{
    "metadata": {
        "total_size": 10176700416,
        "total_parameters": 13568641024
    },
    "weight_map": {
        "lm_head.biases": "model-00002-of-00002.safetensors",
        "lm_head.scales": "model-00002-of-00002.safetensors",
        "lm_head.weight": "model-00002-of-00002.safetensors",
        "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
        "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.gate.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.gate.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.pre_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.gate.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.gate.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.pre_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.gate.biases": "model-00002-of-00002.safetensors",
        "model.layers.10.mlp.gate.scales": "model-00002-of-00002.safetensors",
        "model.layers.10.mlp.gate.weight": "model-00002-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.10.pre_attention_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.10.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.10.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.10.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.10.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.10.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.10.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.10.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.10.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.11.mlp.gate.biases": "model-00002-of-00002.safetensors",
        "model.layers.11.mlp.gate.scales": "model-00002-of-00002.safetensors",
        "model.layers.11.mlp.gate.weight": "model-00002-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.11.pre_attention_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.11.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.11.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.11.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.11.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.11.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.11.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.11.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.11.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.12.mlp.gate.biases": "model-00002-of-00002.safetensors",
        "model.layers.12.mlp.gate.scales": "model-00002-of-00002.safetensors",
        "model.layers.12.mlp.gate.weight": "model-00002-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.12.pre_attention_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.12.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.12.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.12.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.12.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.12.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.12.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.12.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.13.mlp.gate.biases": "model-00002-of-00002.safetensors",
        "model.layers.13.mlp.gate.scales": "model-00002-of-00002.safetensors",
        "model.layers.13.mlp.gate.weight": "model-00002-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.13.pre_attention_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.13.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.13.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.13.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.13.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.14.mlp.gate.biases": "model-00002-of-00002.safetensors",
        "model.layers.14.mlp.gate.scales": "model-00002-of-00002.safetensors",
        "model.layers.14.mlp.gate.weight": "model-00002-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.14.pre_attention_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.14.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.14.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.14.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.14.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.15.mlp.gate.biases": "model-00002-of-00002.safetensors",
        "model.layers.15.mlp.gate.scales": "model-00002-of-00002.safetensors",
        "model.layers.15.mlp.gate.weight": "model-00002-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.15.pre_attention_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.15.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.15.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.15.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.15.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.2.mlp.gate.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.gate.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.pre_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.gate.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.gate.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.pre_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.gate.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.gate.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.pre_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.gate.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.gate.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.pre_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.gate.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.gate.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.pre_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.gate.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.gate.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.pre_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.gate.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.gate.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.8.pre_attention_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.gate.biases": "model-00002-of-00002.safetensors",
        "model.layers.9.mlp.gate.scales": "model-00002-of-00002.safetensors",
        "model.layers.9.mlp.gate.weight": "model-00002-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.9.pre_attention_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
        "model.layers.9.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.9.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.9.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.9.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.9.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.9.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
        "model.layers.9.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
        "model.layers.9.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
        "model.norm.weight": "model-00002-of-00002.safetensors"
    }
}