model.safetensors.index.json

{
  "metadata": {
    "total_size": 83746306688
  },
  "weight_map": {
    "lm_head.bias": "model-00017-of-00017.safetensors",
    "lm_head.weight": "model-00017-of-00017.safetensors",
    "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.input_layernorm.bias": "model-00001-of-00017.safetensors",
    "model.layers.0.input_layernorm.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00017.safetensors",
    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00017.safetensors",
    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.input_layernorm.bias": "model-00002-of-00017.safetensors",
    "model.layers.1.input_layernorm.weight": "model-00002-of-00017.safetensors",
    "model.layers.1.post_attention_layernorm.bias": "model-00002-of-00017.safetensors",
    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00017.safetensors",
    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.10.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.11.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.11.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.11.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.12.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.12.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.12.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.13.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.13.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.14.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.15.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.15.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.15.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.8.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.8.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.9.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.input_layernorm.bias": "model-00006-of-00017.safetensors",
    "model.layers.10.input_layernorm.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.post_attention_layernorm.bias": "model-00006-of-00017.safetensors",
    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.self_attn.o_proj.bias": "model-00006-of-00017.safetensors",
    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
    "model.layers.10.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.10.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.10.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.11.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.11.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.11.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.12.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.12.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.12.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.13.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.13.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.13.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.14.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.14.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.14.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.15.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.15.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.15.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.8.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.8.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.8.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.9.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.9.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.experts.9.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.block_sparse_moe.gate.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.input_layernorm.bias": "model-00007-of-00017.safetensors",
    "model.layers.11.input_layernorm.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.post_attention_layernorm.bias": "model-00007-of-00017.safetensors",
    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
    "model.layers.11.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.self_attn.o_proj.bias": "model-00006-of-00017.safetensors",
    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
    "model.layers.11.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.10.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.10.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.11.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.11.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.11.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.12.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.12.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.12.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.13.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.13.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.13.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.14.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.14.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.14.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.15.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.15.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.15.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.8.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.8.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.8.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.9.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.9.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.experts.9.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.block_sparse_moe.gate.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.input_layernorm.bias": "model-00007-of-00017.safetensors",
    "model.layers.12.input_layernorm.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.post_attention_layernorm.bias": "model-00007-of-00017.safetensors",
    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.self_attn.o_proj.bias": "model-00007-of-00017.safetensors",
    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
    "model.layers.12.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.10.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.10.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.10.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.11.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.11.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.11.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.12.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.12.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.12.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.13.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.13.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.13.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.14.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.14.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.14.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.15.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.15.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.15.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.8.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.8.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.8.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.9.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.9.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.experts.9.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.block_sparse_moe.gate.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.input_layernorm.bias": "model-00008-of-00017.safetensors",
    "model.layers.13.input_layernorm.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.post_attention_layernorm.bias": "model-00008-of-00017.safetensors",
    "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
    "model.layers.13.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.self_attn.o_proj.bias": "model-00007-of-00017.safetensors",
    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
    "model.layers.13.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.10.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.10.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.10.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.11.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.11.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.11.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.12.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.12.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.12.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.13.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.13.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.13.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.14.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.14.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.14.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.15.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.15.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.15.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.8.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.8.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.8.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.9.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.9.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.experts.9.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.block_sparse_moe.gate.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.input_layernorm.bias": "model-00008-of-00017.safetensors",
    "model.layers.14.input_layernorm.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.post_attention_layernorm.bias": "model-00008-of-00017.safetensors",
    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
    "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.self_attn.o_proj.bias": "model-00008-of-00017.safetensors",
    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
    "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
    "model.layers.14.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
    "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.10.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.10.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.10.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.11.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.11.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.11.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.12.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.12.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.12.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.13.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.13.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.13.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.14.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.14.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.14.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.15.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.15.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.15.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.8.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.8.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.8.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.9.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.9.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.experts.9.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.input_layernorm.bias": "model-00009-of-00017.safetensors",
    "model.layers.15.input_layernorm.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.post_attention_layernorm.bias": "model-00009-of-00017.safetensors",
    "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
    "model.layers.15.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.self_attn.o_proj.bias": "model-00008-of-00017.safetensors",
    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
    "model.layers.15.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.10.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.10.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.10.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.11.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.11.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.11.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.12.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.12.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.12.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.13.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.13.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.13.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.14.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.14.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.14.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.15.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.15.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.15.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.8.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.8.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.8.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.9.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.9.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.experts.9.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.block_sparse_moe.gate.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.input_layernorm.bias": "model-00009-of-00017.safetensors",
    "model.layers.16.input_layernorm.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.post_attention_layernorm.bias": "model-00009-of-00017.safetensors",
    "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
    "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.self_attn.o_proj.bias": "model-00009-of-00017.safetensors",
    "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
    "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
    "model.layers.16.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
    "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.10.w1.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.10.w2.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.10.w3.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.11.w1.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.11.w2.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.11.w3.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.12.w1.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.12.w2.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.12.w3.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.13.w1.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.13.w2.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.13.w3.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.14.w1.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.14.w2.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.14.w3.weight": "model-00010-of-00017.safetensors",
    "model.layers.17.block_sparse_moe.experts.15.w1.weight": "model-00010-of-00017.safetensors",