{
    "metadata": {
        "total_size": 5766570816
    },
    "weight_map": {
        "linear_proj_audio.0.bias": "model-00002-of-00002.safetensors",
        "linear_proj_audio.0.weight": "model-00002-of-00002.safetensors",
        "linear_proj_audio.2.bias": "model-00002-of-00002.safetensors",
        "linear_proj_audio.2.weight": "model-00002-of-00002.safetensors",
        "linear_proj_audio.4.bias": "model-00002-of-00002.safetensors",
        "linear_proj_audio.4.weight": "model-00002-of-00002.safetensors",
        "linear_proj_audio.7.bias": "model-00002-of-00002.safetensors",
        "linear_proj_audio.7.biases": "model-00002-of-00002.safetensors",
        "linear_proj_audio.7.scales": "model-00002-of-00002.safetensors",
        "linear_proj_audio.7.weight": "model-00002-of-00002.safetensors",
        "lm_head.biases": "model-00002-of-00002.safetensors",
        "lm_head.scales": "model-00002-of-00002.safetensors",
        "lm_head.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.0.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.0.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.1.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.10.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.11.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.12.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.13.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.14.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.15.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.16.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.17.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.18.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.19.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.2.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.20.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.21.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.22.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.23.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.24.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.25.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.26.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.26.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.26.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.26.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.26.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.26.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.26.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.26.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.26.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.26.mlp.0.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.26.mlp.0.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.26.mlp.2.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.26.mlp.2.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.26.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.26.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.27.attn.key.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.attn.out.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.attn.out.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.attn.query.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.attn.query.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.attn.value.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.attn.value.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.attn_ln.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.attn_ln.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.mlp.0.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.mlp.0.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.mlp.2.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.mlp.2.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.mlp_ln.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.27.mlp_ln.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.attn.key.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.attn.out.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.attn.out.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.attn.query.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.attn.query.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.attn.value.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.attn.value.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.attn_ln.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.attn_ln.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.mlp.0.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.mlp.0.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.mlp.2.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.mlp.2.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.mlp_ln.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.28.mlp_ln.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.attn.key.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.attn.out.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.attn.out.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.attn.query.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.attn.query.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.attn.value.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.attn.value.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.attn_ln.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.attn_ln.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.mlp.0.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.mlp.0.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.mlp.2.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.mlp.2.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.mlp_ln.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.29.mlp_ln.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.3.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.3.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.30.attn.key.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.attn.out.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.attn.out.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.attn.query.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.attn.query.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.attn.value.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.attn.value.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.attn_ln.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.attn_ln.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.mlp.0.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.mlp.0.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.mlp.2.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.mlp.2.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.mlp_ln.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.30.mlp_ln.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.attn.key.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.attn.out.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.attn.out.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.attn.query.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.attn.query.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.attn.value.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.attn.value.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.attn_ln.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.attn_ln.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.mlp.0.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.mlp.0.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.mlp.2.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.mlp.2.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.mlp_ln.bias": "model-00002-of-00002.safetensors",
        "model.audio.blocks.31.mlp_ln.weight": "model-00002-of-00002.safetensors",
        "model.audio.blocks.4.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.4.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.5.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.6.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.7.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.8.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.attn.key.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.attn.out.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.attn.out.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.attn.query.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.attn.query.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.attn.value.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.attn.value.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.attn_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.attn_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.mlp.0.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.mlp.0.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.mlp.2.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.mlp.2.weight": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.mlp_ln.bias": "model-00001-of-00002.safetensors",
        "model.audio.blocks.9.mlp_ln.weight": "model-00001-of-00002.safetensors",
        "model.audio.conv1.bias": "model-00001-of-00002.safetensors",
        "model.audio.conv1.weight": "model-00001-of-00002.safetensors",
        "model.audio.conv2.bias": "model-00001-of-00002.safetensors",
        "model.audio.conv2.weight": "model-00001-of-00002.safetensors",
        "model.audio.ln_post.bias": "model-00002-of-00002.safetensors",
        "model.audio.ln_post.weight": "model-00002-of-00002.safetensors",
        "model.audio.positional_embedding": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.dense.biases": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.dense.scales": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.kv_b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.kv_b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.kv_b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.q_a_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.q_a_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.q_a_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.q_b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.q_b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.11.attention.q_b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.dense.biases": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.dense.scales": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.dense.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.kv_b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.kv_b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.kv_b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.q_a_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.q_a_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.q_a_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.q_b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.q_b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.15.attention.q_b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.dense.biases": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.dense.scales": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.dense.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.kv_b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.kv_b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.kv_b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.q_a_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.q_a_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.q_a_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.q_b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.q_b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.19.attention.q_b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.dense.biases": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.dense.scales": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.dense.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.kv_b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.kv_b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.kv_b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.q_a_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.q_a_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.q_a_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.q_b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.q_b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.23.attention.q_b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.dense.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.dense.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.kv_b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.kv_b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.kv_b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.q_a_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.q_a_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.q_a_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.q_b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.q_b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.attention.q_b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.dense.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.dense.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.kv_b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.kv_b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.kv_b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.q_a_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.q_a_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.q_a_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.q_b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.q_b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.attention.q_b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.A_log": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.b_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.b_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.b_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.dt_bias": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.f_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.f_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.f_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.g_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.g_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.g_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.k_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.k_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.k_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.k_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.o_norm.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.o_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.o_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.o_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.q_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.q_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.q_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.q_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.v_conv1d.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.v_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.v_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.attention.v_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.gate.expert_bias": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.gate.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
        "model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
        "model.norm.weight": "model-00001-of-00002.safetensors",
        "model.word_embeddings.biases": "model-00001-of-00002.safetensors",
        "model.word_embeddings.scales": "model-00001-of-00002.safetensors",
        "model.word_embeddings.weight": "model-00001-of-00002.safetensors"
    }
}