.fc2.weight": "model-00005-of-00007.safetensors", "backbone.layers.56.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.57.mixer.A_log": "model-00005-of-00007.safetensors", "backbone.layers.57.mixer.D": "model-00005-of-00007.safetensors", "backbone.layers.57.mixer.conv1d.bias": "model-00005-of-00007.safetensors", "backbone.layers.57.mixer.conv1d.weight": "model-00005-of-00007.safetensors", "backbone.layers.57.mixer.dt_bias": "model-00005-of-00007.safetensors", "backbone.layers.57.mixer.in_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.57.mixer.in_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.57.mixer.in_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.57.mixer.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.57.mixer.out_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.57.mixer.out_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.57.mixer.out_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.57.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.58.mixer.k_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.58.mixer.k_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.58.mixer.k_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.58.mixer.o_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.58.mixer.o_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.58.mixer.o_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.58.mixer.q_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.58.mixer.q_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.58.mixer.q_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.58.mixer.v_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.58.mixer.v_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.58.mixer.v_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.58.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.fc1_latent_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.fc1_latent_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.fc1_latent_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.fc2_latent_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.fc2_latent_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.fc2_latent_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.gate.e_score_correction_bias": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.gate.weight": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.switch_mlp.fc1.biases": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.switch_mlp.fc1.scales": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.switch_mlp.fc1.weight": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.switch_mlp.fc2.biases": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.switch_mlp.fc2.scales": "model-00005-of-00007.safetensors", "backbone.layers.59.mixer.switch_mlp.fc2.weight": "model-00005-of-00007.safetensors", "backbone.layers.59.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.6.mixer.A_log": "model-00001-of-00007.safetensors", "backbone.layers.6.mixer.D": "model-00001-of-00007.safetensors", "backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00007.safetensors", "backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "backbone.layers.6.mixer.dt_bias": "model-00001-of-00007.safetensors", "backbone.layers.6.mixer.in_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.6.mixer.in_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.6.mixer.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.6.mixer.out_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.6.mixer.out_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.6.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.60.mixer.A_log": "model-00005-of-00007.safetensors", "backbone.layers.60.mixer.D": "model-00005-of-00007.safetensors", "backbone.layers.60.mixer.conv1d.bias": "model-00005-of-00007.safetensors", "backbone.layers.60.mixer.conv1d.weight": "model-00005-of-00007.safetensors", "backbone.layers.60.mixer.dt_bias": "model-00005-of-00007.safetensors", "backbone.layers.60.mixer.in_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.60.mixer.in_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.60.mixer.in_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.60.mixer.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.60.mixer.out_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.60.mixer.out_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.60.mixer.out_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.60.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.fc1_latent_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.fc1_latent_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.fc1_latent_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.fc2_latent_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.fc2_latent_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.fc2_latent_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.gate.e_score_correction_bias": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.gate.weight": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.switch_mlp.fc1.biases": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.switch_mlp.fc1.scales": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.switch_mlp.fc1.weight": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.switch_mlp.fc2.biases": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.switch_mlp.fc2.scales": "model-00005-of-00007.safetensors", "backbone.layers.61.mixer.switch_mlp.fc2.weight": "model-00005-of-00007.safetensors", "backbone.layers.61.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.62.mixer.A_log": "model-00005-of-00007.safetensors", "backbone.layers.62.mixer.D": "model-00005-of-00007.safetensors", "backbone.layers.62.mixer.conv1d.bias": "model-00005-of-00007.safetensors", "backbone.layers.62.mixer.conv1d.weight": "model-00005-of-00007.safetensors", "backbone.layers.62.mixer.dt_bias": "model-00005-of-00007.safetensors", "backbone.layers.62.mixer.in_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.62.mixer.in_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.62.mixer.in_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.62.mixer.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.62.mixer.out_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.62.mixer.out_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.62.mixer.out_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.62.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.fc1_latent_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.fc1_latent_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.fc1_latent_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.fc2_latent_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.fc2_latent_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.fc2_latent_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.gate.e_score_correction_bias": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.gate.weight": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.switch_mlp.fc1.biases": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.switch_mlp.fc1.scales": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.switch_mlp.fc1.weight": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.switch_mlp.fc2.biases": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.switch_mlp.fc2.scales": "model-00005-of-00007.safetensors", "backbone.layers.63.mixer.switch_mlp.fc2.weight": "model-00005-of-00007.safetensors", "backbone.layers.63.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.64.mixer.A_log": "model-00005-of-00007.safetensors", "backbone.layers.64.mixer.D": "model-00005-of-00007.safetensors", "backbone.layers.64.mixer.conv1d.bias": "model-00005-of-00007.safetensors", "backbone.layers.64.mixer.conv1d.weight": "model-00005-of-00007.safetensors", "backbone.layers.64.mixer.dt_bias": "model-00005-of-00007.safetensors", "backbone.layers.64.mixer.in_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.64.mixer.in_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.64.mixer.in_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.64.mixer.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.64.mixer.out_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.64.mixer.out_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.64.mixer.out_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.64.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.fc1_latent_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.fc1_latent_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.fc1_latent_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.fc2_latent_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.fc2_latent_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.fc2_latent_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.gate.e_score_correction_bias": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.gate.weight": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.switch_mlp.fc1.biases": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.switch_mlp.fc1.scales": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.switch_mlp.fc1.weight": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.switch_mlp.fc2.biases": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.switch_mlp.fc2.scales": "model-00005-of-00007.safetensors", "backbone.layers.65.mixer.switch_mlp.fc2.weight": "model-00005-of-00007.safetensors", "backbone.layers.65.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.66.mixer.A_log": "model-00005-of-00007.safetensors", "backbone.layers.66.mixer.D": "model-00005-of-00007.safetensors", "backbone.layers.66.mixer.conv1d.bias": "model-00005-of-00007.safetensors", "backbone.layers.66.mixer.conv1d.weight": "model-00005-of-00007.safetensors", "backbone.layers.66.mixer.dt_bias": "model-00005-of-00007.safetensors", "backbone.layers.66.mixer.in_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.66.mixer.in_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.66.mixer.in_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.66.mixer.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.66.mixer.out_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.66.mixer.out_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.66.mixer.out_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.66.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.67.mixer.fc1_latent_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.67.mixer.fc1_latent_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.67.mixer.fc1_latent_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.67.mixer.fc2_latent_proj.biases": "model-00005-of-00007.safetensors", "backbone.layers.67.mixer.fc2_latent_proj.scales": "model-00005-of-00007.safetensors", "backbone.layers.67.mixer.fc2_latent_proj.weight": "model-00005-of-00007.safetensors", "backbone.layers.67.mixer.gate.e_score_correction_bias": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.gate.weight": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.switch_mlp.fc1.biases": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.switch_mlp.fc1.scales": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.switch_mlp.fc1.weight": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.switch_mlp.fc2.biases": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.switch_mlp.fc2.scales": "model-00006-of-00007.safetensors", "backbone.layers.67.mixer.switch_mlp.fc2.weight": "model-00006-of-00007.safetensors", "backbone.layers.67.norm.weight": "model-00005-of-00007.safetensors", "backbone.layers.68.mixer.A_log": "model-00006-of-00007.safetensors", "backbone.layers.68.mixer.D": "model-00006-of-00007.safetensors", "backbone.layers.68.mixer.conv1d.bias": "model-00006-of-00007.safetensors", "backbone.layers.68.mixer.conv1d.weight": "model-00006-of-00007.safetensors", "backbone.layers.68.mixer.dt_bias": "model-00006-of-00007.safetensors", "backbone.layers.68.mixer.in_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.68.mixer.in_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.68.mixer.in_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.68.mixer.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.68.mixer.out_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.68.mixer.out_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.68.mixer.out_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.68.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.69.mixer.k_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.69.mixer.k_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.69.mixer.k_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.69.mixer.o_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.69.mixer.o_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.69.mixer.o_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.69.mixer.q_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.69.mixer.q_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.69.mixer.q_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.69.mixer.v_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.69.mixer.v_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.69.mixer.v_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.69.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.7.mixer.k_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.7.mixer.k_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.7.mixer.k_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.7.mixer.o_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.7.mixer.o_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.7.mixer.o_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.7.mixer.q_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.7.mixer.q_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.7.mixer.q_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.7.mixer.v_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.7.mixer.v_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.7.mixer.v_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.7.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.70.mixer.fc1_latent_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.fc1_latent_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.fc1_latent_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.fc2_latent_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.fc2_latent_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.fc2_latent_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.gate.e_score_correction_bias": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.gate.weight": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.switch_mlp.fc1.biases": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.switch_mlp.fc1.scales": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.switch_mlp.fc1.weight": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.switch_mlp.fc2.biases": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.switch_mlp.fc2.scales": "model-00006-of-00007.safetensors", "backbone.layers.70.mixer.switch_mlp.fc2.weight": "model-00006-of-00007.safetensors", "backbone.layers.70.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.71.mixer.A_log": "model-00006-of-00007.safetensors", "backbone.layers.71.mixer.D": "model-00006-of-00007.safetensors", "backbone.layers.71.mixer.conv1d.bias": "model-00006-of-00007.safetensors", "backbone.layers.71.mixer.conv1d.weight": "model-00006-of-00007.safetensors", "backbone.layers.71.mixer.dt_bias": "model-00006-of-00007.safetensors", "backbone.layers.71.mixer.in_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.71.mixer.in_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.71.mixer.in_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.71.mixer.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.71.mixer.out_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.71.mixer.out_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.71.mixer.out_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.71.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.fc1_latent_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.fc1_latent_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.fc1_latent_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.fc2_latent_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.fc2_latent_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.fc2_latent_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.gate.e_score_correction_bias": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.gate.weight": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.switch_mlp.fc1.biases": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.switch_mlp.fc1.scales": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.switch_mlp.fc1.weight": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.switch_mlp.fc2.biases": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.switch_mlp.fc2.scales": "model-00006-of-00007.safetensors", "backbone.layers.72.mixer.switch_mlp.fc2.weight": "model-00006-of-00007.safetensors", "backbone.layers.72.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.73.mixer.A_log": "model-00006-of-00007.safetensors", "backbone.layers.73.mixer.D": "model-00006-of-00007.safetensors", "backbone.layers.73.mixer.conv1d.bias": "model-00006-of-00007.safetensors", "backbone.layers.73.mixer.conv1d.weight": "model-00006-of-00007.safetensors", "backbone.layers.73.mixer.dt_bias": "model-00006-of-00007.safetensors", "backbone.layers.73.mixer.in_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.73.mixer.in_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.73.mixer.in_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.73.mixer.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.73.mixer.out_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.73.mixer.out_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.73.mixer.out_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.73.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.fc1_latent_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.fc1_latent_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.fc1_latent_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.fc2_latent_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.fc2_latent_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.fc2_latent_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.gate.e_score_correction_bias": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.gate.weight": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.switch_mlp.fc1.biases": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.switch_mlp.fc1.scales": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.switch_mlp.fc1.weight": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.switch_mlp.fc2.biases": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.switch_mlp.fc2.scales": "model-00006-of-00007.safetensors", "backbone.layers.74.mixer.switch_mlp.fc2.weight": "model-00006-of-00007.safetensors", "backbone.layers.74.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.75.mixer.A_log": "model-00006-of-00007.safetensors", "backbone.layers.75.mixer.D": "model-00006-of-00007.safetensors", "backbone.layers.75.mixer.conv1d.bias": "model-00006-of-00007.safetensors", "backbone.layers.75.mixer.conv1d.weight": "model-00006-of-00007.safetensors", "backbone.layers.75.mixer.dt_bias": "model-00006-of-00007.safetensors", "backbone.layers.75.mixer.in_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.75.mixer.in_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.75.mixer.in_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.75.mixer.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.75.mixer.out_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.75.mixer.out_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.75.mixer.out_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.75.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.fc1_latent_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.fc1_latent_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.fc1_latent_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.fc2_latent_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.fc2_latent_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.fc2_latent_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.gate.e_score_correction_bias": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.gate.weight": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.switch_mlp.fc1.biases": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.switch_mlp.fc1.scales": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.switch_mlp.fc1.weight": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.switch_mlp.fc2.biases": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.switch_mlp.fc2.scales": "model-00006-of-00007.safetensors", "backbone.layers.76.mixer.switch_mlp.fc2.weight": "model-00006-of-00007.safetensors", "backbone.layers.76.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.77.mixer.A_log": "model-00006-of-00007.safetensors", "backbone.layers.77.mixer.D": "model-00006-of-00007.safetensors", "backbone.layers.77.mixer.conv1d.bias": "model-00006-of-00007.safetensors", "backbone.layers.77.mixer.conv1d.weight": "model-00006-of-00007.safetensors", "backbone.layers.77.mixer.dt_bias": "model-00006-of-00007.safetensors", "backbone.layers.77.mixer.in_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.77.mixer.in_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.77.mixer.in_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.77.mixer.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.77.mixer.out_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.77.mixer.out_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.77.mixer.out_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.77.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.78.mixer.k_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.78.mixer.k_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.78.mixer.k_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.78.mixer.o_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.78.mixer.o_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.78.mixer.o_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.78.mixer.q_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.78.mixer.q_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.78.mixer.q_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.78.mixer.v_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.78.mixer.v_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.78.mixer.v_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.78.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.fc1_latent_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.fc1_latent_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.fc1_latent_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.fc2_latent_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.fc2_latent_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.fc2_latent_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.gate.e_score_correction_bias": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.gate.weight": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.switch_mlp.fc1.biases": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.switch_mlp.fc1.scales": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.switch_mlp.fc1.weight": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.switch_mlp.fc2.biases": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.switch_mlp.fc2.scales": "model-00006-of-00007.safetensors", "backbone.layers.79.mixer.switch_mlp.fc2.weight": "model-00006-of-00007.safetensors", "backbone.layers.79.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.8.mixer.fc1_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.fc1_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.fc1_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.fc2_latent_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.fc2_latent_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.fc2_latent_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.gate.e_score_correction_bias": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.gate.weight": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.switch_mlp.fc1.biases": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.switch_mlp.fc1.scales": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.switch_mlp.fc1.weight": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.switch_mlp.fc2.biases": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.switch_mlp.fc2.scales": "model-00001-of-00007.safetensors", "backbone.layers.8.mixer.switch_mlp.fc2.weight": "model-00001-of-00007.safetensors", "backbone.layers.8.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.80.mixer.A_log": "model-00006-of-00007.safetensors", "backbone.layers.80.mixer.D": "model-00006-of-00007.safetensors", "backbone.layers.80.mixer.conv1d.bias": "model-00006-of-00007.safetensors", "backbone.layers.80.mixer.conv1d.weight": "model-00006-of-00007.safetensors", "backbone.layers.80.mixer.dt_bias": "model-00006-of-00007.safetensors", "backbone.layers.80.mixer.in_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.80.mixer.in_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.80.mixer.in_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.80.mixer.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.80.mixer.out_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.80.mixer.out_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.80.mixer.out_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.80.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.81.mixer.fc1_latent_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.81.mixer.fc1_latent_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.81.mixer.fc1_latent_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.81.mixer.fc2_latent_proj.biases": "model-00006-of-00007.safetensors", "backbone.layers.81.mixer.fc2_latent_proj.scales": "model-00006-of-00007.safetensors", "backbone.layers.81.mixer.fc2_latent_proj.weight": "model-00006-of-00007.safetensors", "backbone.layers.81.mixer.gate.e_score_correction_bias": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.gate.weight": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.shared_experts.down_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.shared_experts.down_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.shared_experts.down_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.shared_experts.up_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.shared_experts.up_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.shared_experts.up_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.switch_mlp.fc1.biases": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.switch_mlp.fc1.scales": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.switch_mlp.fc1.weight": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.switch_mlp.fc2.biases": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.switch_mlp.fc2.scales": "model-00007-of-00007.safetensors", "backbone.layers.81.mixer.switch_mlp.fc2.weight": "model-00007-of-00007.safetensors", "backbone.layers.81.norm.weight": "model-00006-of-00007.safetensors", "backbone.layers.82.mixer.A_log": "model-00007-of-00007.safetensors", "backbone.layers.82.mixer.D": "model-00007-of-00007.safetensors", "backbone.layers.82.mixer.conv1d.bias": "model-00007-of-00007.safetensors", "backbone.layers.82.mixer.conv1d.weight": "model-00007-of-00007.safetensors", "backbone.layers.82.mixer.dt_bias": "model-00007-of-00007.safetensors", "backbone.layers.82.mixer.in_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.82.mixer.in_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.82.mixer.in_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.82.mixer.norm.weight": "model-00007-of-00007.safetensors", "backbone.layers.82.mixer.out_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.82.mixer.out_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.82.mixer.out_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.82.norm.weight": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.fc1_latent_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.fc1_latent_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.fc1_latent_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.fc2_latent_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.fc2_latent_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.fc2_latent_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.gate.e_score_correction_bias": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.gate.weight": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.shared_experts.down_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.shared_experts.down_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.shared_experts.down_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.shared_experts.up_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.shared_experts.up_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.shared_experts.up_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.switch_mlp.fc1.biases": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.switch_mlp.fc1.scales": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.switch_mlp.fc1.weight": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.switch_mlp.fc2.biases": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.switch_mlp.fc2.scales": "model-00007-of-00007.safetensors", "backbone.layers.83.mixer.switch_mlp.fc2.weight": "model-00007-of-00007.safetensors", "backbone.layers.83.norm.weight": "model-00007-of-00007.safetensors", "backbone.layers.84.mixer.A_log": "model-00007-of-00007.safetensors", "backbone.layers.84.mixer.D": "model-00007-of-00007.safetensors", "backbone.layers.84.mixer.conv1d.bias": "model-00007-of-00007.safetensors", "backbone.layers.84.mixer.conv1d.weight": "model-00007-of-00007.safetensors", "backbone.layers.84.mixer.dt_bias": "model-00007-of-00007.safetensors", "backbone.layers.84.mixer.in_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.84.mixer.in_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.84.mixer.in_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.84.mixer.norm.weight": "model-00007-of-00007.safetensors", "backbone.layers.84.mixer.out_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.84.mixer.out_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.84.mixer.out_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.84.norm.weight": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.fc1_latent_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.fc1_latent_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.fc1_latent_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.fc2_latent_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.fc2_latent_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.fc2_latent_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.gate.e_score_correction_bias": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.gate.weight": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.shared_experts.down_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.shared_experts.down_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.shared_experts.down_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.shared_experts.up_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.shared_experts.up_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.shared_experts.up_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.switch_mlp.fc1.biases": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.switch_mlp.fc1.scales": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.switch_mlp.fc1.weight": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.switch_mlp.fc2.biases": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.switch_mlp.fc2.scales": "model-00007-of-00007.safetensors", "backbone.layers.85.mixer.switch_mlp.fc2.weight": "model-00007-of-00007.safetensors", "backbone.layers.85.norm.weight": "model-00007-of-00007.safetensors", "backbone.layers.86.mixer.A_log": "model-00007-of-00007.safetensors", "backbone.layers.86.mixer.D": "model-00007-of-00007.safetensors", "backbone.layers.86.mixer.conv1d.bias": "model-00007-of-00007.safetensors", "backbone.layers.86.mixer.conv1d.weight": "model-00007-of-00007.safetensors", "backbone.layers.86.mixer.dt_bias": "model-00007-of-00007.safetensors", "backbone.layers.86.mixer.in_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.86.mixer.in_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.86.mixer.in_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.86.mixer.norm.weight": "model-00007-of-00007.safetensors", "backbone.layers.86.mixer.out_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.86.mixer.out_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.86.mixer.out_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.86.norm.weight": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.fc1_latent_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.fc1_latent_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.fc1_latent_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.fc2_latent_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.fc2_latent_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.fc2_latent_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.gate.e_score_correction_bias": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.gate.weight": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.shared_experts.down_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.shared_experts.down_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.shared_experts.down_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.shared_experts.up_proj.biases": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.shared_experts.up_proj.scales": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.shared_experts.up_proj.weight": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.switch_mlp.fc1.biases": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.switch_mlp.fc1.scales": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.switch_mlp.fc1.weight": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.switch_mlp.fc2.biases": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.switch_mlp.fc2.scales": "model-00007-of-00007.safetensors", "backbone.layers.87.mixer.switch_mlp.fc2.weight": "model-00007-of-00007.safetensors", "backbone.layers.87.norm.weight": "model-00007-of-00007.safetensors", "backbone.layers.9.mixer.A_log": "model-00001-of-00007.safetensors", "backbone.layers.9.mixer.D": "model-00001-of-00007.safetensors", "backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00007.safetensors", "backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00007.safetensors", "backbone.layers.9.mixer.dt_bias": "model-00001-of-00007.safetensors", "backbone.layers.9.mixer.in_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.9.mixer.in_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.9.mixer.norm.weight": "model-00001-of-00007.safetensors", "backbone.layers.9.mixer.out_proj.biases": "model-00001-of-00007.safetensors", "backbone.layers.9.mixer.out_proj.scales": "model-00001-of-00007.safetensors", "backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00007.safetensors", "backbone.layers.9.norm.weight": "model-00001-of-00007.safetensors", "backbone.norm_f.weight": "model-00007-of-00007.safetensors", "lm_head.biases": "model-00007-of-00007.safetensors", "lm_head.scales": "model-00007-of-00007.safetensors", "lm_head.weight": "model-00007-of-00007.safetensors" } }