{
  "metadata": {
    "total_size": 539030994944
  },
  "weight_map": {
    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.pre_attn_norm.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.post_attn_norm.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.pre_moe_norm.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.post_moe_norm.weight": "pytorch_model-00001.safetensors",
    "model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001.safetensors",
    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.pre_attn_norm.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.post_attn_norm.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.pre_moe_norm.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.post_moe_norm.weight": "pytorch_model-00002.safetensors",
    "model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00002.safetensors",
    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.pre_attn_norm.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.post_attn_norm.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.pre_moe_norm.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.post_moe_norm.weight": "pytorch_model-00003.safetensors",
    "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00003.safetensors",
    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.pre_attn_norm.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.post_attn_norm.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.pre_moe_norm.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.post_moe_norm.weight": "pytorch_model-00004.safetensors",
    "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00004.safetensors",
    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.pre_attn_norm.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.post_attn_norm.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.pre_moe_norm.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.post_moe_norm.weight": "pytorch_model-00005.safetensors",
    "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00005.safetensors",
    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.pre_attn_norm.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.post_attn_norm.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.pre_moe_norm.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.post_moe_norm.weight": "pytorch_model-00006.safetensors",
    "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00006.safetensors",
    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.pre_attn_norm.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.post_attn_norm.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.pre_moe_norm.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.post_moe_norm.weight": "pytorch_model-00007.safetensors",
    "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00007.safetensors",
    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.pre_attn_norm.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.post_attn_norm.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.pre_moe_norm.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.post_moe_norm.weight": "pytorch_model-00008.safetensors",
    "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00008.safetensors",
    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.pre_attn_norm.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.post_attn_norm.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.pre_moe_norm.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.post_moe_norm.weight": "pytorch_model-00009.safetensors",
    "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00009.safetensors",
    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.pre_attn_norm.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.post_attn_norm.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.pre_moe_norm.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.post_moe_norm.weight": "pytorch_model-00010.safetensors",
    "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00010.safetensors",
    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.pre_attn_norm.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.post_attn_norm.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.pre_moe_norm.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.post_moe_norm.weight": "pytorch_model-00011.safetensors",
    "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00011.safetensors",
    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.pre_attn_norm.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.post_attn_norm.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.pre_moe_norm.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.post_moe_norm.weight": "pytorch_model-00012.safetensors",
    "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00012.safetensors",
    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.pre_attn_norm.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.post_attn_norm.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.pre_moe_norm.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.post_moe_norm.weight": "pytorch_model-00013.safetensors",
    "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00013.safetensors",
    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.pre_attn_norm.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.post_attn_norm.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.pre_moe_norm.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.post_moe_norm.weight": "pytorch_model-00014.safetensors",
    "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00014.safetensors",
    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.pre_attn_norm.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.post_attn_norm.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.pre_moe_norm.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.post_moe_norm.weight": "pytorch_model-00015.safetensors",
    "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00015.safetensors",
    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.pre_attn_norm.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.post_attn_norm.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.pre_moe_norm.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.post_moe_norm.weight": "pytorch_model-00016.safetensors",
    "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00016.safetensors",
    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.pre_attn_norm.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.post_attn_norm.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.pre_moe_norm.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.post_moe_norm.weight": "pytorch_model-00017.safetensors",
    "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00017.safetensors",
    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.pre_attn_norm.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.post_attn_norm.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.pre_moe_norm.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.post_moe_norm.weight": "pytorch_model-00018.safetensors",
    "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00018.safetensors",
    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.pre_attn_norm.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.post_attn_norm.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.pre_moe_norm.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.post_moe_norm.weight": "pytorch_model-00019.safetensors",
    "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00019.safetensors",
    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.pre_attn_norm.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.post_attn_norm.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.pre_moe_norm.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.post_moe_norm.weight": "pytorch_model-00020.safetensors",
    "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00020.safetensors",
    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.pre_attn_norm.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.post_attn_norm.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.pre_moe_norm.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.post_moe_norm.weight": "pytorch_model-00021.safetensors",
    "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00021.safetensors",
    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.pre_attn_norm.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.post_attn_norm.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.pre_moe_norm.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.post_moe_norm.weight": "pytorch_model-00022.safetensors",
    "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00022.safetensors",
    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.pre_attn_norm.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.post_attn_norm.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.pre_moe_norm.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.post_moe_norm.weight": "pytorch_model-00023.safetensors",
    "model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00023.safetensors",
    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.pre_attn_norm.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.post_attn_norm.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.pre_moe_norm.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.post_moe_norm.weight": "pytorch_model-00024.safetensors",
    "model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00024.safetensors",
    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.pre_attn_norm.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.post_attn_norm.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.pre_moe_norm.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.post_moe_norm.weight": "pytorch_model-00025.safetensors",
    "model.layers.24.block_sparse_moe.gate.weight": "pytorch_model-00025.safetensors",
    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.pre_attn_norm.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.post_attn_norm.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.pre_moe_norm.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.post_moe_norm.weight": "pytorch_model-00026.safetensors",
    "model.layers.25.block_sparse_moe.gate.weight": "pytorch_model-00026.safetensors",
    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.pre_attn_norm.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.post_attn_norm.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.pre_moe_norm.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.post_moe_norm.weight": "pytorch_model-00027.safetensors",
    "model.layers.26.block_sparse_moe.gate.weight": "pytorch_model-00027.safetensors",
    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.pre_attn_norm.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.post_attn_norm.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.pre_moe_norm.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.post_moe_norm.weight": "pytorch_model-00028.safetensors",
    "model.layers.27.block_sparse_moe.gate.weight": "pytorch_model-00028.safetensors",
    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.pre_attn_norm.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.post_attn_norm.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.pre_moe_norm.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.post_moe_norm.weight": "pytorch_model-00029.safetensors",
    "model.layers.28.block_sparse_moe.gate.weight": "pytorch_model-00029.safetensors",
    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.pre_attn_norm.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.post_attn_norm.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.pre_moe_norm.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.post_moe_norm.weight": "pytorch_model-00030.safetensors",
    "model.layers.29.block_sparse_moe.gate.weight": "pytorch_model-00030.safetensors",
    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.pre_attn_norm.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.post_attn_norm.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.pre_moe_norm.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.post_moe_norm.weight": "pytorch_model-00031.safetensors",
    "model.layers.30.block_sparse_moe.gate.weight": "pytorch_model-00031.safetensors",
    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.pre_attn_norm.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.post_attn_norm.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.pre_moe_norm.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.post_moe_norm.weight": "pytorch_model-00032.safetensors",
    "model.layers.31.block_sparse_moe.gate.weight": "pytorch_model-00032.safetensors",
    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.pre_attn_norm.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.post_attn_norm.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.pre_moe_norm.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.post_moe_norm.weight": "pytorch_model-00033.safetensors",
    "model.layers.32.block_sparse_moe.gate.weight": "pytorch_model-00033.safetensors",
    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.pre_attn_norm.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.post_attn_norm.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.pre_moe_norm.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.post_moe_norm.weight": "pytorch_model-00034.safetensors",
    "model.layers.33.block_sparse_moe.gate.weight": "pytorch_model-00034.safetensors",
    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.pre_attn_norm.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.post_attn_norm.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.pre_moe_norm.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.post_moe_norm.weight": "pytorch_model-00035.safetensors",
    "model.layers.34.block_sparse_moe.gate.weight": "pytorch_model-00035.safetensors",
    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.pre_attn_norm.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.post_attn_norm.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.pre_moe_norm.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.post_moe_norm.weight": "pytorch_model-00036.safetensors",
    "model.layers.35.block_sparse_moe.gate.weight": "pytorch_model-00036.safetensors",
    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.pre_attn_norm.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.post_attn_norm.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.pre_moe_norm.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.post_moe_norm.weight": "pytorch_model-00037.safetensors",
    "model.layers.36.block_sparse_moe.gate.weight": "pytorch_model-00037.safetensors",
    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.pre_attn_norm.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.post_attn_norm.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.pre_moe_norm.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.post_moe_norm.weight": "pytorch_model-00038.safetensors",
    "model.layers.37.block_sparse_moe.gate.weight": "pytorch_model-00038.safetensors",
    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.pre_attn_norm.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.post_attn_norm.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.pre_moe_norm.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.post_moe_norm.weight": "pytorch_model-00039.safetensors",
    "model.layers.38.block_sparse_moe.gate.weight": "pytorch_model-00039.safetensors",
    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.pre_attn_norm.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.post_attn_norm.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.pre_moe_norm.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.post_moe_norm.weight": "pytorch_model-00040.safetensors",
    "model.layers.39.block_sparse_moe.gate.weight": "pytorch_model-00040.safetensors",
    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.pre_attn_norm.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.post_attn_norm.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.pre_moe_norm.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.post_moe_norm.weight": "pytorch_model-00041.safetensors",
    "model.layers.40.block_sparse_moe.gate.weight": "pytorch_model-00041.safetensors",
    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.pre_attn_norm.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.post_attn_norm.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.pre_moe_norm.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.post_moe_norm.weight": "pytorch_model-00042.safetensors",
    "model.layers.41.block_sparse_moe.gate.weight": "pytorch_model-00042.safetensors",
    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.pre_attn_norm.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.post_attn_norm.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.pre_moe_norm.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.post_moe_norm.weight": "pytorch_model-00043.safetensors",
    "model.layers.42.block_sparse_moe.gate.weight": "pytorch_model-00043.safetensors",
    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.pre_attn_norm.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.post_attn_norm.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.pre_moe_norm.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.post_moe_norm.weight": "pytorch_model-00044.safetensors",
    "model.layers.43.block_sparse_moe.gate.weight": "pytorch_model-00044.safetensors",
    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.pre_attn_norm.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.post_attn_norm.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.pre_moe_norm.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.post_moe_norm.weight": "pytorch_model-00045.safetensors",
    "model.layers.44.block_sparse_moe.gate.weight": "pytorch_model-00045.safetensors",
    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.pre_attn_norm.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.post_attn_norm.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.pre_moe_norm.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.post_moe_norm.weight": "pytorch_model-00046.safetensors",
    "model.layers.45.block_sparse_moe.gate.weight": "pytorch_model-00046.safetensors",
    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.pre_attn_norm.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.post_attn_norm.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.pre_moe_norm.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.post_moe_norm.weight": "pytorch_model-00047.safetensors",
    "model.layers.46.block_sparse_moe.gate.weight": "pytorch_model-00047.safetensors",
    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.pre_attn_norm.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.post_attn_norm.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.pre_moe_norm.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.post_moe_norm.weight": "pytorch_model-00048.safetensors",
    "model.layers.47.block_sparse_moe.gate.weight": "pytorch_model-00048.safetensors",
    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.pre_attn_norm.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.post_attn_norm.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.pre_moe_norm.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.post_moe_norm.weight": "pytorch_model-00049.safetensors",
    "model.layers.48.block_sparse_moe.gate.weight": "pytorch_model-00049.safetensors",
    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.pre_attn_norm.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.post_attn_norm.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.pre_moe_norm.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.post_moe_norm.weight": "pytorch_model-00050.safetensors",
    "model.layers.49.block_sparse_moe.gate.weight": "pytorch_model-00050.safetensors",
    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.pre_attn_norm.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.post_attn_norm.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.pre_moe_norm.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.post_moe_norm.weight": "pytorch_model-00051.safetensors",
    "model.layers.50.block_sparse_moe.gate.weight": "pytorch_model-00051.safetensors",
    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.pre_attn_norm.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.post_attn_norm.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.pre_moe_norm.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.post_moe_norm.weight": "pytorch_model-00052.safetensors",
    "model.layers.51.block_sparse_moe.gate.weight": "pytorch_model-00052.safetensors",
    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.pre_attn_norm.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.post_attn_norm.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.pre_moe_norm.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.post_moe_norm.weight": "pytorch_model-00053.safetensors",
    "model.layers.52.block_sparse_moe.gate.weight": "pytorch_model-00053.safetensors",
    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.pre_attn_norm.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.post_attn_norm.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.pre_moe_norm.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.post_moe_norm.weight": "pytorch_model-00054.safetensors",
    "model.layers.53.block_sparse_moe.gate.weight": "pytorch_model-00054.safetensors",
    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.pre_attn_norm.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.post_attn_norm.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.pre_moe_norm.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.post_moe_norm.weight": "pytorch_model-00055.safetensors",
    "model.layers.54.block_sparse_moe.gate.weight": "pytorch_model-00055.safetensors",
    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.pre_attn_norm.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.post_attn_norm.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.pre_moe_norm.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.post_moe_norm.weight": "pytorch_model-00056.safetensors",
    "model.layers.55.block_sparse_moe.gate.weight": "pytorch_model-00056.safetensors",
    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.pre_attn_norm.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.post_attn_norm.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.pre_moe_norm.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.post_moe_norm.weight": "pytorch_model-00057.safetensors",
    "model.layers.56.block_sparse_moe.gate.weight": "pytorch_model-00057.safetensors",
    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.pre_attn_norm.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.post_attn_norm.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.pre_moe_norm.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.post_moe_norm.weight": "pytorch_model-00058.safetensors",
    "model.layers.57.block_sparse_moe.gate.weight": "pytorch_model-00058.safetensors",
    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.pre_attn_norm.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.post_attn_norm.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.pre_moe_norm.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.post_moe_norm.weight": "pytorch_model-00059.safetensors",
    "model.layers.58.block_sparse_moe.gate.weight": "pytorch_model-00059.safetensors",
    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.pre_attn_norm.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.post_attn_norm.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.pre_moe_norm.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.post_moe_norm.weight": "pytorch_model-00060.safetensors",
    "model.layers.59.block_sparse_moe.gate.weight": "pytorch_model-00060.safetensors",
    "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.mlp.down_proj.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.mlp.up_proj.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.pre_attn_norm.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.post_attn_norm.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.pre_moe_norm.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.post_moe_norm.weight": "pytorch_model-00061.safetensors",
    "model.layers.60.block_sparse_moe.gate.weight": "pytorch_model-00061.safetensors",
    "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.mlp.down_proj.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.mlp.up_proj.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.pre_attn_norm.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.post_attn_norm.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.pre_moe_norm.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.post_moe_norm.weight": "pytorch_model-00062.safetensors",
    "model.layers.61.block_sparse_moe.gate.weight": "pytorch_model-00062.safetensors",
    "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.mlp.down_proj.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.mlp.up_proj.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.pre_attn_norm.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.post_attn_norm.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.pre_moe_norm.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.post_moe_norm.weight": "pytorch_model-00063.safetensors",
    "model.layers.62.block_sparse_moe.gate.weight": "pytorch_model-00063.safetensors",
    "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.mlp.down_proj.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.mlp.up_proj.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.pre_attn_norm.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.post_attn_norm.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.pre_moe_norm.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.post_moe_norm.weight": "pytorch_model-00064.safetensors",
    "model.layers.63.block_sparse_moe.gate.weight": "pytorch_model-00064.safetensors",
    "lm_head.weight": "pytorch_model-00064.safetensors",
    "model.embed_tokens.weight": "pytorch_model-00064.safetensors",
    "model.norm.weight": "pytorch_model-00064.safetensors"
  }
}