{
    "metadata": {
        "total_size": 3222321152
    },
    "weight_map": {
        "decoder.embeddings.0.weight": "model.safetensors",
        "decoder.embeddings.1.weight": "model.safetensors",
        "decoder.embeddings.2.weight": "model.safetensors",
        "decoder.embeddings.3.weight": "model.safetensors",
        "decoder.embeddings.4.weight": "model.safetensors",
        "decoder.embeddings.5.weight": "model.safetensors",
        "decoder.embeddings.6.weight": "model.safetensors",
        "decoder.embeddings.7.weight": "model.safetensors",
        "decoder.embeddings.8.weight": "model.safetensors",
        "decoder.layers.0.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.0.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.0.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.0.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.0.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.0.mlp.wo.weight": "model.safetensors",
        "decoder.layers.0.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.0.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.0.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.0.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.0.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.0.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.0.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.1.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.1.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.1.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.1.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.1.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.1.mlp.wo.weight": "model.safetensors",
        "decoder.layers.1.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.1.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.1.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.1.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.1.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.1.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.1.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.10.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.10.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.10.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.10.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.10.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.10.mlp.wo.weight": "model.safetensors",
        "decoder.layers.10.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.10.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.10.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.10.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.10.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.10.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.10.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.11.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.11.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.11.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.11.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.11.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.11.mlp.wo.weight": "model.safetensors",
        "decoder.layers.11.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.11.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.11.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.11.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.11.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.11.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.11.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.12.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.12.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.12.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.12.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.12.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.12.mlp.wo.weight": "model.safetensors",
        "decoder.layers.12.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.12.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.12.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.12.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.12.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.12.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.12.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.13.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.13.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.13.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.13.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.13.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.13.mlp.wo.weight": "model.safetensors",
        "decoder.layers.13.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.13.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.13.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.13.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.13.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.13.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.13.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.14.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.14.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.14.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.14.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.14.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.14.mlp.wo.weight": "model.safetensors",
        "decoder.layers.14.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.14.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.14.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.14.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.14.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.14.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.14.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.15.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.15.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.15.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.15.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.15.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.15.mlp.wo.weight": "model.safetensors",
        "decoder.layers.15.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.15.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.15.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.15.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.15.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.15.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.15.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.16.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.16.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.16.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.16.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.16.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.16.mlp.wo.weight": "model.safetensors",
        "decoder.layers.16.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.16.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.16.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.16.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.16.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.16.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.16.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.17.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.17.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.17.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.17.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.17.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.17.mlp.wo.weight": "model.safetensors",
        "decoder.layers.17.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.17.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.17.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.17.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.17.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.17.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.17.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.2.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.2.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.2.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.2.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.2.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.2.mlp.wo.weight": "model.safetensors",
        "decoder.layers.2.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.2.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.2.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.2.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.2.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.2.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.2.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.3.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.3.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.3.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.3.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.3.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.3.mlp.wo.weight": "model.safetensors",
        "decoder.layers.3.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.3.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.3.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.3.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.3.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.3.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.3.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.4.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.4.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.4.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.4.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.4.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.4.mlp.wo.weight": "model.safetensors",
        "decoder.layers.4.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.4.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.4.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.4.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.4.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.4.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.4.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.5.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.5.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.5.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.5.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.5.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.5.mlp.wo.weight": "model.safetensors",
        "decoder.layers.5.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.5.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.5.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.5.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.5.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.5.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.5.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.6.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.6.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.6.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.6.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.6.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.6.mlp.wo.weight": "model.safetensors",
        "decoder.layers.6.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.6.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.6.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.6.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.6.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.6.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.6.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.7.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.7.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.7.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.7.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.7.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.7.mlp.wo.weight": "model.safetensors",
        "decoder.layers.7.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.7.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.7.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.7.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.7.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.7.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.7.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.8.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.8.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.8.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.8.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.8.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.8.mlp.wo.weight": "model.safetensors",
        "decoder.layers.8.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.8.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.8.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.8.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.8.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.8.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.8.self_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.9.cross_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.9.cross_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.9.cross_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.9.cross_attention.v_proj.weight": "model.safetensors",
        "decoder.layers.9.mlp.wi_fused.weight": "model.safetensors",
        "decoder.layers.9.mlp.wo.weight": "model.safetensors",
        "decoder.layers.9.pre_ca_norm.weight": "model.safetensors",
        "decoder.layers.9.pre_mlp_norm.weight": "model.safetensors",
        "decoder.layers.9.pre_sa_norm.weight": "model.safetensors",
        "decoder.layers.9.self_attention.k_proj.weight": "model.safetensors",
        "decoder.layers.9.self_attention.o_proj.weight": "model.safetensors",
        "decoder.layers.9.self_attention.q_proj.weight": "model.safetensors",
        "decoder.layers.9.self_attention.v_proj.weight": "model.safetensors",
        "decoder.logits_dense.weight": "model.safetensors",
        "decoder.norm.weight": "model.safetensors",
        "encoder.embedding.weight": "model.safetensors",
        "encoder.layers.0.mlp.wi_fused.weight": "model.safetensors",
        "encoder.layers.0.mlp.wo.weight": "model.safetensors",
        "encoder.layers.0.post_sa_norm.weight": "model.safetensors",
        "encoder.layers.0.pre_sa_norm.weight": "model.safetensors",
        "encoder.layers.0.self_attention.k_proj.weight": "model.safetensors",
        "encoder.layers.0.self_attention.o_proj.weight": "model.safetensors",
        "encoder.layers.0.self_attention.q_proj.weight": "model.safetensors",
        "encoder.layers.0.self_attention.v_proj.weight": "model.safetensors",
        "encoder.layers.1.mlp.wi_fused.weight": "model.safetensors",
        "encoder.layers.1.mlp.wo.weight": "model.safetensors",
        "encoder.layers.1.post_sa_norm.weight": "model.safetensors",
        "encoder.layers.1.pre_sa_norm.weight": "model.safetensors",
        "encoder.layers.1.self_attention.k_proj.weight": "model.safetensors",
        "encoder.layers.1.self_attention.o_proj.weight": "model.safetensors",
        "encoder.layers.1.self_attention.q_proj.weight": "model.safetensors",
        "encoder.layers.1.self_attention.v_proj.weight": "model.safetensors",
        "encoder.layers.10.mlp.wi_fused.weight": "model.safetensors",
        "encoder.layers.10.mlp.wo.weight": "model.safetensors",
        "encoder.layers.10.post_sa_norm.weight": "model.safetensors",
        "encoder.layers.10.pre_sa_norm.weight": "model.safetensors",
        "encoder.layers.10.self_attention.k_proj.weight": "model.safetensors",
        "encoder.layers.10.self_attention.o_proj.weight": "model.safetensors",
        "encoder.layers.10.self_attention.q_proj.weight": "model.safetensors",
        "encoder.layers.10.self_attention.v_proj.weight": "model.safetensors",
        "encoder.layers.11.mlp.wi_fused.weight": "model.safetensors",
        "encoder.layers.11.mlp.wo.weight": "model.safetensors",
        "encoder.layers.11.post_sa_norm.weight": "model.safetensors",
        "encoder.layers.11.pre_sa_norm.weight": "model.safetensors",
        "encoder.layers.11.self_attention.k_proj.weight": "model.safetensors",
        "encoder.layers.11.self_attention.o_proj.weight": "model.safetensors",
        "encoder.layers.11.self_attention.q_proj.weight": "model.safetensors",
        "encoder.layers.11.self_attention.v_proj.weight": "model.safetensors",
        "encoder.layers.2.mlp.wi_fused.weight": "model.safetensors",
        "encoder.layers.2.mlp.wo.weight": "model.safetensors",
        "encoder.layers.2.post_sa_norm.weight": "model.safetensors",
        "encoder.layers.2.pre_sa_norm.weight": "model.safetensors",
        "encoder.layers.2.self_attention.k_proj.weight": "model.safetensors",
        "encoder.layers.2.self_attention.o_proj.weight": "model.safetensors",
        "encoder.layers.2.self_attention.q_proj.weight": "model.safetensors",
        "encoder.layers.2.self_attention.v_proj.weight": "model.safetensors",
        "encoder.layers.3.mlp.wi_fused.weight": "model.safetensors",
        "encoder.layers.3.mlp.wo.weight": "model.safetensors",
        "encoder.layers.3.post_sa_norm.weight": "model.safetensors",
        "encoder.layers.3.pre_sa_norm.weight": "model.safetensors",
        "encoder.layers.3.self_attention.k_proj.weight": "model.safetensors",
        "encoder.layers.3.self_attention.o_proj.weight": "model.safetensors",
        "encoder.layers.3.self_attention.q_proj.weight": "model.safetensors",
        "encoder.layers.3.self_attention.v_proj.weight": "model.safetensors",
        "encoder.layers.4.mlp.wi_fused.weight": "model.safetensors",
        "encoder.layers.4.mlp.wo.weight": "model.safetensors",
        "encoder.layers.4.post_sa_norm.weight": "model.safetensors",
        "encoder.layers.4.pre_sa_norm.weight": "model.safetensors",
        "encoder.layers.4.self_attention.k_proj.weight": "model.safetensors",
        "encoder.layers.4.self_attention.o_proj.weight": "model.safetensors",
        "encoder.layers.4.self_attention.q_proj.weight": "model.safetensors",
        "encoder.layers.4.self_attention.v_proj.weight": "model.safetensors",
        "encoder.layers.5.mlp.wi_fused.weight": "model.safetensors",
        "encoder.layers.5.mlp.wo.weight": "model.safetensors",
        "encoder.layers.5.post_sa_norm.weight": "model.safetensors",
        "encoder.layers.5.pre_sa_norm.weight": "model.safetensors",
        "encoder.layers.5.self_attention.k_proj.weight": "model.safetensors",
        "encoder.layers.5.self_attention.o_proj.weight": "model.safetensors",
        "encoder.layers.5.self_attention.q_proj.weight": "model.safetensors",
        "encoder.layers.5.self_attention.v_proj.weight": "model.safetensors",
        "encoder.layers.6.mlp.wi_fused.weight": "model.safetensors",
        "encoder.layers.6.mlp.wo.weight": "model.safetensors",
        "encoder.layers.6.post_sa_norm.weight": "model.safetensors",
        "encoder.layers.6.pre_sa_norm.weight": "model.safetensors",
        "encoder.layers.6.self_attention.k_proj.weight": "model.safetensors",
        "encoder.layers.6.self_attention.o_proj.weight": "model.safetensors",
        "encoder.layers.6.self_attention.q_proj.weight": "model.safetensors",
        "encoder.layers.6.self_attention.v_proj.weight": "model.safetensors",
        "encoder.layers.7.mlp.wi_fused.weight": "model.safetensors",
        "encoder.layers.7.mlp.wo.weight": "model.safetensors",
        "encoder.layers.7.post_sa_norm.weight": "model.safetensors",
        "encoder.layers.7.pre_sa_norm.weight": "model.safetensors",
        "encoder.layers.7.self_attention.k_proj.weight": "model.safetensors",
        "encoder.layers.7.self_attention.o_proj.weight": "model.safetensors",
        "encoder.layers.7.self_attention.q_proj.weight": "model.safetensors",
        "encoder.layers.7.self_attention.v_proj.weight": "model.safetensors",
        "encoder.layers.8.mlp.wi_fused.weight": "model.safetensors",
        "encoder.layers.8.mlp.wo.weight": "model.safetensors",
        "encoder.layers.8.post_sa_norm.weight": "model.safetensors",
        "encoder.layers.8.pre_sa_norm.weight": "model.safetensors",
        "encoder.layers.8.self_attention.k_proj.weight": "model.safetensors",
        "encoder.layers.8.self_attention.o_proj.weight": "model.safetensors",
        "encoder.layers.8.self_attention.q_proj.weight": "model.safetensors",
        "encoder.layers.8.self_attention.v_proj.weight": "model.safetensors",
        "encoder.layers.9.mlp.wi_fused.weight": "model.safetensors",
        "encoder.layers.9.mlp.wo.weight": "model.safetensors",
        "encoder.layers.9.post_sa_norm.weight": "model.safetensors",
        "encoder.layers.9.pre_sa_norm.weight": "model.safetensors",
        "encoder.layers.9.self_attention.k_proj.weight": "model.safetensors",
        "encoder.layers.9.self_attention.o_proj.weight": "model.safetensors",
        "encoder.layers.9.self_attention.q_proj.weight": "model.safetensors",
        "encoder.layers.9.self_attention.v_proj.weight": "model.safetensors",
        "encoder.norm.weight": "model.safetensors"
    }
}