{ "metadata": { "total_size": 52815976448 }, "weight_map": { "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.2.layer_norm.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.2.mlp.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.0.layer.2.mlp.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.layer_norm.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_0.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_0.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_1.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_1.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_10.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_10.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_100.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_100.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_101.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_101.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_102.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_102.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_103.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_103.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_104.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_104.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_105.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_105.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_106.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_106.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_107.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_107.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_108.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_108.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_109.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_109.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_11.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_11.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_110.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_110.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_111.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_111.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_112.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_112.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_113.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_113.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_114.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_114.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_115.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_115.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_116.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_116.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_117.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_117.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_118.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_118.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_119.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_119.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_12.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_12.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_120.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_120.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_121.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_121.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_122.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_122.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_123.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_123.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_124.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_124.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_125.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_125.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_126.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_126.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_127.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_127.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_13.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_13.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_14.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_14.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_15.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_15.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_16.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_16.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_17.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_17.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_18.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_18.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_19.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_19.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_2.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_2.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_20.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_20.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_21.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_21.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_22.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_22.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_23.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_23.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_24.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_24.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_25.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_25.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_26.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_26.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_27.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_27.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_28.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_28.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_29.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_29.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_3.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_3.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_30.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_30.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_31.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_31.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_32.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_32.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_33.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_33.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_34.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_34.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_35.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_35.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_36.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_36.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_37.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_37.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_38.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_38.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_39.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_39.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_4.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_4.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_40.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_40.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_41.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_41.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_42.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_42.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_43.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_43.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_44.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_44.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_45.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_45.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_46.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_46.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_47.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_47.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_48.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_48.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_49.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_49.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_5.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_5.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_50.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_50.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_51.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_51.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_52.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_52.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_53.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_53.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_54.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_54.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_55.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_55.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_56.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_56.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_57.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_57.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_58.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_58.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_59.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_59.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_6.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_6.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_60.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_60.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_61.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_61.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_62.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_62.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_63.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_63.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_64.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_64.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_65.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_65.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_66.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_66.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_67.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_67.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_68.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_68.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_69.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_69.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_7.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_7.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_70.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_70.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_71.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_71.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_72.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_72.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_73.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_73.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_74.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_74.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_75.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_75.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_76.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_76.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_77.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_77.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_78.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_78.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_79.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_79.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_8.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_8.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_80.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_80.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_81.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_81.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_82.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_82.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_83.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_83.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_84.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_84.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_85.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_85.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_86.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_86.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_87.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_87.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_88.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_88.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_89.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_89.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_9.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_9.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_90.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_90.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_91.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_91.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_92.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_92.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_93.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_93.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_94.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_94.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_95.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_95.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_96.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_96.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_97.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_97.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_98.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_98.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_99.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.experts.expert_99.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.1.layer.2.mlp.router.classifier.weight": "model-00003-of-00006.safetensors", "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.10.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.10.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.10.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.10.layer.2.mlp.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.10.layer.2.mlp.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_0.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_0.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_1.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_1.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_10.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_10.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_100.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_100.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_101.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_101.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_102.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_102.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_103.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_103.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_104.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_104.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_105.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_105.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_106.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_106.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_107.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_107.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_108.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_108.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_109.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_109.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_11.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_11.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_110.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_110.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_111.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_111.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_112.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_112.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_113.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_113.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_114.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_114.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_115.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_115.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_116.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_116.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_117.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_117.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_118.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_118.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_119.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_119.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_12.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_12.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_120.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_120.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_121.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_121.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_122.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_122.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_123.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_123.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_124.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_124.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_125.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_125.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_126.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_126.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_127.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_127.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_13.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_13.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_14.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_14.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_15.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_15.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_16.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_16.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_17.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_17.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_18.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_18.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_19.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_19.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_2.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_2.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_20.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_20.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_21.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_21.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_22.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_22.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_23.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_23.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_24.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_24.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_25.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_25.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_26.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_26.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_27.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_27.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_28.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_28.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_29.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_29.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_3.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_3.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_30.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_30.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_31.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_31.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_32.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_32.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_33.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_33.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_34.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_34.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_35.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_35.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_36.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_36.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_37.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_37.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_38.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_38.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_39.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_39.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_4.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_4.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_40.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_40.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_41.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_41.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_42.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_42.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_43.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_43.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_44.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_44.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_45.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_45.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_46.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_46.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_47.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_47.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_48.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_48.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_49.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_49.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_5.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_5.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_50.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_50.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_51.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_51.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_52.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_52.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_53.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_53.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_54.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_54.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_55.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_55.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_56.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_56.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_57.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_57.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_58.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_58.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_59.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_59.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_6.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_6.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_60.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_60.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_61.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_61.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_62.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_62.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_63.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_63.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_64.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_64.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_65.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_65.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_66.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_66.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_67.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_67.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_68.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_68.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_69.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_69.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_7.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_7.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_70.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_70.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_71.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_71.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_72.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_72.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_73.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_73.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_74.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_74.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_75.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_75.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_76.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_76.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_77.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_77.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_78.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_78.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_79.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_79.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_8.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_8.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_80.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_80.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_81.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_81.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_82.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_82.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_83.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_83.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_84.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_84.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_85.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_85.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_86.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_86.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_87.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_87.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_88.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_88.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_89.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_89.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_9.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_9.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_90.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_90.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_91.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_91.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_92.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_92.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_93.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_93.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_94.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_94.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_95.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_95.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_96.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_96.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_97.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_97.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_98.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_98.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_99.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.experts.expert_99.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.11.layer.2.mlp.router.classifier.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.2.mlp.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.12.layer.2.mlp.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_0.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_0.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_1.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_1.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_10.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_10.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_100.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_100.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_101.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_101.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_102.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_102.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_103.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_103.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_104.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_104.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_105.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_105.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_106.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_106.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_107.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_107.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_108.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_108.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_109.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_109.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_11.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_11.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_110.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_110.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_111.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_111.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_112.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_112.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_113.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_113.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_114.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_114.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_115.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_115.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_116.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_116.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_117.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_117.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_118.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_118.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_119.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_119.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_12.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_12.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_120.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_120.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_121.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_121.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_122.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_122.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_123.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_123.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_124.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_124.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_125.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_125.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_126.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_126.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_127.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_127.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_13.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_13.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_14.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_14.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_15.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_15.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_16.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_16.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_17.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_17.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_18.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_18.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_19.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_19.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_2.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_2.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_20.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_20.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_21.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_21.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_22.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_22.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_23.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_23.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_24.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_24.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_25.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_25.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_26.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_26.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_27.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_27.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_28.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_28.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_29.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_29.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_3.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_3.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_30.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_30.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_31.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_31.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_32.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_32.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_33.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_33.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_34.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_34.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_35.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_35.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_36.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_36.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_37.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_37.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_38.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_38.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_39.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_39.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_4.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_4.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_40.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_40.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_41.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_41.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_42.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_42.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_43.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_43.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_44.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_44.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_45.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_45.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_46.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_46.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_47.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_47.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_48.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_48.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_49.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_49.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_5.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_5.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_50.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_50.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_51.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_51.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_52.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_52.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_53.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_53.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_54.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_54.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_55.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_55.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_56.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_56.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_57.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_57.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_58.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_58.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_59.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_59.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_6.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_6.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_60.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_60.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_61.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_61.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_62.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_62.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_63.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_63.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_64.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_64.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_65.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_65.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_66.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_66.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_67.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_67.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_68.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_68.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_69.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_69.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_7.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_7.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_70.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_70.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_71.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_71.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_72.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_72.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_73.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_73.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_74.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_74.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_75.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_75.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_76.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_76.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_77.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_77.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_78.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_78.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_79.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_79.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_8.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_8.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_80.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_80.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_81.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_81.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_82.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_82.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_83.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_83.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_84.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_84.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_85.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_85.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_86.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_86.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_87.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_87.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_88.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_88.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_89.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_89.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_9.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_9.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_90.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_90.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_91.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_91.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_92.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_92.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_93.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_93.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_94.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_94.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_95.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_95.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_96.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_96.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_97.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_97.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_98.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_98.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_99.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.experts.expert_99.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.13.layer.2.mlp.router.classifier.weight": "model-00004-of-00006.safetensors", "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.14.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.14.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.14.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.14.layer.2.mlp.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.14.layer.2.mlp.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_0.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_0.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_1.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_1.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_10.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_10.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_100.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_100.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_101.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_101.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_102.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_102.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_103.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_103.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_104.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_104.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_105.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_105.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_106.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_106.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_107.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_107.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_108.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_108.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_109.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_109.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_11.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_11.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_110.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_110.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_111.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_111.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_112.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_112.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_113.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_113.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_114.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_114.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_115.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_115.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_116.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_116.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_117.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_117.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_118.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_118.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_119.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_119.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_12.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_12.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_120.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_120.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_121.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_121.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_122.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_122.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_123.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_123.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_124.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_124.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_125.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_125.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_126.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_126.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_127.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_127.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_13.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_13.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_14.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_14.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_15.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_15.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_16.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_16.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_17.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_17.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_18.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_18.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_19.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_19.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_2.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_2.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_20.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_20.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_21.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_21.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_22.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_22.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_23.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_23.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_24.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_24.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_25.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_25.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_26.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_26.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_27.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_27.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_28.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_28.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_29.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_29.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_3.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_3.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_30.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_30.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_31.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_31.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_32.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_32.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_33.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_33.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_34.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_34.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_35.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_35.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_36.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_36.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_37.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_37.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_38.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_38.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_39.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_39.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_4.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_4.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_40.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_40.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_41.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_41.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_42.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_42.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_43.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_43.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_44.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_44.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_45.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_45.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_46.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_46.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_47.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_47.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_48.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_48.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_49.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_49.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_5.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_5.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_50.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_50.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_51.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_51.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_52.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_52.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_53.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_53.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_54.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_54.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_55.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_55.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_56.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_56.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_57.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_57.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_58.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_58.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_59.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_59.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_6.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_6.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_60.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_60.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_61.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_61.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_62.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_62.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_63.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_63.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_64.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_64.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_65.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_65.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_66.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_66.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_67.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_67.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_68.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_68.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_69.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_69.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_7.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_7.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_70.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_70.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_71.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_71.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_72.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_72.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_73.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_73.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_74.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_74.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_75.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_75.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_76.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_76.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_77.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_77.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_78.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_78.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_79.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_79.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_8.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_8.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_80.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_80.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_81.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_81.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_82.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_82.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_83.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_83.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_84.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_84.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_85.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_85.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_86.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_86.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_87.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_87.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_88.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_88.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_89.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_89.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_9.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_9.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_90.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_90.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_91.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_91.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_92.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_92.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_93.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_93.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_94.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_94.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_95.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_95.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_96.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_96.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_97.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_97.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_98.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_98.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_99.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.experts.expert_99.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.15.layer.2.mlp.router.classifier.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.2.mlp.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.16.layer.2.mlp.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_0.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_0.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_1.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_1.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_10.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_10.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_100.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_100.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_101.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_101.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_102.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_102.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_103.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_103.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_104.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_104.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_105.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_105.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_106.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_106.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_107.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_107.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_108.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_108.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_109.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_109.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_11.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_11.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_110.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_110.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_111.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_111.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_112.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_112.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_113.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_113.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_114.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_114.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_115.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_115.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_116.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_116.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_117.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_117.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_118.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_118.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_119.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_119.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_12.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_12.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_120.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_120.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_121.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_121.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_122.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_122.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_123.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_123.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_124.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_124.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_125.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_125.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_126.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_126.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_127.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_127.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_13.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_13.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_14.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_14.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_15.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_15.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_16.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_16.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_17.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_17.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_18.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_18.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_19.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_19.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_2.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_2.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_20.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_20.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_21.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_21.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_22.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_22.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_23.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_23.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_24.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_24.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_25.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_25.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_26.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_26.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_27.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_27.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_28.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_28.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_29.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_29.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_3.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_3.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_30.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_30.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_31.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_31.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_32.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_32.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_33.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_33.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_34.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_34.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_35.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_35.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_36.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_36.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_37.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_37.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_38.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_38.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_39.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_39.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_4.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_4.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_40.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_40.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_41.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_41.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_42.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_42.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_43.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_43.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_44.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_44.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_45.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_45.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_46.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_46.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_47.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_47.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_48.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_48.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_49.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_49.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_5.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_5.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_50.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_50.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_51.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_51.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_52.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_52.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_53.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_53.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_54.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_54.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_55.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_55.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_56.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_56.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_57.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_57.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_58.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_58.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_59.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_59.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_6.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_6.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_60.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_60.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_61.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_61.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_62.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_62.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_63.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_63.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_64.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_64.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_65.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_65.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_66.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_66.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_67.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_67.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_68.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_68.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_69.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_69.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_7.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_7.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_70.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_70.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_71.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_71.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_72.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_72.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_73.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_73.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_74.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_74.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_75.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_75.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_76.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_76.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_77.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_77.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_78.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_78.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_79.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_79.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_8.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_8.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_80.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_80.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_81.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_81.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_82.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_82.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_83.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_83.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_84.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_84.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_85.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_85.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_86.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_86.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_87.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_87.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_88.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_88.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_89.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_89.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_9.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_9.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_90.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_90.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_91.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_91.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_92.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_92.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_93.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_93.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_94.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_94.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_95.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_95.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_96.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_96.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_97.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_97.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_98.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_98.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_99.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.experts.expert_99.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.17.layer.2.mlp.router.classifier.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.2.mlp.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.18.layer.2.mlp.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_0.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_0.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_1.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_1.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_10.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_10.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_100.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_100.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_101.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_101.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_102.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_102.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_103.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_103.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_104.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_104.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_105.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_105.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_106.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_106.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_107.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_107.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_108.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_108.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_109.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_109.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_11.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_11.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_110.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_110.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_111.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_111.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_112.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_112.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_113.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_113.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_114.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_114.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_115.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_115.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_116.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_116.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_117.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_117.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_118.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_118.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_119.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_119.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_12.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_12.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_120.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_120.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_121.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_121.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_122.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_122.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_123.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_123.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_124.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_124.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_125.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_125.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_126.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_126.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_127.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_127.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_13.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_13.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_14.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_14.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_15.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_15.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_16.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_16.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_17.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_17.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_18.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_18.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_19.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_19.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_2.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_2.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_20.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_20.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_21.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_21.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_22.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_22.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_23.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_23.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_24.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_24.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_25.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_25.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_26.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_26.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_27.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_27.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_28.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_28.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_29.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_29.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_3.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_3.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_30.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_30.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_31.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_31.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_32.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_32.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_33.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_33.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_34.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_34.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_35.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_35.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_36.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_36.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_37.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_37.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_38.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_38.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_39.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_39.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_4.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_4.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_40.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_40.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_41.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_41.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_42.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_42.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_43.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_43.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_44.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_44.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_45.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_45.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_46.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_46.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_47.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_47.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_48.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_48.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_49.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_49.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_5.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_5.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_50.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_50.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_51.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_51.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_52.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_52.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_53.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_53.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_54.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_54.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_55.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_55.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_56.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_56.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_57.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_57.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_58.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_58.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_59.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_59.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_6.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_6.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_60.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_60.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_61.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_61.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_62.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_62.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_63.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_63.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_64.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_64.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_65.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_65.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_66.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_66.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_67.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_67.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_68.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_68.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_69.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_69.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_7.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_7.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_70.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_70.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_71.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_71.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_72.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_72.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_73.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_73.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_74.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_74.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_75.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_75.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_76.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_76.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_77.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_77.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_78.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_78.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_79.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_79.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_8.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_8.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_80.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_80.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_81.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_81.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_82.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_82.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_83.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_83.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_84.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_84.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_85.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_85.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_86.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_86.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_87.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_87.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_88.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_88.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_89.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_89.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_9.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_9.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_90.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_90.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_91.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_91.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_92.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_92.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_93.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_93.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_94.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_94.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_95.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_95.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_96.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_96.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_97.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_97.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_98.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_98.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_99.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.experts.expert_99.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.19.layer.2.mlp.router.classifier.weight": "model-00005-of-00006.safetensors", "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors", "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors", "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors", "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors", "decoder.block.2.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors", "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00003-of-00006.safetensors", "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00003-of-00006.safetensors", "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00003-of-00006.safetensors", "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00003-of-00006.safetensors", "decoder.block.2.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors", "decoder.block.2.layer.2.layer_norm.weight": "model-00003-of-00006.safetensors", "decoder.block.2.layer.2.mlp.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.2.layer.2.mlp.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.20.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.20.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.20.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.20.layer.2.mlp.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.20.layer.2.mlp.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.layer_norm.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_0.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_0.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_1.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_1.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_10.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_10.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_100.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_100.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_101.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_101.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_102.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_102.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_103.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_103.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_104.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_104.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_105.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_105.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_106.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_106.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_107.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_107.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_108.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_108.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_109.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_109.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_11.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_11.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_110.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_110.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_111.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_111.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_112.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_112.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_113.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_113.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_114.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_114.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_115.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_115.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_116.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_116.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_117.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_117.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_118.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_118.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_119.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_119.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_12.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_12.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_120.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_120.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_121.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_121.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_122.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_122.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_123.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_123.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_124.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_124.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_125.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_125.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_126.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_126.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_127.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_127.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_13.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_13.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_14.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_14.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_15.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_15.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_16.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_16.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_17.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_17.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_18.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_18.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_19.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_19.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_2.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_2.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_20.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_20.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_21.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_21.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_22.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_22.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_23.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_23.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_24.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_24.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_25.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_25.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_26.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_26.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_27.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_27.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_28.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_28.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_29.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_29.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_3.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_3.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_30.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_30.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_31.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_31.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_32.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_32.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_33.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_33.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_34.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_34.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_35.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_35.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_36.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_36.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_37.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_37.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_38.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_38.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_39.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_39.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_4.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_4.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_40.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_40.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_41.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_41.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_42.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_42.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_43.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_43.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_44.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_44.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_45.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_45.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_46.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_46.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_47.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_47.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_48.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_48.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_49.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_49.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_5.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_5.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_50.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_50.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_51.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_51.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_52.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_52.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_53.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_53.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_54.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_54.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_55.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_55.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_56.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_56.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_57.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_57.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_58.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_58.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_59.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_59.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_6.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_6.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_60.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_60.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_61.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_61.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_62.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_62.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_63.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_63.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_64.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_64.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_65.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_65.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_66.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_66.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_67.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_67.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_68.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_68.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_69.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_69.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_7.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_7.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_70.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_70.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_71.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_71.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_72.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_72.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_73.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_73.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_74.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_74.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_75.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_75.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_76.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_76.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_77.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_77.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_78.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_78.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_79.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_79.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_8.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_8.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_80.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_80.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_81.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_81.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_82.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_82.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_83.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_83.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_84.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_84.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_85.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_85.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_86.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_86.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_87.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_87.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_88.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_88.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_89.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_89.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_9.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_9.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_90.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_90.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_91.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_91.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_92.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_92.wo.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_93.wi.weight": "model-00005-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_93.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_94.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_94.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_95.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_95.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_96.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_96.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_97.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_97.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_98.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_98.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_99.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.experts.expert_99.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.21.layer.2.mlp.router.classifier.weight": "model-00005-of-00006.safetensors", "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00006-of-00006.safetensors", "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00006-of-00006.safetensors", "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00006-of-00006.safetensors", "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00006-of-00006.safetensors", "decoder.block.22.layer.0.layer_norm.weight": "model-00006-of-00006.safetensors", "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00006-of-00006.safetensors", "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00006-of-00006.safetensors", "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00006-of-00006.safetensors", "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00006-of-00006.safetensors", "decoder.block.22.layer.1.layer_norm.weight": "model-00006-of-00006.safetensors", "decoder.block.22.layer.2.layer_norm.weight": "model-00006-of-00006.safetensors", "decoder.block.22.layer.2.mlp.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.22.layer.2.mlp.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.0.layer_norm.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.1.layer_norm.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.layer_norm.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_0.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_0.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_1.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_1.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_10.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_10.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_100.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_100.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_101.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_101.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_102.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_102.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_103.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_103.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_104.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_104.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_105.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_105.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_106.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_106.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_107.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_107.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_108.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_108.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_109.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_109.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_11.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_11.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_110.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_110.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_111.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_111.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_112.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_112.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_113.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_113.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_114.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_114.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_115.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_115.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_116.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_116.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_117.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_117.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_118.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_118.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_119.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_119.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_12.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_12.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_120.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_120.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_121.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_121.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_122.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_122.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_123.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_123.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_124.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_124.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_125.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_125.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_126.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_126.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_127.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_127.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_13.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_13.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_14.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_14.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_15.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_15.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_16.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_16.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_17.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_17.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_18.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_18.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_19.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_19.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_2.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_2.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_20.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_20.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_21.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_21.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_22.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_22.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_23.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_23.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_24.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_24.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_25.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_25.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_26.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_26.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_27.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_27.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_28.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_28.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_29.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_29.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_3.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_3.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_30.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_30.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_31.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_31.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_32.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_32.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_33.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_33.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_34.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_34.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_35.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_35.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_36.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_36.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_37.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_37.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_38.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_38.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_39.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_39.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_4.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_4.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_40.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_40.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_41.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_41.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_42.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_42.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_43.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_43.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_44.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_44.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_45.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_45.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_46.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_46.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_47.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_47.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_48.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_48.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_49.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_49.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_5.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_5.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_50.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_50.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_51.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_51.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_52.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_52.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_53.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_53.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_54.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_54.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_55.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_55.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_56.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_56.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_57.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_57.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_58.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_58.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_59.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_59.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_6.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_6.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_60.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_60.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_61.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_61.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_62.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_62.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_63.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_63.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_64.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_64.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_65.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_65.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_66.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_66.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_67.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_67.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_68.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_68.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_69.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_69.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_7.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_7.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_70.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_70.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_71.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_71.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_72.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_72.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_73.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_73.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_74.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_74.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_75.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_75.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_76.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_76.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_77.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_77.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_78.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_78.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_79.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_79.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_8.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_8.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_80.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_80.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_81.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_81.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_82.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_82.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_83.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_83.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_84.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_84.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_85.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_85.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_86.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_86.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_87.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_87.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_88.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_88.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_89.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_89.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_9.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_9.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_90.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_90.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_91.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_91.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_92.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_92.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_93.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_93.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_94.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_94.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_95.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_95.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_96.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_96.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_97.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_97.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_98.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_98.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_99.wi.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.experts.expert_99.wo.weight": "model-00006-of-00006.safetensors", "decoder.block.23.layer.2.mlp.router.classifier.weight": "model-00006-of-00006.safetensors", "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_0.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_0.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_1.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_1.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_10.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_10.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_100.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_100.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_101.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_101.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_102.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_102.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_103.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_103.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_104.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_104.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_105.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_105.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_106.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_106.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_107.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_107.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_108.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_108.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_109.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_109.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_11.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_11.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_110.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_110.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_111.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_111.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_112.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_112.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_113.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_113.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_114.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_114.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_115.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_115.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_116.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_116.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_117.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_117.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_118.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_118.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_119.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_119.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_12.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_12.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_120.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_120.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_121.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_121.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_122.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_122.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_123.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_123.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_124.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_124.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_125.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_125.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_126.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_126.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_127.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_127.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_13.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_13.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_14.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_14.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_15.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_15.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_16.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_16.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_17.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_17.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_18.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_18.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_19.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_19.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_2.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_2.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_20.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_20.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_21.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_21.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_22.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_22.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_23.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_23.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_24.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_24.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_25.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_25.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_26.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_26.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_27.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_27.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_28.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_28.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_29.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_29.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_3.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_3.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_30.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_30.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_31.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_31.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_32.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_32.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_33.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_33.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_34.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_34.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_35.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_35.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_36.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_36.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_37.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_37.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_38.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_38.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_39.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_39.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_4.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_4.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_40.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_40.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_41.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_41.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_42.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_42.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_43.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_43.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_44.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_44.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_45.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_45.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_46.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_46.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_47.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_47.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_48.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_48.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_49.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_49.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_5.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_5.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_50.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_50.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_51.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_51.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_52.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_52.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_53.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_53.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_54.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_54.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_55.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_55.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_56.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_56.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_57.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_57.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_58.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_58.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_59.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_59.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_6.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_6.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_60.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_60.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_61.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_61.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_62.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_62.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_63.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_63.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_64.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_64.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_65.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_65.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_66.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_66.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_67.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_67.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_68.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_68.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_69.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_69.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_7.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_7.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_70.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_70.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_71.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_71.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_72.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_72.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_73.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_73.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_74.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_74.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_75.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_75.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_76.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_76.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_77.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_77.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_78.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_78.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_79.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_79.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_8.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_8.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_80.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_80.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_81.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_81.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_82.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_82.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_83.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_83.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_84.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_84.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_85.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_85.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_86.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_86.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_87.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_87.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_88.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_88.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_89.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_89.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_9.wi.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_9.wo.weight": "model-00003-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_90.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_90.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_91.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_91.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_92.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_92.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_93.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_93.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_94.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_94.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_95.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_95.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_96.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_96.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_97.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_97.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_98.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_98.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_99.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.experts.expert_99.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.3.layer.2.mlp.router.classifier.weight": "model-00003-of-00006.safetensors", "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.4.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.4.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.4.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.4.layer.2.mlp.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.4.layer.2.mlp.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_0.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_0.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_1.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_1.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_10.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_10.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_100.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_100.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_101.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_101.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_102.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_102.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_103.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_103.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_104.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_104.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_105.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_105.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_106.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_106.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_107.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_107.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_108.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_108.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_109.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_109.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_11.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_11.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_110.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_110.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_111.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_111.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_112.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_112.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_113.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_113.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_114.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_114.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_115.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_115.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_116.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_116.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_117.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_117.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_118.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_118.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_119.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_119.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_12.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_12.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_120.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_120.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_121.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_121.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_122.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_122.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_123.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_123.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_124.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_124.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_125.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_125.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_126.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_126.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_127.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_127.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_13.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_13.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_14.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_14.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_15.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_15.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_16.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_16.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_17.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_17.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_18.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_18.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_19.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_19.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_2.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_2.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_20.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_20.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_21.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_21.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_22.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_22.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_23.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_23.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_24.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_24.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_25.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_25.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_26.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_26.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_27.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_27.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_28.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_28.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_29.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_29.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_3.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_3.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_30.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_30.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_31.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_31.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_32.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_32.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_33.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_33.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_34.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_34.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_35.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_35.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_36.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_36.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_37.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_37.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_38.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_38.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_39.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_39.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_4.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_4.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_40.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_40.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_41.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_41.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_42.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_42.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_43.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_43.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_44.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_44.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_45.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_45.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_46.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_46.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_47.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_47.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_48.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_48.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_49.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_49.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_5.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_5.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_50.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_50.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_51.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_51.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_52.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_52.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_53.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_53.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_54.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_54.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_55.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_55.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_56.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_56.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_57.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_57.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_58.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_58.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_59.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_59.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_6.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_6.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_60.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_60.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_61.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_61.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_62.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_62.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_63.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_63.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_64.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_64.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_65.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_65.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_66.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_66.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_67.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_67.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_68.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_68.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_69.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_69.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_7.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_7.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_70.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_70.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_71.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_71.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_72.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_72.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_73.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_73.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_74.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_74.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_75.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_75.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_76.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_76.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_77.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_77.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_78.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_78.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_79.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_79.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_8.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_8.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_80.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_80.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_81.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_81.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_82.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_82.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_83.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_83.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_84.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_84.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_85.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_85.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_86.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_86.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_87.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_87.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_88.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_88.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_89.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_89.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_9.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_9.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_90.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_90.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_91.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_91.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_92.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_92.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_93.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_93.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_94.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_94.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_95.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_95.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_96.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_96.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_97.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_97.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_98.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_98.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_99.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.experts.expert_99.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.5.layer.2.mlp.router.classifier.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.2.mlp.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.6.layer.2.mlp.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_0.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_0.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_1.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_1.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_10.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_10.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_100.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_100.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_101.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_101.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_102.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_102.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_103.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_103.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_104.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_104.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_105.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_105.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_106.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_106.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_107.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_107.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_108.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_108.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_109.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_109.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_11.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_11.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_110.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_110.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_111.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_111.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_112.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_112.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_113.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_113.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_114.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_114.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_115.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_115.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_116.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_116.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_117.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_117.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_118.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_118.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_119.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_119.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_12.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_12.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_120.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_120.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_121.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_121.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_122.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_122.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_123.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_123.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_124.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_124.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_125.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_125.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_126.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_126.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_127.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_127.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_13.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_13.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_14.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_14.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_15.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_15.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_16.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_16.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_17.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_17.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_18.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_18.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_19.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_19.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_2.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_2.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_20.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_20.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_21.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_21.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_22.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_22.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_23.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_23.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_24.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_24.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_25.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_25.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_26.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_26.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_27.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_27.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_28.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_28.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_29.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_29.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_3.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_3.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_30.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_30.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_31.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_31.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_32.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_32.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_33.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_33.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_34.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_34.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_35.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_35.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_36.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_36.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_37.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_37.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_38.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_38.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_39.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_39.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_4.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_4.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_40.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_40.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_41.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_41.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_42.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_42.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_43.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_43.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_44.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_44.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_45.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_45.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_46.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_46.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_47.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_47.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_48.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_48.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_49.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_49.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_5.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_5.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_50.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_50.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_51.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_51.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_52.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_52.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_53.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_53.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_54.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_54.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_55.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_55.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_56.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_56.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_57.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_57.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_58.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_58.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_59.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_59.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_6.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_6.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_60.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_60.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_61.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_61.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_62.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_62.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_63.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_63.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_64.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_64.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_65.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_65.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_66.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_66.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_67.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_67.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_68.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_68.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_69.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_69.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_7.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_7.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_70.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_70.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_71.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_71.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_72.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_72.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_73.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_73.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_74.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_74.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_75.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_75.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_76.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_76.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_77.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_77.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_78.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_78.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_79.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_79.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_8.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_8.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_80.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_80.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_81.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_81.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_82.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_82.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_83.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_83.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_84.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_84.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_85.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_85.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_86.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_86.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_87.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_87.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_88.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_88.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_89.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_89.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_9.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_9.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_90.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_90.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_91.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_91.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_92.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_92.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_93.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_93.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_94.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_94.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_95.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_95.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_96.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_96.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_97.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_97.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_98.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_98.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_99.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.experts.expert_99.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.7.layer.2.mlp.router.classifier.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.2.mlp.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.8.layer.2.mlp.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_0.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_0.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_1.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_1.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_10.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_10.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_100.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_100.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_101.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_101.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_102.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_102.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_103.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_103.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_104.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_104.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_105.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_105.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_106.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_106.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_107.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_107.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_108.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_108.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_109.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_109.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_11.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_11.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_110.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_110.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_111.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_111.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_112.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_112.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_113.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_113.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_114.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_114.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_115.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_115.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_116.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_116.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_117.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_117.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_118.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_118.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_119.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_119.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_12.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_12.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_120.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_120.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_121.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_121.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_122.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_122.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_123.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_123.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_124.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_124.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_125.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_125.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_126.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_126.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_127.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_127.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_13.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_13.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_14.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_14.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_15.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_15.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_16.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_16.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_17.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_17.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_18.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_18.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_19.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_19.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_2.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_2.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_20.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_20.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_21.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_21.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_22.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_22.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_23.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_23.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_24.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_24.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_25.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_25.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_26.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_26.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_27.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_27.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_28.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_28.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_29.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_29.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_3.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_3.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_30.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_30.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_31.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_31.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_32.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_32.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_33.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_33.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_34.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_34.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_35.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_35.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_36.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_36.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_37.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_37.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_38.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_38.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_39.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_39.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_4.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_4.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_40.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_40.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_41.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_41.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_42.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_42.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_43.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_43.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_44.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_44.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_45.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_45.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_46.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_46.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_47.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_47.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_48.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_48.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_49.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_49.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_5.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_5.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_50.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_50.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_51.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_51.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_52.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_52.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_53.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_53.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_54.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_54.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_55.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_55.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_56.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_56.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_57.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_57.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_58.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_58.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_59.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_59.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_6.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_6.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_60.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_60.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_61.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_61.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_62.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_62.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_63.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_63.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_64.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_64.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_65.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_65.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_66.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_66.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_67.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_67.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_68.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_68.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_69.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_69.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_7.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_7.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_70.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_70.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_71.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_71.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_72.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_72.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_73.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_73.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_74.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_74.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_75.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_75.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_76.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_76.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_77.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_77.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_78.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_78.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_79.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_79.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_8.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_8.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_80.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_80.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_81.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_81.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_82.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_82.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_83.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_83.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_84.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_84.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_85.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_85.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_86.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_86.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_87.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_87.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_88.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_88.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_89.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_89.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_9.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_9.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_90.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_90.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_91.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_91.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_92.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_92.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_93.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_93.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_94.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_94.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_95.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_95.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_96.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_96.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_97.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_97.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_98.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_98.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_99.wi.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.experts.expert_99.wo.weight": "model-00004-of-00006.safetensors", "decoder.block.9.layer.2.mlp.router.classifier.weight": "model-00004-of-00006.safetensors", "decoder.embed_tokens.weight": "model-00003-of-00006.safetensors", "decoder.final_layer_norm.weight": "model-00006-of-00006.safetensors", "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors", "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors", "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors", "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00006.safetensors", "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors", "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.0.layer.1.mlp.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.0.layer.1.mlp.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_0.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_0.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_1.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_1.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_10.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_10.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_100.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_100.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_101.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_101.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_102.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_102.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_103.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_103.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_104.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_104.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_105.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_105.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_106.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_106.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_107.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_107.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_108.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_108.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_109.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_109.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_11.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_11.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_110.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_110.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_111.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_111.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_112.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_112.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_113.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_113.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_114.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_114.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_115.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_115.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_116.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_116.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_117.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_117.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_118.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_118.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_119.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_119.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_12.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_12.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_120.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_120.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_121.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_121.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_122.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_122.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_123.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_123.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_124.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_124.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_125.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_125.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_126.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_126.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_127.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_127.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_13.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_13.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_14.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_14.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_15.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_15.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_16.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_16.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_17.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_17.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_18.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_18.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_19.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_19.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_2.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_2.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_20.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_20.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_21.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_21.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_22.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_22.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_23.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_23.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_24.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_24.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_25.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_25.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_26.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_26.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_27.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_27.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_28.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_28.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_29.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_29.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_3.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_3.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_30.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_30.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_31.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_31.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_32.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_32.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_33.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_33.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_34.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_34.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_35.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_35.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_36.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_36.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_37.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_37.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_38.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_38.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_39.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_39.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_4.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_4.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_40.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_40.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_41.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_41.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_42.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_42.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_43.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_43.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_44.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_44.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_45.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_45.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_46.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_46.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_47.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_47.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_48.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_48.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_49.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_49.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_5.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_5.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_50.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_50.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_51.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_51.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_52.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_52.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_53.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_53.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_54.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_54.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_55.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_55.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_56.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_56.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_57.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_57.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_58.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_58.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_59.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_59.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_6.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_6.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_60.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_60.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_61.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_61.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_62.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_62.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_63.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_63.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_64.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_64.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_65.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_65.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_66.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_66.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_67.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_67.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_68.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_68.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_69.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_69.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_7.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_7.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_70.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_70.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_71.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_71.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_72.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_72.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_73.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_73.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_74.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_74.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_75.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_75.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_76.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_76.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_77.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_77.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_78.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_78.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_79.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_79.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_8.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_8.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_80.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_80.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_81.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_81.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_82.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_82.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_83.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_83.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_84.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_84.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_85.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_85.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_86.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_86.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_87.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_87.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_88.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_88.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_89.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_89.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_9.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_9.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_90.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_90.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_91.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_91.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_92.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_92.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_93.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_93.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_94.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_94.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_95.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_95.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_96.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_96.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_97.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_97.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_98.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_98.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_99.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.experts.expert_99.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.1.layer.1.mlp.router.classifier.weight": "model-00001-of-00006.safetensors", "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors", "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors", "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors", "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors", "encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.10.layer.1.mlp.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.10.layer.1.mlp.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_0.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_0.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_1.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_1.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_10.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_10.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_100.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_100.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_101.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_101.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_102.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_102.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_103.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_103.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_104.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_104.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_105.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_105.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_106.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_106.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_107.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_107.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_108.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_108.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_109.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_109.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_11.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_11.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_110.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_110.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_111.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_111.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_112.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_112.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_113.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_113.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_114.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_114.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_115.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_115.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_116.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_116.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_117.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_117.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_118.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_118.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_119.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_119.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_12.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_12.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_120.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_120.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_121.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_121.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_122.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_122.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_123.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_123.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_124.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_124.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_125.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_125.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_126.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_126.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_127.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_127.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_13.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_13.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_14.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_14.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_15.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_15.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_16.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_16.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_17.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_17.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_18.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_18.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_19.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_19.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_2.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_2.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_20.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_20.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_21.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_21.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_22.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_22.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_23.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_23.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_24.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_24.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_25.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_25.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_26.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_26.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_27.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_27.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_28.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_28.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_29.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_29.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_3.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_3.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_30.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_30.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_31.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_31.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_32.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_32.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_33.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_33.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_34.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_34.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_35.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_35.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_36.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_36.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_37.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_37.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_38.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_38.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_39.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_39.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_4.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_4.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_40.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_40.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_41.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_41.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_42.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_42.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_43.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_43.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_44.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_44.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_45.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_45.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_46.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_46.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_47.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_47.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_48.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_48.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_49.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_49.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_5.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_5.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_50.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_50.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_51.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_51.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_52.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_52.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_53.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_53.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_54.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_54.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_55.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_55.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_56.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_56.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_57.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_57.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_58.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_58.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_59.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_59.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_6.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_6.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_60.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_60.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_61.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_61.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_62.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_62.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_63.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_63.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_64.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_64.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_65.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_65.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_66.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_66.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_67.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_67.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_68.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_68.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_69.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_69.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_7.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_7.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_70.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_70.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_71.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_71.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_72.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_72.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_73.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_73.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_74.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_74.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_75.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_75.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_76.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_76.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_77.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_77.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_78.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_78.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_79.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_79.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_8.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_8.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_80.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_80.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_81.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_81.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_82.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_82.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_83.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_83.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_84.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_84.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_85.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_85.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_86.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_86.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_87.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_87.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_88.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_88.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_89.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_89.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_9.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_9.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_90.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_90.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_91.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_91.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_92.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_92.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_93.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_93.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_94.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_94.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_95.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_95.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_96.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_96.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_97.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_97.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_98.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_98.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_99.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.experts.expert_99.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.11.layer.1.mlp.router.classifier.weight": "model-00002-of-00006.safetensors", "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors", "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors", "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors", "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors", "encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.12.layer.1.mlp.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.12.layer.1.mlp.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_0.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_0.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_1.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_1.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_10.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_10.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_100.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_100.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_101.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_101.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_102.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_102.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_103.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_103.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_104.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_104.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_105.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_105.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_106.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_106.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_107.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_107.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_108.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_108.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_109.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_109.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_11.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_11.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_110.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_110.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_111.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_111.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_112.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_112.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_113.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_113.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_114.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_114.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_115.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_115.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_116.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_116.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_117.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_117.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_118.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_118.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_119.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_119.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_12.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_12.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_120.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_120.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_121.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_121.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_122.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_122.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_123.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_123.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_124.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_124.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_125.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_125.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_126.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_126.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_127.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_127.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_13.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_13.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_14.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_14.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_15.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_15.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_16.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_16.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_17.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_17.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_18.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_18.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_19.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_19.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_2.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_2.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_20.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_20.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_21.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_21.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_22.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_22.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_23.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_23.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_24.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_24.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_25.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_25.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_26.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_26.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_27.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_27.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_28.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_28.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_29.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_29.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_3.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_3.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_30.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_30.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_31.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_31.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_32.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_32.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_33.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_33.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_34.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_34.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_35.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_35.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_36.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_36.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_37.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_37.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_38.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_38.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_39.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_39.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_4.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_4.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_40.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_40.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_41.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_41.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_42.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_42.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_43.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_43.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_44.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_44.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_45.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_45.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_46.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_46.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_47.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_47.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_48.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_48.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_49.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_49.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_5.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_5.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_50.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_50.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_51.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_51.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_52.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_52.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_53.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_53.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_54.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_54.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_55.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_55.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_56.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_56.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_57.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_57.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_58.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_58.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_59.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_59.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_6.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_6.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_60.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_60.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_61.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_61.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_62.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_62.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_63.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_63.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_64.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_64.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_65.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_65.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_66.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_66.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_67.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_67.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_68.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_68.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_69.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_69.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_7.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_7.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_70.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_70.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_71.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_71.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_72.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_72.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_73.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_73.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_74.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_74.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_75.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_75.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_76.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_76.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_77.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_77.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_78.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_78.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_79.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_79.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_8.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_8.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_80.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_80.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_81.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_81.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_82.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_82.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_83.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_83.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_84.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_84.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_85.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_85.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_86.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_86.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_87.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_87.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_88.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_88.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_89.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_89.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_9.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_9.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_90.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_90.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_91.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_91.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_92.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_92.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_93.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_93.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_94.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_94.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_95.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_95.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_96.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_96.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_97.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_97.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_98.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_98.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_99.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.experts.expert_99.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.13.layer.1.mlp.router.classifier.weight": "model-00002-of-00006.safetensors", "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors", "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors", "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors", "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors", "encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.14.layer.1.mlp.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.14.layer.1.mlp.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_0.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_0.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_1.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_1.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_10.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_10.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_100.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_100.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_101.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_101.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_102.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_102.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_103.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_103.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_104.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_104.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_105.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_105.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_106.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_106.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_107.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_107.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_108.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_108.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_109.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_109.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_11.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_11.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_110.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_110.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_111.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_111.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_112.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_112.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_113.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_113.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_114.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_114.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_115.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_115.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_116.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_116.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_117.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_117.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_118.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_118.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_119.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_119.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_12.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_12.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_120.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_120.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_121.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_121.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_122.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_122.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_123.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_123.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_124.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_124.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_125.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_125.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_126.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_126.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_127.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_127.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_13.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_13.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_14.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_14.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_15.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_15.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_16.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_16.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_17.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_17.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_18.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_18.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_19.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_19.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_2.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_2.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_20.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_20.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_21.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_21.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_22.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_22.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_23.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_23.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_24.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_24.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_25.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_25.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_26.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_26.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_27.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_27.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_28.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_28.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_29.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_29.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_3.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_3.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_30.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_30.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_31.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_31.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_32.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_32.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_33.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_33.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_34.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_34.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_35.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_35.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_36.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_36.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_37.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_37.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_38.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_38.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_39.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_39.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_4.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_4.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_40.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_40.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_41.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_41.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_42.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_42.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_43.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_43.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_44.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_44.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_45.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_45.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_46.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_46.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_47.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_47.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_48.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_48.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_49.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_49.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_5.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_5.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_50.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_50.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_51.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_51.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_52.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_52.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_53.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_53.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_54.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_54.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_55.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_55.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_56.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_56.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_57.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_57.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_58.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_58.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_59.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_59.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_6.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_6.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_60.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_60.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_61.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_61.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_62.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_62.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_63.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_63.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_64.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_64.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_65.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_65.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_66.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_66.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_67.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_67.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_68.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_68.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_69.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_69.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_7.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_7.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_70.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_70.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_71.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_71.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_72.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_72.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_73.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_73.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_74.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_74.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_75.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_75.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_76.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_76.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_77.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_77.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_78.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_78.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_79.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_79.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_8.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_8.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_80.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_80.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_81.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_81.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_82.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_82.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_83.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_83.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_84.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_84.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_85.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_85.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_86.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_86.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_87.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_87.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_88.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_88.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_89.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_89.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_9.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_9.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_90.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_90.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_91.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_91.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_92.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_92.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_93.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_93.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_94.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_94.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_95.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_95.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_96.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_96.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_97.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_97.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_98.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_98.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_99.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.experts.expert_99.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.15.layer.1.mlp.router.classifier.weight": "model-00002-of-00006.safetensors", "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors", "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors", "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors", "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors", "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.16.layer.1.mlp.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.16.layer.1.mlp.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_0.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_0.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_1.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_1.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_10.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_10.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_100.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_100.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_101.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_101.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_102.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_102.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_103.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_103.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_104.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_104.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_105.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_105.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_106.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_106.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_107.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_107.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_108.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_108.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_109.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_109.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_11.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_11.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_110.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_110.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_111.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_111.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_112.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_112.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_113.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_113.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_114.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_114.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_115.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_115.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_116.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_116.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_117.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_117.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_118.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_118.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_119.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_119.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_12.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_12.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_120.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_120.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_121.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_121.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_122.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_122.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_123.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_123.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_124.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_124.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_125.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_125.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_126.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_126.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_127.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_127.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_13.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_13.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_14.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_14.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_15.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_15.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_16.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_16.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_17.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_17.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_18.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_18.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_19.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_19.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_2.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_2.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_20.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_20.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_21.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_21.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_22.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_22.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_23.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_23.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_24.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_24.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_25.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_25.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_26.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_26.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_27.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_27.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_28.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_28.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_29.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_29.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_3.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_3.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_30.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_30.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_31.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_31.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_32.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_32.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_33.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_33.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_34.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_34.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_35.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_35.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_36.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_36.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_37.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_37.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_38.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_38.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_39.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_39.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_4.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_4.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_40.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_40.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_41.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_41.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_42.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_42.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_43.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_43.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_44.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_44.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_45.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_45.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_46.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_46.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_47.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_47.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_48.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_48.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_49.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_49.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_5.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_5.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_50.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_50.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_51.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_51.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_52.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_52.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_53.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_53.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_54.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_54.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_55.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_55.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_56.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_56.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_57.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_57.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_58.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_58.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_59.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_59.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_6.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_6.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_60.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_60.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_61.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_61.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_62.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_62.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_63.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_63.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_64.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_64.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_65.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_65.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_66.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_66.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_67.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_67.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_68.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_68.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_69.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_69.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_7.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_7.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_70.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_70.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_71.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_71.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_72.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_72.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_73.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_73.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_74.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_74.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_75.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_75.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_76.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_76.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_77.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_77.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_78.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_78.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_79.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_79.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_8.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_8.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_80.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_80.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_81.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_81.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_82.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_82.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_83.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_83.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_84.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_84.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_85.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_85.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_86.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_86.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_87.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_87.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_88.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_88.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_89.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_89.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_9.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_9.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_90.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_90.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_91.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_91.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_92.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_92.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_93.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_93.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_94.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_94.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_95.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_95.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_96.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_96.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_97.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_97.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_98.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_98.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_99.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.experts.expert_99.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.17.layer.1.mlp.router.classifier.weight": "model-00002-of-00006.safetensors", "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors", "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors", "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors", "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors", "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.18.layer.1.mlp.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.18.layer.1.mlp.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_0.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_0.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_1.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_1.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_10.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_10.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_100.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_100.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_101.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_101.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_102.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_102.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_103.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_103.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_104.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_104.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_105.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_105.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_106.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_106.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_107.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_107.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_108.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_108.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_109.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_109.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_11.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_11.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_110.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_110.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_111.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_111.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_112.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_112.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_113.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_113.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_114.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_114.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_115.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_115.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_116.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_116.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_117.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_117.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_118.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_118.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_119.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_119.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_12.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_12.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_120.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_120.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_121.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_121.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_122.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_122.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_123.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_123.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_124.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_124.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_125.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_125.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_126.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_126.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_127.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_127.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_13.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_13.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_14.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_14.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_15.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_15.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_16.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_16.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_17.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_17.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_18.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_18.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_19.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_19.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_2.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_2.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_20.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_20.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_21.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_21.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_22.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_22.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_23.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_23.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_24.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_24.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_25.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_25.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_26.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_26.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_27.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_27.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_28.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_28.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_29.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_29.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_3.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_3.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_30.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_30.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_31.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_31.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_32.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_32.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_33.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_33.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_34.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_34.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_35.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_35.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_36.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_36.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_37.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_37.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_38.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_38.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_39.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_39.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_4.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_4.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_40.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_40.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_41.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_41.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_42.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_42.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_43.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_43.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_44.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_44.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_45.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_45.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_46.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_46.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_47.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_47.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_48.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_48.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_49.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_49.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_5.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_5.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_50.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_50.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_51.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_51.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_52.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_52.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_53.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_53.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_54.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_54.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_55.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_55.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_56.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_56.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_57.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_57.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_58.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_58.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_59.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_59.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_6.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_6.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_60.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_60.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_61.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_61.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_62.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_62.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_63.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_63.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_64.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_64.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_65.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_65.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_66.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_66.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_67.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_67.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_68.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_68.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_69.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_69.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_7.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_7.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_70.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_70.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_71.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_71.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_72.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_72.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_73.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_73.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_74.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_74.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_75.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_75.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_76.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_76.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_77.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_77.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_78.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_78.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_79.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_79.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_8.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_8.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_80.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_80.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_81.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_81.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_82.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_82.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_83.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_83.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_84.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_84.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_85.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_85.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_86.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_86.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_87.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_87.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_88.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_88.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_89.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_89.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_9.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_9.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_90.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_90.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_91.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_91.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_92.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_92.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_93.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_93.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_94.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_94.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_95.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_95.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_96.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_96.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_97.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_97.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_98.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_98.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_99.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.experts.expert_99.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.19.layer.1.mlp.router.classifier.weight": "model-00002-of-00006.safetensors", "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors", "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors", "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors", "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors", "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.2.layer.1.mlp.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.2.layer.1.mlp.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors", "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors", "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors", "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors", "encoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors", "encoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors", "encoder.block.20.layer.1.mlp.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.20.layer.1.mlp.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_0.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_0.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_1.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_1.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_10.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_10.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_100.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_100.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_101.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_101.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_102.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_102.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_103.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_103.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_104.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_104.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_105.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_105.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_106.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_106.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_107.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_107.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_108.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_108.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_109.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_109.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_11.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_11.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_110.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_110.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_111.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_111.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_112.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_112.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_113.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_113.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_114.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_114.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_115.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_115.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_116.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_116.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_117.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_117.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_118.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_118.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_119.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_119.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_12.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_12.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_120.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_120.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_121.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_121.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_122.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_122.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_123.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_123.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_124.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_124.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_125.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_125.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_126.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_126.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_127.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_127.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_13.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_13.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_14.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_14.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_15.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_15.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_16.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_16.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_17.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_17.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_18.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_18.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_19.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_19.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_2.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_2.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_20.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_20.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_21.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_21.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_22.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_22.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_23.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_23.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_24.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_24.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_25.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_25.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_26.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_26.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_27.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_27.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_28.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_28.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_29.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_29.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_3.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_3.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_30.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_30.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_31.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_31.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_32.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_32.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_33.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_33.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_34.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_34.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_35.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_35.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_36.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_36.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_37.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_37.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_38.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_38.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_39.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_39.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_4.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_4.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_40.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_40.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_41.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_41.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_42.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_42.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_43.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_43.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_44.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_44.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_45.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_45.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_46.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_46.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_47.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_47.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_48.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_48.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_49.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_49.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_5.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_5.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_50.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_50.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_51.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_51.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_52.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_52.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_53.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_53.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_54.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_54.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_55.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_55.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_56.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_56.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_57.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_57.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_58.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_58.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_59.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_59.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_6.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_6.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_60.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_60.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_61.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_61.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_62.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_62.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_63.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_63.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_64.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_64.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_65.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_65.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_66.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_66.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_67.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_67.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_68.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_68.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_69.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_69.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_7.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_7.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_70.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_70.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_71.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_71.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_72.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_72.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_73.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_73.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_74.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_74.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_75.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_75.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_76.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_76.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_77.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_77.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_78.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_78.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_79.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_79.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_8.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_8.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_80.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_80.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_81.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_81.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_82.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_82.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_83.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_83.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_84.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_84.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_85.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_85.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_86.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_86.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_87.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_87.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_88.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_88.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_89.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_89.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_9.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_9.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_90.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_90.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_91.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_91.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_92.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_92.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_93.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_93.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_94.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_94.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_95.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_95.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_96.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_96.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_97.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_97.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_98.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_98.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_99.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.experts.expert_99.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.21.layer.1.mlp.router.classifier.weight": "model-00003-of-00006.safetensors", "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors", "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors", "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors", "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors", "encoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors", "encoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors", "encoder.block.22.layer.1.mlp.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.22.layer.1.mlp.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_0.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_0.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_1.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_1.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_10.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_10.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_100.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_100.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_101.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_101.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_102.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_102.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_103.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_103.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_104.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_104.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_105.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_105.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_106.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_106.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_107.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_107.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_108.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_108.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_109.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_109.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_11.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_11.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_110.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_110.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_111.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_111.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_112.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_112.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_113.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_113.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_114.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_114.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_115.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_115.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_116.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_116.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_117.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_117.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_118.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_118.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_119.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_119.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_12.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_12.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_120.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_120.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_121.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_121.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_122.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_122.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_123.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_123.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_124.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_124.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_125.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_125.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_126.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_126.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_127.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_127.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_13.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_13.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_14.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_14.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_15.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_15.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_16.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_16.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_17.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_17.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_18.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_18.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_19.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_19.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_2.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_2.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_20.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_20.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_21.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_21.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_22.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_22.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_23.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_23.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_24.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_24.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_25.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_25.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_26.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_26.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_27.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_27.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_28.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_28.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_29.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_29.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_3.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_3.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_30.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_30.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_31.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_31.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_32.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_32.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_33.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_33.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_34.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_34.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_35.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_35.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_36.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_36.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_37.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_37.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_38.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_38.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_39.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_39.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_4.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_4.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_40.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_40.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_41.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_41.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_42.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_42.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_43.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_43.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_44.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_44.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_45.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_45.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_46.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_46.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_47.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_47.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_48.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_48.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_49.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_49.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_5.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_5.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_50.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_50.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_51.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_51.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_52.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_52.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_53.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_53.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_54.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_54.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_55.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_55.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_56.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_56.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_57.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_57.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_58.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_58.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_59.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_59.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_6.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_6.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_60.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_60.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_61.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_61.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_62.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_62.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_63.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_63.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_64.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_64.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_65.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_65.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_66.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_66.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_67.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_67.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_68.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_68.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_69.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_69.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_7.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_7.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_70.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_70.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_71.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_71.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_72.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_72.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_73.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_73.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_74.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_74.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_75.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_75.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_76.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_76.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_77.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_77.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_78.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_78.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_79.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_79.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_8.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_8.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_80.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_80.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_81.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_81.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_82.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_82.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_83.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_83.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_84.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_84.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_85.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_85.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_86.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_86.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_87.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_87.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_88.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_88.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_89.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_89.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_9.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_9.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_90.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_90.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_91.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_91.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_92.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_92.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_93.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_93.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_94.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_94.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_95.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_95.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_96.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_96.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_97.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_97.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_98.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_98.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_99.wi.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.experts.expert_99.wo.weight": "model-00003-of-00006.safetensors", "encoder.block.23.layer.1.mlp.router.classifier.weight": "model-00003-of-00006.safetensors", "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_0.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_0.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_1.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_1.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_10.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_10.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_100.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_100.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_101.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_101.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_102.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_102.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_103.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_103.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_104.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_104.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_105.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_105.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_106.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_106.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_107.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_107.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_108.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_108.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_109.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_109.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_11.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_11.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_110.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_110.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_111.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_111.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_112.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_112.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_113.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_113.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_114.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_114.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_115.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_115.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_116.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_116.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_117.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_117.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_118.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_118.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_119.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_119.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_12.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_12.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_120.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_120.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_121.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_121.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_122.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_122.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_123.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_123.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_124.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_124.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_125.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_125.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_126.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_126.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_127.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_127.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_13.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_13.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_14.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_14.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_15.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_15.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_16.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_16.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_17.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_17.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_18.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_18.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_19.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_19.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_2.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_2.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_20.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_20.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_21.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_21.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_22.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_22.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_23.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_23.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_24.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_24.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_25.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_25.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_26.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_26.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_27.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_27.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_28.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_28.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_29.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_29.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_3.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_3.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_30.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_30.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_31.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_31.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_32.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_32.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_33.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_33.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_34.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_34.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_35.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_35.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_36.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_36.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_37.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_37.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_38.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_38.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_39.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_39.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_4.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_4.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_40.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_40.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_41.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_41.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_42.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_42.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_43.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_43.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_44.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_44.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_45.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_45.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_46.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_46.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_47.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_47.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_48.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_48.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_49.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_49.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_5.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_5.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_50.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_50.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_51.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_51.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_52.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_52.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_53.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_53.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_54.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_54.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_55.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_55.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_56.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_56.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_57.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_57.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_58.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_58.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_59.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_59.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_6.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_6.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_60.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_60.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_61.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_61.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_62.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_62.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_63.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_63.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_64.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_64.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_65.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_65.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_66.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_66.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_67.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_67.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_68.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_68.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_69.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_69.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_7.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_7.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_70.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_70.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_71.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_71.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_72.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_72.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_73.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_73.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_74.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_74.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_75.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_75.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_76.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_76.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_77.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_77.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_78.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_78.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_79.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_79.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_8.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_8.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_80.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_80.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_81.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_81.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_82.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_82.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_83.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_83.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_84.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_84.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_85.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_85.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_86.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_86.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_87.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_87.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_88.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_88.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_89.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_89.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_9.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_9.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_90.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_90.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_91.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_91.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_92.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_92.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_93.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_93.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_94.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_94.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_95.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_95.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_96.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_96.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_97.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_97.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_98.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_98.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_99.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.experts.expert_99.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.3.layer.1.mlp.router.classifier.weight": "model-00001-of-00006.safetensors", "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors", "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors", "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors", "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors", "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.4.layer.1.mlp.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.4.layer.1.mlp.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_0.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_0.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_1.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_1.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_10.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_10.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_100.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_100.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_101.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_101.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_102.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_102.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_103.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_103.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_104.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_104.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_105.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_105.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_106.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_106.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_107.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_107.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_108.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_108.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_109.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_109.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_11.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_11.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_110.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_110.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_111.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_111.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_112.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_112.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_113.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_113.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_114.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_114.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_115.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_115.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_116.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_116.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_117.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_117.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_118.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_118.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_119.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_119.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_12.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_12.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_120.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_120.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_121.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_121.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_122.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_122.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_123.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_123.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_124.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_124.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_125.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_125.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_126.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_126.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_127.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_127.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_13.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_13.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_14.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_14.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_15.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_15.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_16.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_16.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_17.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_17.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_18.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_18.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_19.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_19.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_2.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_2.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_20.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_20.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_21.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_21.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_22.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_22.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_23.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_23.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_24.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_24.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_25.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_25.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_26.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_26.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_27.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_27.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_28.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_28.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_29.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_29.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_3.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_3.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_30.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_30.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_31.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_31.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_32.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_32.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_33.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_33.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_34.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_34.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_35.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_35.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_36.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_36.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_37.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_37.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_38.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_38.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_39.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_39.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_4.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_4.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_40.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_40.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_41.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_41.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_42.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_42.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_43.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_43.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_44.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_44.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_45.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_45.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_46.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_46.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_47.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_47.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_48.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_48.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_49.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_49.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_5.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_5.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_50.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_50.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_51.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_51.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_52.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_52.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_53.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_53.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_54.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_54.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_55.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_55.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_56.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_56.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_57.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_57.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_58.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_58.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_59.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_59.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_6.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_6.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_60.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_60.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_61.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_61.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_62.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_62.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_63.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_63.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_64.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_64.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_65.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_65.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_66.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_66.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_67.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_67.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_68.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_68.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_69.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_69.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_7.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_7.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_70.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_70.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_71.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_71.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_72.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_72.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_73.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_73.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_74.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_74.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_75.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_75.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_76.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_76.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_77.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_77.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_78.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_78.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_79.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_79.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_8.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_8.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_80.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_80.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_81.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_81.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_82.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_82.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_83.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_83.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_84.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_84.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_85.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_85.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_86.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_86.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_87.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_87.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_88.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_88.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_89.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_89.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_9.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_9.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_90.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_90.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_91.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_91.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_92.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_92.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_93.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_93.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_94.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_94.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_95.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_95.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_96.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_96.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_97.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_97.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_98.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_98.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_99.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.experts.expert_99.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.5.layer.1.mlp.router.classifier.weight": "model-00001-of-00006.safetensors", "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors", "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors", "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors", "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors", "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.6.layer.1.mlp.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.6.layer.1.mlp.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_0.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_0.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_1.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_1.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_10.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_10.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_100.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_100.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_101.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_101.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_102.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_102.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_103.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_103.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_104.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_104.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_105.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_105.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_106.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_106.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_107.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_107.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_108.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_108.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_109.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_109.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_11.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_11.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_110.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_110.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_111.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_111.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_112.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_112.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_113.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_113.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_114.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_114.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_115.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_115.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_116.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_116.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_117.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_117.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_118.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_118.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_119.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_119.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_12.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_12.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_120.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_120.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_121.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_121.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_122.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_122.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_123.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_123.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_124.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_124.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_125.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_125.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_126.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_126.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_127.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_127.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_13.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_13.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_14.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_14.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_15.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_15.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_16.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_16.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_17.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_17.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_18.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_18.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_19.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_19.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_2.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_2.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_20.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_20.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_21.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_21.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_22.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_22.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_23.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_23.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_24.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_24.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_25.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_25.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_26.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_26.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_27.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_27.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_28.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_28.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_29.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_29.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_3.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_3.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_30.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_30.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_31.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_31.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_32.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_32.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_33.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_33.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_34.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_34.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_35.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_35.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_36.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_36.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_37.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_37.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_38.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_38.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_39.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_39.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_4.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_4.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_40.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_40.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_41.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_41.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_42.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_42.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_43.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_43.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_44.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_44.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_45.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_45.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_46.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_46.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_47.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_47.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_48.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_48.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_49.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_49.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_5.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_5.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_50.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_50.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_51.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_51.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_52.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_52.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_53.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_53.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_54.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_54.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_55.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_55.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_56.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_56.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_57.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_57.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_58.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_58.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_59.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_59.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_6.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_6.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_60.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_60.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_61.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_61.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_62.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_62.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_63.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_63.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_64.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_64.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_65.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_65.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_66.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_66.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_67.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_67.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_68.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_68.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_69.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_69.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_7.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_7.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_70.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_70.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_71.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_71.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_72.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_72.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_73.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_73.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_74.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_74.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_75.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_75.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_76.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_76.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_77.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_77.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_78.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_78.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_79.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_79.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_8.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_8.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_80.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_80.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_81.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_81.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_82.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_82.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_83.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_83.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_84.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_84.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_85.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_85.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_86.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_86.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_87.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_87.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_88.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_88.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_89.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_89.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_9.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_9.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_90.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_90.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_91.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_91.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_92.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_92.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_93.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_93.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_94.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_94.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_95.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_95.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_96.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_96.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_97.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_97.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_98.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_98.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_99.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.experts.expert_99.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.7.layer.1.mlp.router.classifier.weight": "model-00001-of-00006.safetensors", "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors", "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors", "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors", "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors", "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.8.layer.1.mlp.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.8.layer.1.mlp.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_0.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_0.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_1.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_1.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_10.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_10.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_100.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_100.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_101.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_101.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_102.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_102.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_103.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_103.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_104.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_104.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_105.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_105.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_106.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_106.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_107.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_107.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_108.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_108.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_109.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_109.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_11.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_11.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_110.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_110.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_111.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_111.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_112.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_112.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_113.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_113.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_114.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_114.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_115.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_115.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_116.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_116.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_117.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_117.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_118.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_118.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_119.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_119.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_12.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_12.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_120.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_120.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_121.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_121.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_122.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_122.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_123.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_123.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_124.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_124.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_125.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_125.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_126.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_126.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_127.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_127.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_13.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_13.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_14.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_14.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_15.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_15.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_16.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_16.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_17.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_17.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_18.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_18.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_19.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_19.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_2.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_2.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_20.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_20.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_21.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_21.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_22.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_22.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_23.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_23.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_24.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_24.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_25.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_25.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_26.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_26.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_27.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_27.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_28.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_28.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_29.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_29.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_3.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_3.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_30.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_30.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_31.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_31.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_32.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_32.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_33.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_33.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_34.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_34.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_35.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_35.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_36.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_36.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_37.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_37.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_38.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_38.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_39.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_39.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_4.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_4.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_40.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_40.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_41.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_41.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_42.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_42.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_43.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_43.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_44.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_44.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_45.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_45.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_46.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_46.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_47.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_47.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_48.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_48.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_49.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_49.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_5.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_5.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_50.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_50.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_51.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_51.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_52.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_52.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_53.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_53.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_54.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_54.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_55.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_55.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_56.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_56.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_57.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_57.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_58.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_58.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_59.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_59.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_6.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_6.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_60.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_60.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_61.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_61.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_62.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_62.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_63.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_63.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_64.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_64.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_65.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_65.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_66.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_66.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_67.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_67.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_68.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_68.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_69.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_69.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_7.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_7.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_70.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_70.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_71.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_71.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_72.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_72.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_73.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_73.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_74.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_74.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_75.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_75.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_76.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_76.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_77.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_77.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_78.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_78.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_79.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_79.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_8.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_8.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_80.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_80.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_81.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_81.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_82.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_82.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_83.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_83.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_84.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_84.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_85.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_85.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_86.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_86.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_87.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_87.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_88.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_88.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_89.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_89.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_9.wi.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_9.wo.weight": "model-00001-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_90.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_90.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_91.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_91.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_92.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_92.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_93.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_93.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_94.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_94.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_95.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_95.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_96.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_96.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_97.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_97.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_98.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_98.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_99.wi.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.experts.expert_99.wo.weight": "model-00002-of-00006.safetensors", "encoder.block.9.layer.1.mlp.router.classifier.weight": "model-00001-of-00006.safetensors", "encoder.embed_tokens.weight": "model-00001-of-00006.safetensors", "encoder.final_layer_norm.weight": "model-00003-of-00006.safetensors", "lm_head.weight": "model-00006-of-00006.safetensors", "shared.weight": "model-00001-of-00006.safetensors" } }