{
  "metadata": {
    "total_size": 359999963128.0
  },
  "weight_map": {
    "lm_head.weight": "model-00131-of-00131.safetensors",
    "model.language_model.embed_tokens.weight": "model-00130-of-00131.safetensors",
    "model.language_model.hyper_connection_mixer.hc_norm.weight": "model-00001-of-00131.safetensors",
    "model.language_model.hyper_connection_mixer.input_mix_weight_down.weight": "model-00001-of-00131.safetensors",
    "model.language_model.hyper_connection_mixer.input_mix_weight_up.weight": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.attn_hyper_connection.hc_norm.weight": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00131.safetensors",
    "model.language_model.layers.0.mlp.experts.down_proj": "model-00003-of-00131.safetensors",
    "model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00002-of-00131.safetensors",
    "model.language_model.layers.0.mlp.gate.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.0.mlp.shared_expert.down_proj.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.0.mlp.shared_expert.up_proj.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.0.mlp.shared_expert_gate.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.0.mlp_hyper_connection.block_inject_weight.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.0.mlp_hyper_connection.hc_norm.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_down.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_up.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.attn_hyper_connection.block_inject_weight.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.attn_hyper_connection.hc_norm.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.attn_hyper_connection.input_mix_weight_down.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.attn_hyper_connection.input_mix_weight_up.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.linear_attn.A_log": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.linear_attn.dt_bias": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.linear_attn.norm.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00003-of-00131.safetensors",
    "model.language_model.layers.1.mlp.experts.down_proj": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00004-of-00131.safetensors",
    "model.language_model.layers.1.mlp.gate.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.mlp.shared_expert.down_proj.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.mlp.shared_expert.up_proj.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.mlp.shared_expert_gate.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.mlp_hyper_connection.block_inject_weight.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.mlp_hyper_connection.hc_norm.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_down.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_up.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.ple.conv1d.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.1.ple.key_proj.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.ple.norm_conv.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.ple.norm_key.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.ple.norm_query.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.layer_multipliers": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_0.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_1.weight": "model-00005-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_10.weight": "model-00008-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_100.weight": "model-00030-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_101.weight": "model-00030-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_102.weight": "model-00031-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_103.weight": "model-00031-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_104.weight": "model-00031-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_105.weight": "model-00031-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_106.weight": "model-00032-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_107.weight": "model-00032-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_108.weight": "model-00032-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_109.weight": "model-00032-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_11.weight": "model-00008-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_110.weight": "model-00033-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_111.weight": "model-00033-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_112.weight": "model-00033-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_113.weight": "model-00033-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_114.weight": "model-00034-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_115.weight": "model-00034-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_116.weight": "model-00034-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_117.weight": "model-00034-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_118.weight": "model-00035-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_119.weight": "model-00035-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_12.weight": "model-00008-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_120.weight": "model-00035-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_121.weight": "model-00035-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_122.weight": "model-00036-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_123.weight": "model-00036-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_124.weight": "model-00036-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_125.weight": "model-00036-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_126.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_127.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_13.weight": "model-00008-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_14.weight": "model-00009-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_15.weight": "model-00009-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_16.weight": "model-00009-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_17.weight": "model-00009-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_18.weight": "model-00010-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_19.weight": "model-00010-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_2.weight": "model-00006-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_20.weight": "model-00010-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_21.weight": "model-00010-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_22.weight": "model-00011-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_23.weight": "model-00011-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_24.weight": "model-00011-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_25.weight": "model-00011-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_26.weight": "model-00012-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_27.weight": "model-00012-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_28.weight": "model-00012-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_29.weight": "model-00012-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_3.weight": "model-00006-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_30.weight": "model-00013-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_31.weight": "model-00013-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_32.weight": "model-00013-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_33.weight": "model-00013-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_34.weight": "model-00014-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_35.weight": "model-00014-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_36.weight": "model-00014-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_37.weight": "model-00014-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_38.weight": "model-00015-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_39.weight": "model-00015-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_4.weight": "model-00006-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_40.weight": "model-00015-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_41.weight": "model-00015-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_42.weight": "model-00016-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_43.weight": "model-00016-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_44.weight": "model-00016-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_45.weight": "model-00016-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_46.weight": "model-00017-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_47.weight": "model-00017-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_48.weight": "model-00017-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_49.weight": "model-00017-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_5.weight": "model-00006-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_50.weight": "model-00018-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_51.weight": "model-00018-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_52.weight": "model-00018-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_53.weight": "model-00018-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_54.weight": "model-00019-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_55.weight": "model-00019-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_56.weight": "model-00019-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_57.weight": "model-00019-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_58.weight": "model-00020-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_59.weight": "model-00020-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_6.weight": "model-00007-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_60.weight": "model-00020-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_61.weight": "model-00020-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_62.weight": "model-00021-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_63.weight": "model-00021-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_64.weight": "model-00021-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_65.weight": "model-00021-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_66.weight": "model-00022-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_67.weight": "model-00022-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_68.weight": "model-00022-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_69.weight": "model-00022-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_7.weight": "model-00007-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_70.weight": "model-00023-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_71.weight": "model-00023-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_72.weight": "model-00023-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_73.weight": "model-00023-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_74.weight": "model-00024-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_75.weight": "model-00024-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_76.weight": "model-00024-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_77.weight": "model-00024-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_78.weight": "model-00025-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_79.weight": "model-00025-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_8.weight": "model-00007-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_80.weight": "model-00025-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_81.weight": "model-00025-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_82.weight": "model-00026-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_83.weight": "model-00026-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_84.weight": "model-00026-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_85.weight": "model-00026-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_86.weight": "model-00027-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_87.weight": "model-00027-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_88.weight": "model-00027-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_89.weight": "model-00027-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_9.weight": "model-00007-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_90.weight": "model-00028-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_91.weight": "model-00028-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_92.weight": "model-00028-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_93.weight": "model-00028-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_94.weight": "model-00029-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_95.weight": "model-00029-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_96.weight": "model-00029-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_97.weight": "model-00029-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_98.weight": "model-00030-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_embedding.shard_99.weight": "model-00030-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_heads_offsets": "model-00037-of-00131.safetensors",
    "model.language_model.layers.1.ple.ple_embedding.ngram_heads_vocab_sizes": "model-00037-of-00131.safetensors",
    "model.language_model.layers.1.ple.value_proj.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.attn_hyper_connection.block_inject_weight.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.attn_hyper_connection.hc_norm.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.attn_hyper_connection.input_mix_weight_down.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.attn_hyper_connection.input_mix_weight_up.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.linear_attn.A_log": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.linear_attn.dt_bias": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.linear_attn.norm.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00037-of-00131.safetensors",
    "model.language_model.layers.10.mlp.experts.down_proj": "model-00039-of-00131.safetensors",
    "model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00038-of-00131.safetensors",
    "model.language_model.layers.10.mlp.gate.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.10.mlp.shared_expert.down_proj.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.10.mlp.shared_expert.up_proj.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.10.mlp.shared_expert_gate.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.10.mlp_hyper_connection.block_inject_weight.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.10.mlp_hyper_connection.hc_norm.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.10.mlp_hyper_connection.input_mix_weight_down.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.10.mlp_hyper_connection.input_mix_weight_up.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.11.attn_hyper_connection.block_inject_weight.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.11.attn_hyper_connection.hc_norm.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.11.attn_hyper_connection.input_mix_weight_down.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.11.attn_hyper_connection.input_mix_weight_up.weight": "model-00039-of-00131.safetensors",
    "model.language_model.layers.11.mlp.experts.down_proj": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00040-of-00131.safetensors",
    "model.language_model.layers.11.mlp.gate.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.mlp.shared_expert.down_proj.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.mlp.shared_expert.up_proj.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.mlp.shared_expert_gate.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.mlp_hyper_connection.block_inject_weight.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.mlp_hyper_connection.hc_norm.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.mlp_hyper_connection.input_mix_weight_down.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.mlp_hyper_connection.input_mix_weight_up.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.self_attn.indexer.index_qk_proj.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.self_attn.indexer.k_layernorm.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.self_attn.indexer.q_layernorm.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.attn_hyper_connection.block_inject_weight.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.attn_hyper_connection.hc_norm.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.attn_hyper_connection.input_mix_weight_down.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.attn_hyper_connection.input_mix_weight_up.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.linear_attn.A_log": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.linear_attn.dt_bias": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.linear_attn.norm.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00041-of-00131.safetensors",
    "model.language_model.layers.12.mlp.experts.down_proj": "model-00043-of-00131.safetensors",
    "model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00042-of-00131.safetensors",
    "model.language_model.layers.12.mlp.gate.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.12.mlp.shared_expert.down_proj.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.12.mlp.shared_expert.up_proj.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.12.mlp.shared_expert_gate.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.12.mlp_hyper_connection.block_inject_weight.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.12.mlp_hyper_connection.hc_norm.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.12.mlp_hyper_connection.input_mix_weight_down.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.12.mlp_hyper_connection.input_mix_weight_up.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.attn_hyper_connection.block_inject_weight.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.attn_hyper_connection.hc_norm.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.attn_hyper_connection.input_mix_weight_down.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.attn_hyper_connection.input_mix_weight_up.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.linear_attn.A_log": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.linear_attn.dt_bias": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.linear_attn.norm.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00043-of-00131.safetensors",
    "model.language_model.layers.13.mlp.experts.down_proj": "model-00045-of-00131.safetensors",
    "model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00044-of-00131.safetensors",
    "model.language_model.layers.13.mlp.gate.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.13.mlp.shared_expert.down_proj.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.13.mlp.shared_expert.up_proj.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.13.mlp.shared_expert_gate.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.13.mlp_hyper_connection.block_inject_weight.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.13.mlp_hyper_connection.hc_norm.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.13.mlp_hyper_connection.input_mix_weight_down.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.13.mlp_hyper_connection.input_mix_weight_up.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.attn_hyper_connection.block_inject_weight.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.attn_hyper_connection.hc_norm.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.attn_hyper_connection.input_mix_weight_down.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.attn_hyper_connection.input_mix_weight_up.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.linear_attn.A_log": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.linear_attn.dt_bias": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.linear_attn.norm.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00045-of-00131.safetensors",
    "model.language_model.layers.14.mlp.experts.down_proj": "model-00047-of-00131.safetensors",
    "model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00046-of-00131.safetensors",
    "model.language_model.layers.14.mlp.gate.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.14.mlp.shared_expert.down_proj.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.14.mlp.shared_expert.up_proj.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.14.mlp.shared_expert_gate.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.14.mlp_hyper_connection.block_inject_weight.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.14.mlp_hyper_connection.hc_norm.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.14.mlp_hyper_connection.input_mix_weight_down.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.14.mlp_hyper_connection.input_mix_weight_up.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.15.attn_hyper_connection.block_inject_weight.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.15.attn_hyper_connection.hc_norm.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.15.attn_hyper_connection.input_mix_weight_down.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.15.attn_hyper_connection.input_mix_weight_up.weight": "model-00047-of-00131.safetensors",
    "model.language_model.layers.15.mlp.experts.down_proj": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00048-of-00131.safetensors",
    "model.language_model.layers.15.mlp.gate.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.mlp.shared_expert.down_proj.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.mlp.shared_expert.up_proj.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.mlp.shared_expert_gate.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.mlp_hyper_connection.block_inject_weight.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.mlp_hyper_connection.hc_norm.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.mlp_hyper_connection.input_mix_weight_down.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.mlp_hyper_connection.input_mix_weight_up.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.self_attn.indexer.index_qk_proj.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.self_attn.indexer.k_layernorm.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.self_attn.indexer.q_layernorm.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.attn_hyper_connection.block_inject_weight.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.attn_hyper_connection.hc_norm.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.attn_hyper_connection.input_mix_weight_down.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.attn_hyper_connection.input_mix_weight_up.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.linear_attn.A_log": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.linear_attn.dt_bias": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.linear_attn.norm.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00049-of-00131.safetensors",
    "model.language_model.layers.16.mlp.experts.down_proj": "model-00051-of-00131.safetensors",
    "model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00050-of-00131.safetensors",
    "model.language_model.layers.16.mlp.gate.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.16.mlp.shared_expert.down_proj.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.16.mlp.shared_expert.up_proj.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.16.mlp.shared_expert_gate.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.16.mlp_hyper_connection.block_inject_weight.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.16.mlp_hyper_connection.hc_norm.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.16.mlp_hyper_connection.input_mix_weight_down.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.16.mlp_hyper_connection.input_mix_weight_up.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.attn_hyper_connection.block_inject_weight.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.attn_hyper_connection.hc_norm.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.attn_hyper_connection.input_mix_weight_down.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.attn_hyper_connection.input_mix_weight_up.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.linear_attn.A_log": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.linear_attn.dt_bias": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.linear_attn.norm.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00051-of-00131.safetensors",
    "model.language_model.layers.17.mlp.experts.down_proj": "model-00053-of-00131.safetensors",
    "model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00052-of-00131.safetensors",
    "model.language_model.layers.17.mlp.gate.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.17.mlp.shared_expert.down_proj.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.17.mlp.shared_expert.up_proj.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.17.mlp.shared_expert_gate.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.17.mlp_hyper_connection.block_inject_weight.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.17.mlp_hyper_connection.hc_norm.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.17.mlp_hyper_connection.input_mix_weight_down.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.17.mlp_hyper_connection.input_mix_weight_up.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.attn_hyper_connection.block_inject_weight.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.attn_hyper_connection.hc_norm.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.attn_hyper_connection.input_mix_weight_down.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.attn_hyper_connection.input_mix_weight_up.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.linear_attn.A_log": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.linear_attn.dt_bias": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.linear_attn.norm.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00053-of-00131.safetensors",
    "model.language_model.layers.18.mlp.experts.down_proj": "model-00055-of-00131.safetensors",
    "model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00054-of-00131.safetensors",
    "model.language_model.layers.18.mlp.gate.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.18.mlp.shared_expert.down_proj.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.18.mlp.shared_expert.up_proj.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.18.mlp.shared_expert_gate.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.18.mlp_hyper_connection.block_inject_weight.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.18.mlp_hyper_connection.hc_norm.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.18.mlp_hyper_connection.input_mix_weight_down.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.18.mlp_hyper_connection.input_mix_weight_up.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.19.attn_hyper_connection.block_inject_weight.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.19.attn_hyper_connection.hc_norm.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.19.attn_hyper_connection.input_mix_weight_down.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.19.attn_hyper_connection.input_mix_weight_up.weight": "model-00055-of-00131.safetensors",
    "model.language_model.layers.19.mlp.experts.down_proj": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00056-of-00131.safetensors",
    "model.language_model.layers.19.mlp.gate.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.mlp.shared_expert.down_proj.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.mlp.shared_expert.up_proj.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.mlp.shared_expert_gate.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.mlp_hyper_connection.block_inject_weight.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.mlp_hyper_connection.hc_norm.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.mlp_hyper_connection.input_mix_weight_down.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.mlp_hyper_connection.input_mix_weight_up.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.self_attn.indexer.index_qk_proj.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.self_attn.indexer.k_layernorm.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.self_attn.indexer.q_layernorm.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.attn_hyper_connection.block_inject_weight.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.attn_hyper_connection.hc_norm.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.attn_hyper_connection.input_mix_weight_down.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.attn_hyper_connection.input_mix_weight_up.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.linear_attn.A_log": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.linear_attn.dt_bias": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.linear_attn.norm.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00057-of-00131.safetensors",
    "model.language_model.layers.2.mlp.experts.down_proj": "model-00059-of-00131.safetensors",
    "model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00058-of-00131.safetensors",
    "model.language_model.layers.2.mlp.gate.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.2.mlp.shared_expert.down_proj.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.2.mlp.shared_expert.up_proj.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.2.mlp.shared_expert_gate.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.2.mlp_hyper_connection.block_inject_weight.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.2.mlp_hyper_connection.hc_norm.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_down.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_up.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.20.attn_hyper_connection.block_inject_weight.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.20.attn_hyper_connection.hc_norm.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.20.attn_hyper_connection.input_mix_weight_down.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.20.attn_hyper_connection.input_mix_weight_up.weight": "model-00059-of-00131.safetensors",
    "model.language_model.layers.20.linear_attn.A_log": "model-00059-of-00131.safetensors",
    "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00060-of-00131.safetensors",
    "model.language_model.layers.20.linear_attn.dt_bias": "model-00060-of-00131.safetensors",
    "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00060-of-00131.safetensors",
    "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00060-of-00131.safetensors",
    "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00060-of-00131.safetensors",
    "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00060-of-00131.safetensors",
    "model.language_model.layers.20.linear_attn.norm.weight": "model-00060-of-00131.safetensors",
    "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00060-of-00131.safetensors",
    "model.language_model.layers.20.mlp.experts.down_proj": "model-00062-of-00131.safetensors",
    "model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00061-of-00131.safetensors",
    "model.language_model.layers.20.mlp.gate.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.20.mlp.shared_expert.down_proj.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.20.mlp.shared_expert.up_proj.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.20.mlp.shared_expert_gate.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.20.mlp_hyper_connection.block_inject_weight.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.20.mlp_hyper_connection.hc_norm.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.20.mlp_hyper_connection.input_mix_weight_down.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.20.mlp_hyper_connection.input_mix_weight_up.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.attn_hyper_connection.block_inject_weight.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.attn_hyper_connection.hc_norm.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.attn_hyper_connection.input_mix_weight_down.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.attn_hyper_connection.input_mix_weight_up.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.linear_attn.A_log": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.linear_attn.dt_bias": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.linear_attn.norm.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00062-of-00131.safetensors",
    "model.language_model.layers.21.mlp.experts.down_proj": "model-00064-of-00131.safetensors",
    "model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00063-of-00131.safetensors",
    "model.language_model.layers.21.mlp.gate.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.21.mlp.shared_expert.down_proj.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.21.mlp.shared_expert.up_proj.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.21.mlp.shared_expert_gate.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.21.mlp_hyper_connection.block_inject_weight.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.21.mlp_hyper_connection.hc_norm.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.21.mlp_hyper_connection.input_mix_weight_down.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.21.mlp_hyper_connection.input_mix_weight_up.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.attn_hyper_connection.block_inject_weight.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.attn_hyper_connection.hc_norm.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.attn_hyper_connection.input_mix_weight_down.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.attn_hyper_connection.input_mix_weight_up.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.linear_attn.A_log": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.linear_attn.dt_bias": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.linear_attn.norm.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00064-of-00131.safetensors",
    "model.language_model.layers.22.mlp.experts.down_proj": "model-00066-of-00131.safetensors",
    "model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00065-of-00131.safetensors",
    "model.language_model.layers.22.mlp.gate.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.22.mlp.shared_expert.down_proj.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.22.mlp.shared_expert.up_proj.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.22.mlp.shared_expert_gate.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.22.mlp_hyper_connection.block_inject_weight.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.22.mlp_hyper_connection.hc_norm.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.22.mlp_hyper_connection.input_mix_weight_down.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.22.mlp_hyper_connection.input_mix_weight_up.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.23.attn_hyper_connection.block_inject_weight.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.23.attn_hyper_connection.hc_norm.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.23.attn_hyper_connection.input_mix_weight_down.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.23.attn_hyper_connection.input_mix_weight_up.weight": "model-00066-of-00131.safetensors",
    "model.language_model.layers.23.mlp.experts.down_proj": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00067-of-00131.safetensors",
    "model.language_model.layers.23.mlp.gate.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.mlp.shared_expert.down_proj.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.mlp.shared_expert.up_proj.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.mlp.shared_expert_gate.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.mlp_hyper_connection.block_inject_weight.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.mlp_hyper_connection.hc_norm.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.mlp_hyper_connection.input_mix_weight_down.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.mlp_hyper_connection.input_mix_weight_up.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.self_attn.indexer.index_qk_proj.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.self_attn.indexer.k_layernorm.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.self_attn.indexer.q_layernorm.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.attn_hyper_connection.block_inject_weight.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.attn_hyper_connection.hc_norm.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.attn_hyper_connection.input_mix_weight_down.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.attn_hyper_connection.input_mix_weight_up.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.linear_attn.A_log": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.linear_attn.dt_bias": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.linear_attn.norm.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00068-of-00131.safetensors",
    "model.language_model.layers.24.mlp.experts.down_proj": "model-00070-of-00131.safetensors",
    "model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00069-of-00131.safetensors",
    "model.language_model.layers.24.mlp.gate.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.24.mlp.shared_expert.down_proj.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.24.mlp.shared_expert.up_proj.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.24.mlp.shared_expert_gate.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.24.mlp_hyper_connection.block_inject_weight.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.24.mlp_hyper_connection.hc_norm.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.24.mlp_hyper_connection.input_mix_weight_down.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.24.mlp_hyper_connection.input_mix_weight_up.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.attn_hyper_connection.block_inject_weight.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.attn_hyper_connection.hc_norm.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.attn_hyper_connection.input_mix_weight_down.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.attn_hyper_connection.input_mix_weight_up.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.linear_attn.A_log": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.linear_attn.dt_bias": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.linear_attn.norm.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00070-of-00131.safetensors",
    "model.language_model.layers.25.mlp.experts.down_proj": "model-00072-of-00131.safetensors",
    "model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00071-of-00131.safetensors",
    "model.language_model.layers.25.mlp.gate.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.25.mlp.shared_expert.down_proj.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.25.mlp.shared_expert.up_proj.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.25.mlp.shared_expert_gate.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.25.mlp_hyper_connection.block_inject_weight.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.25.mlp_hyper_connection.hc_norm.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.25.mlp_hyper_connection.input_mix_weight_down.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.25.mlp_hyper_connection.input_mix_weight_up.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.attn_hyper_connection.block_inject_weight.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.attn_hyper_connection.hc_norm.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.attn_hyper_connection.input_mix_weight_down.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.attn_hyper_connection.input_mix_weight_up.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.linear_attn.A_log": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.linear_attn.dt_bias": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.linear_attn.norm.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00072-of-00131.safetensors",
    "model.language_model.layers.26.mlp.experts.down_proj": "model-00074-of-00131.safetensors",
    "model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00073-of-00131.safetensors",
    "model.language_model.layers.26.mlp.gate.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.26.mlp.shared_expert.down_proj.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.26.mlp.shared_expert.up_proj.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.26.mlp.shared_expert_gate.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.26.mlp_hyper_connection.block_inject_weight.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.26.mlp_hyper_connection.hc_norm.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.26.mlp_hyper_connection.input_mix_weight_down.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.26.mlp_hyper_connection.input_mix_weight_up.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.27.attn_hyper_connection.block_inject_weight.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.27.attn_hyper_connection.hc_norm.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.27.attn_hyper_connection.input_mix_weight_down.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.27.attn_hyper_connection.input_mix_weight_up.weight": "model-00074-of-00131.safetensors",
    "model.language_model.layers.27.mlp.experts.down_proj": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00075-of-00131.safetensors",
    "model.language_model.layers.27.mlp.gate.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.mlp.shared_expert.down_proj.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.mlp.shared_expert.up_proj.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.mlp.shared_expert_gate.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.mlp_hyper_connection.block_inject_weight.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.mlp_hyper_connection.hc_norm.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.mlp_hyper_connection.input_mix_weight_down.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.mlp_hyper_connection.input_mix_weight_up.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.self_attn.indexer.index_qk_proj.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.self_attn.indexer.k_layernorm.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.self_attn.indexer.q_layernorm.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.attn_hyper_connection.block_inject_weight.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.attn_hyper_connection.hc_norm.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.attn_hyper_connection.input_mix_weight_down.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.attn_hyper_connection.input_mix_weight_up.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.linear_attn.A_log": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.linear_attn.dt_bias": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.linear_attn.norm.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00076-of-00131.safetensors",
    "model.language_model.layers.28.mlp.experts.down_proj": "model-00078-of-00131.safetensors",
    "model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00077-of-00131.safetensors",
    "model.language_model.layers.28.mlp.gate.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.28.mlp.shared_expert.down_proj.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.28.mlp.shared_expert.up_proj.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.28.mlp.shared_expert_gate.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.28.mlp_hyper_connection.block_inject_weight.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.28.mlp_hyper_connection.hc_norm.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.28.mlp_hyper_connection.input_mix_weight_down.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.28.mlp_hyper_connection.input_mix_weight_up.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.attn_hyper_connection.block_inject_weight.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.attn_hyper_connection.hc_norm.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.attn_hyper_connection.input_mix_weight_down.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.attn_hyper_connection.input_mix_weight_up.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.linear_attn.A_log": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.linear_attn.dt_bias": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.linear_attn.norm.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00078-of-00131.safetensors",
    "model.language_model.layers.29.mlp.experts.down_proj": "model-00080-of-00131.safetensors",
    "model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00079-of-00131.safetensors",
    "model.language_model.layers.29.mlp.gate.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.29.mlp.shared_expert.down_proj.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.29.mlp.shared_expert.up_proj.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.29.mlp.shared_expert_gate.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.29.mlp_hyper_connection.block_inject_weight.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.29.mlp_hyper_connection.hc_norm.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.29.mlp_hyper_connection.input_mix_weight_down.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.29.mlp_hyper_connection.input_mix_weight_up.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.3.attn_hyper_connection.block_inject_weight.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.3.attn_hyper_connection.hc_norm.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.3.attn_hyper_connection.input_mix_weight_down.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.3.attn_hyper_connection.input_mix_weight_up.weight": "model-00080-of-00131.safetensors",
    "model.language_model.layers.3.mlp.experts.down_proj": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00081-of-00131.safetensors",
    "model.language_model.layers.3.mlp.gate.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.mlp.shared_expert.down_proj.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.mlp.shared_expert.up_proj.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.mlp.shared_expert_gate.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.mlp_hyper_connection.block_inject_weight.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.mlp_hyper_connection.hc_norm.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_down.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_up.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.self_attn.indexer.index_qk_proj.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.self_attn.indexer.k_layernorm.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.self_attn.indexer.q_layernorm.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.attn_hyper_connection.block_inject_weight.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.attn_hyper_connection.hc_norm.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.attn_hyper_connection.input_mix_weight_down.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.attn_hyper_connection.input_mix_weight_up.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.linear_attn.A_log": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.linear_attn.dt_bias": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.linear_attn.norm.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00082-of-00131.safetensors",
    "model.language_model.layers.30.mlp.experts.down_proj": "model-00084-of-00131.safetensors",
    "model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00083-of-00131.safetensors",
    "model.language_model.layers.30.mlp.gate.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.30.mlp.shared_expert.down_proj.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.30.mlp.shared_expert.up_proj.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.30.mlp.shared_expert_gate.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.30.mlp_hyper_connection.block_inject_weight.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.30.mlp_hyper_connection.hc_norm.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.30.mlp_hyper_connection.input_mix_weight_down.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.30.mlp_hyper_connection.input_mix_weight_up.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.31.attn_hyper_connection.block_inject_weight.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.31.attn_hyper_connection.hc_norm.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.31.attn_hyper_connection.input_mix_weight_down.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.31.attn_hyper_connection.input_mix_weight_up.weight": "model-00084-of-00131.safetensors",
    "model.language_model.layers.31.mlp.experts.down_proj": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00085-of-00131.safetensors",
    "model.language_model.layers.31.mlp.gate.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.mlp.shared_expert.down_proj.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.mlp.shared_expert.up_proj.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.mlp.shared_expert_gate.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.mlp_hyper_connection.block_inject_weight.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.mlp_hyper_connection.hc_norm.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.mlp_hyper_connection.input_mix_weight_down.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.mlp_hyper_connection.input_mix_weight_up.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.self_attn.indexer.index_qk_proj.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.self_attn.indexer.k_layernorm.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.self_attn.indexer.q_layernorm.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.attn_hyper_connection.block_inject_weight.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.attn_hyper_connection.hc_norm.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.attn_hyper_connection.input_mix_weight_down.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.attn_hyper_connection.input_mix_weight_up.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.linear_attn.A_log": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.linear_attn.conv1d.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.linear_attn.dt_bias": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.linear_attn.norm.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.linear_attn.out_proj.weight": "model-00086-of-00131.safetensors",
    "model.language_model.layers.32.mlp.experts.down_proj": "model-00088-of-00131.safetensors",
    "model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00087-of-00131.safetensors",
    "model.language_model.layers.32.mlp.gate.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.32.mlp.shared_expert.down_proj.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.32.mlp.shared_expert.up_proj.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.32.mlp.shared_expert_gate.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.32.mlp_hyper_connection.block_inject_weight.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.32.mlp_hyper_connection.hc_norm.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.32.mlp_hyper_connection.input_mix_weight_down.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.32.mlp_hyper_connection.input_mix_weight_up.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.attn_hyper_connection.block_inject_weight.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.attn_hyper_connection.hc_norm.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.attn_hyper_connection.input_mix_weight_down.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.attn_hyper_connection.input_mix_weight_up.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.linear_attn.A_log": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.linear_attn.conv1d.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.linear_attn.dt_bias": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.linear_attn.norm.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.linear_attn.out_proj.weight": "model-00088-of-00131.safetensors",
    "model.language_model.layers.33.mlp.experts.down_proj": "model-00090-of-00131.safetensors",
    "model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00089-of-00131.safetensors",
    "model.language_model.layers.33.mlp.gate.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.33.mlp.shared_expert.down_proj.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.33.mlp.shared_expert.up_proj.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.33.mlp.shared_expert_gate.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.33.mlp_hyper_connection.block_inject_weight.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.33.mlp_hyper_connection.hc_norm.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.33.mlp_hyper_connection.input_mix_weight_down.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.33.mlp_hyper_connection.input_mix_weight_up.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.attn_hyper_connection.block_inject_weight.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.attn_hyper_connection.hc_norm.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.attn_hyper_connection.input_mix_weight_down.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.attn_hyper_connection.input_mix_weight_up.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.linear_attn.A_log": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.linear_attn.conv1d.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.linear_attn.dt_bias": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.linear_attn.norm.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.linear_attn.out_proj.weight": "model-00090-of-00131.safetensors",
    "model.language_model.layers.34.mlp.experts.down_proj": "model-00092-of-00131.safetensors",
    "model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00091-of-00131.safetensors",
    "model.language_model.layers.34.mlp.gate.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.34.mlp.shared_expert.down_proj.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.34.mlp.shared_expert.up_proj.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.34.mlp.shared_expert_gate.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.34.mlp_hyper_connection.block_inject_weight.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.34.mlp_hyper_connection.hc_norm.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.34.mlp_hyper_connection.input_mix_weight_down.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.34.mlp_hyper_connection.input_mix_weight_up.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.35.attn_hyper_connection.block_inject_weight.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.35.attn_hyper_connection.hc_norm.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.35.attn_hyper_connection.input_mix_weight_down.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.35.attn_hyper_connection.input_mix_weight_up.weight": "model-00092-of-00131.safetensors",
    "model.language_model.layers.35.mlp.experts.down_proj": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00093-of-00131.safetensors",
    "model.language_model.layers.35.mlp.gate.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.mlp.shared_expert.down_proj.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.mlp.shared_expert.up_proj.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.mlp.shared_expert_gate.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.mlp_hyper_connection.block_inject_weight.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.mlp_hyper_connection.hc_norm.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.mlp_hyper_connection.input_mix_weight_down.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.mlp_hyper_connection.input_mix_weight_up.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.self_attn.indexer.index_qk_proj.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.self_attn.indexer.k_layernorm.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.self_attn.indexer.q_layernorm.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.attn_hyper_connection.block_inject_weight.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.attn_hyper_connection.hc_norm.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.attn_hyper_connection.input_mix_weight_down.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.attn_hyper_connection.input_mix_weight_up.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.linear_attn.A_log": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.linear_attn.conv1d.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.linear_attn.dt_bias": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.linear_attn.norm.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.linear_attn.out_proj.weight": "model-00094-of-00131.safetensors",
    "model.language_model.layers.36.mlp.experts.down_proj": "model-00096-of-00131.safetensors",
    "model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00095-of-00131.safetensors",
    "model.language_model.layers.36.mlp.gate.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.36.mlp.shared_expert.down_proj.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.36.mlp.shared_expert.up_proj.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.36.mlp.shared_expert_gate.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.36.mlp_hyper_connection.block_inject_weight.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.36.mlp_hyper_connection.hc_norm.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.36.mlp_hyper_connection.input_mix_weight_down.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.36.mlp_hyper_connection.input_mix_weight_up.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.attn_hyper_connection.block_inject_weight.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.attn_hyper_connection.hc_norm.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.attn_hyper_connection.input_mix_weight_down.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.attn_hyper_connection.input_mix_weight_up.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.linear_attn.A_log": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.linear_attn.conv1d.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.linear_attn.dt_bias": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.linear_attn.norm.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.linear_attn.out_proj.weight": "model-00096-of-00131.safetensors",
    "model.language_model.layers.37.mlp.experts.down_proj": "model-00098-of-00131.safetensors",
    "model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00097-of-00131.safetensors",
    "model.language_model.layers.37.mlp.gate.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.37.mlp.shared_expert.down_proj.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.37.mlp.shared_expert.up_proj.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.37.mlp.shared_expert_gate.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.37.mlp_hyper_connection.block_inject_weight.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.37.mlp_hyper_connection.hc_norm.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.37.mlp_hyper_connection.input_mix_weight_down.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.37.mlp_hyper_connection.input_mix_weight_up.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.attn_hyper_connection.block_inject_weight.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.attn_hyper_connection.hc_norm.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.attn_hyper_connection.input_mix_weight_down.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.attn_hyper_connection.input_mix_weight_up.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.linear_attn.A_log": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.linear_attn.conv1d.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.linear_attn.dt_bias": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.linear_attn.norm.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.linear_attn.out_proj.weight": "model-00098-of-00131.safetensors",
    "model.language_model.layers.38.mlp.experts.down_proj": "model-00100-of-00131.safetensors",
    "model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00099-of-00131.safetensors",
    "model.language_model.layers.38.mlp.gate.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.38.mlp.shared_expert.down_proj.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.38.mlp.shared_expert.up_proj.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.38.mlp.shared_expert_gate.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.38.mlp_hyper_connection.block_inject_weight.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.38.mlp_hyper_connection.hc_norm.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.38.mlp_hyper_connection.input_mix_weight_down.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.38.mlp_hyper_connection.input_mix_weight_up.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.39.attn_hyper_connection.block_inject_weight.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.39.attn_hyper_connection.hc_norm.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.39.attn_hyper_connection.input_mix_weight_down.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.39.attn_hyper_connection.input_mix_weight_up.weight": "model-00100-of-00131.safetensors",
    "model.language_model.layers.39.mlp.experts.down_proj": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00101-of-00131.safetensors",
    "model.language_model.layers.39.mlp.gate.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.mlp.shared_expert.down_proj.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.mlp.shared_expert.up_proj.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.mlp.shared_expert_gate.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.mlp_hyper_connection.block_inject_weight.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.mlp_hyper_connection.hc_norm.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.mlp_hyper_connection.input_mix_weight_down.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.mlp_hyper_connection.input_mix_weight_up.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.self_attn.indexer.index_qk_proj.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.self_attn.indexer.k_layernorm.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.self_attn.indexer.q_layernorm.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.self_attn.k_norm.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.self_attn.k_proj.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.self_attn.o_proj.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.self_attn.q_norm.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.self_attn.q_proj.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.39.self_attn.v_proj.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.attn_hyper_connection.block_inject_weight.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.attn_hyper_connection.hc_norm.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.attn_hyper_connection.input_mix_weight_down.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.attn_hyper_connection.input_mix_weight_up.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.linear_attn.A_log": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.linear_attn.dt_bias": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.linear_attn.norm.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00102-of-00131.safetensors",
    "model.language_model.layers.4.mlp.experts.down_proj": "model-00104-of-00131.safetensors",
    "model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00103-of-00131.safetensors",
    "model.language_model.layers.4.mlp.gate.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.4.mlp.shared_expert.down_proj.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.4.mlp.shared_expert.up_proj.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.4.mlp.shared_expert_gate.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.4.mlp_hyper_connection.block_inject_weight.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.4.mlp_hyper_connection.hc_norm.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_down.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_up.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.attn_hyper_connection.block_inject_weight.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.attn_hyper_connection.hc_norm.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.attn_hyper_connection.input_mix_weight_down.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.attn_hyper_connection.input_mix_weight_up.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.linear_attn.A_log": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.linear_attn.conv1d.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.linear_attn.dt_bias": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.linear_attn.in_proj_a.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.linear_attn.in_proj_b.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.linear_attn.in_proj_qkv.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.linear_attn.in_proj_z.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.linear_attn.norm.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.linear_attn.out_proj.weight": "model-00104-of-00131.safetensors",
    "model.language_model.layers.40.mlp.experts.down_proj": "model-00106-of-00131.safetensors",
    "model.language_model.layers.40.mlp.experts.gate_up_proj": "model-00105-of-00131.safetensors",
    "model.language_model.layers.40.mlp.gate.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.40.mlp.shared_expert.down_proj.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.40.mlp.shared_expert.gate_proj.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.40.mlp.shared_expert.up_proj.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.40.mlp.shared_expert_gate.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.40.mlp_hyper_connection.block_inject_weight.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.40.mlp_hyper_connection.hc_norm.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.40.mlp_hyper_connection.input_mix_weight_down.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.40.mlp_hyper_connection.input_mix_weight_up.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.attn_hyper_connection.block_inject_weight.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.attn_hyper_connection.hc_norm.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.attn_hyper_connection.input_mix_weight_down.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.attn_hyper_connection.input_mix_weight_up.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.linear_attn.A_log": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.linear_attn.conv1d.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.linear_attn.dt_bias": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.linear_attn.in_proj_a.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.linear_attn.in_proj_b.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.linear_attn.in_proj_qkv.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.linear_attn.in_proj_z.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.linear_attn.norm.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.linear_attn.out_proj.weight": "model-00106-of-00131.safetensors",
    "model.language_model.layers.41.mlp.experts.down_proj": "model-00108-of-00131.safetensors",
    "model.language_model.layers.41.mlp.experts.gate_up_proj": "model-00107-of-00131.safetensors",
    "model.language_model.layers.41.mlp.gate.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.41.mlp.shared_expert.down_proj.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.41.mlp.shared_expert.gate_proj.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.41.mlp.shared_expert.up_proj.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.41.mlp.shared_expert_gate.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.41.mlp_hyper_connection.block_inject_weight.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.41.mlp_hyper_connection.hc_norm.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.41.mlp_hyper_connection.input_mix_weight_down.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.41.mlp_hyper_connection.input_mix_weight_up.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.attn_hyper_connection.block_inject_weight.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.attn_hyper_connection.hc_norm.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.attn_hyper_connection.input_mix_weight_down.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.attn_hyper_connection.input_mix_weight_up.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.linear_attn.A_log": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.linear_attn.conv1d.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.linear_attn.dt_bias": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.linear_attn.in_proj_a.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.linear_attn.in_proj_b.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.linear_attn.in_proj_qkv.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.linear_attn.in_proj_z.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.linear_attn.norm.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.linear_attn.out_proj.weight": "model-00108-of-00131.safetensors",
    "model.language_model.layers.42.mlp.experts.down_proj": "model-00110-of-00131.safetensors",
    "model.language_model.layers.42.mlp.experts.gate_up_proj": "model-00109-of-00131.safetensors",
    "model.language_model.layers.42.mlp.gate.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.42.mlp.shared_expert.down_proj.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.42.mlp.shared_expert.gate_proj.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.42.mlp.shared_expert.up_proj.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.42.mlp.shared_expert_gate.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.42.mlp_hyper_connection.block_inject_weight.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.42.mlp_hyper_connection.hc_norm.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.42.mlp_hyper_connection.input_mix_weight_down.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.42.mlp_hyper_connection.input_mix_weight_up.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.43.attn_hyper_connection.block_inject_weight.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.43.attn_hyper_connection.hc_norm.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.43.attn_hyper_connection.input_mix_weight_down.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.43.attn_hyper_connection.input_mix_weight_up.weight": "model-00110-of-00131.safetensors",
    "model.language_model.layers.43.mlp.experts.down_proj": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.mlp.experts.gate_up_proj": "model-00111-of-00131.safetensors",
    "model.language_model.layers.43.mlp.gate.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.mlp.shared_expert.down_proj.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.mlp.shared_expert.gate_proj.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.mlp.shared_expert.up_proj.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.mlp.shared_expert_gate.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.mlp_hyper_connection.block_inject_weight.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.mlp_hyper_connection.hc_norm.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.mlp_hyper_connection.input_mix_weight_down.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.mlp_hyper_connection.input_mix_weight_up.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.self_attn.indexer.index_qk_proj.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.self_attn.indexer.k_layernorm.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.self_attn.indexer.q_layernorm.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.self_attn.k_norm.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.self_attn.k_proj.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.self_attn.o_proj.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.self_attn.q_norm.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.self_attn.q_proj.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.43.self_attn.v_proj.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.attn_hyper_connection.block_inject_weight.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.attn_hyper_connection.hc_norm.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.attn_hyper_connection.input_mix_weight_down.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.attn_hyper_connection.input_mix_weight_up.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.linear_attn.A_log": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.linear_attn.conv1d.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.linear_attn.dt_bias": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.linear_attn.in_proj_a.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.linear_attn.in_proj_b.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.linear_attn.in_proj_qkv.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.linear_attn.in_proj_z.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.linear_attn.norm.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.linear_attn.out_proj.weight": "model-00112-of-00131.safetensors",
    "model.language_model.layers.44.mlp.experts.down_proj": "model-00114-of-00131.safetensors",
    "model.language_model.layers.44.mlp.experts.gate_up_proj": "model-00113-of-00131.safetensors",
    "model.language_model.layers.44.mlp.gate.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.44.mlp.shared_expert.down_proj.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.44.mlp.shared_expert.gate_proj.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.44.mlp.shared_expert.up_proj.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.44.mlp.shared_expert_gate.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.44.mlp_hyper_connection.block_inject_weight.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.44.mlp_hyper_connection.hc_norm.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.44.mlp_hyper_connection.input_mix_weight_down.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.44.mlp_hyper_connection.input_mix_weight_up.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.attn_hyper_connection.block_inject_weight.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.attn_hyper_connection.hc_norm.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.attn_hyper_connection.input_mix_weight_down.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.attn_hyper_connection.input_mix_weight_up.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.linear_attn.A_log": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.linear_attn.conv1d.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.linear_attn.dt_bias": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.linear_attn.in_proj_a.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.linear_attn.in_proj_b.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.linear_attn.in_proj_qkv.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.linear_attn.in_proj_z.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.linear_attn.norm.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.linear_attn.out_proj.weight": "model-00114-of-00131.safetensors",
    "model.language_model.layers.45.mlp.experts.down_proj": "model-00116-of-00131.safetensors",
    "model.language_model.layers.45.mlp.experts.gate_up_proj": "model-00115-of-00131.safetensors",
    "model.language_model.layers.45.mlp.gate.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.45.mlp.shared_expert.down_proj.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.45.mlp.shared_expert.gate_proj.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.45.mlp.shared_expert.up_proj.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.45.mlp.shared_expert_gate.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.45.mlp_hyper_connection.block_inject_weight.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.45.mlp_hyper_connection.hc_norm.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.45.mlp_hyper_connection.input_mix_weight_down.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.45.mlp_hyper_connection.input_mix_weight_up.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.attn_hyper_connection.block_inject_weight.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.attn_hyper_connection.hc_norm.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.attn_hyper_connection.input_mix_weight_down.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.attn_hyper_connection.input_mix_weight_up.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.linear_attn.A_log": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.linear_attn.conv1d.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.linear_attn.dt_bias": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.linear_attn.in_proj_a.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.linear_attn.in_proj_b.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.linear_attn.in_proj_qkv.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.linear_attn.in_proj_z.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.linear_attn.norm.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.linear_attn.out_proj.weight": "model-00116-of-00131.safetensors",
    "model.language_model.layers.46.mlp.experts.down_proj": "model-00118-of-00131.safetensors",
    "model.language_model.layers.46.mlp.experts.gate_up_proj": "model-00117-of-00131.safetensors",
    "model.language_model.layers.46.mlp.gate.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.46.mlp.shared_expert.down_proj.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.46.mlp.shared_expert.gate_proj.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.46.mlp.shared_expert.up_proj.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.46.mlp.shared_expert_gate.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.46.mlp_hyper_connection.block_inject_weight.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.46.mlp_hyper_connection.hc_norm.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.46.mlp_hyper_connection.input_mix_weight_down.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.46.mlp_hyper_connection.input_mix_weight_up.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.47.attn_hyper_connection.block_inject_weight.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.47.attn_hyper_connection.hc_norm.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.47.attn_hyper_connection.input_mix_weight_down.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.47.attn_hyper_connection.input_mix_weight_up.weight": "model-00118-of-00131.safetensors",
    "model.language_model.layers.47.mlp.experts.down_proj": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.mlp.experts.gate_up_proj": "model-00119-of-00131.safetensors",
    "model.language_model.layers.47.mlp.gate.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.mlp.shared_expert.down_proj.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.mlp.shared_expert.gate_proj.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.mlp.shared_expert.up_proj.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.mlp.shared_expert_gate.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.mlp_hyper_connection.block_inject_weight.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.mlp_hyper_connection.hc_norm.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.mlp_hyper_connection.input_mix_weight_down.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.mlp_hyper_connection.input_mix_weight_up.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.self_attn.indexer.index_qk_proj.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.self_attn.indexer.k_layernorm.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.self_attn.indexer.q_layernorm.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.self_attn.k_norm.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.self_attn.k_proj.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.self_attn.o_proj.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.self_attn.q_norm.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.self_attn.q_proj.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.47.self_attn.v_proj.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.attn_hyper_connection.block_inject_weight.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.attn_hyper_connection.hc_norm.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.attn_hyper_connection.input_mix_weight_down.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.attn_hyper_connection.input_mix_weight_up.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.linear_attn.A_log": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.linear_attn.dt_bias": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.linear_attn.norm.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00120-of-00131.safetensors",
    "model.language_model.layers.5.mlp.experts.down_proj": "model-00122-of-00131.safetensors",
    "model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00121-of-00131.safetensors",
    "model.language_model.layers.5.mlp.gate.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.5.mlp.shared_expert.down_proj.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.5.mlp.shared_expert.up_proj.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.5.mlp.shared_expert_gate.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.5.mlp_hyper_connection.block_inject_weight.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.5.mlp_hyper_connection.hc_norm.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_down.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_up.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.attn_hyper_connection.block_inject_weight.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.attn_hyper_connection.hc_norm.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.attn_hyper_connection.input_mix_weight_down.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.attn_hyper_connection.input_mix_weight_up.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.linear_attn.A_log": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.linear_attn.dt_bias": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.linear_attn.norm.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00122-of-00131.safetensors",
    "model.language_model.layers.6.mlp.experts.down_proj": "model-00124-of-00131.safetensors",
    "model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00123-of-00131.safetensors",
    "model.language_model.layers.6.mlp.gate.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.6.mlp.shared_expert.down_proj.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.6.mlp.shared_expert.up_proj.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.6.mlp.shared_expert_gate.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.6.mlp_hyper_connection.block_inject_weight.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.6.mlp_hyper_connection.hc_norm.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_down.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_up.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.7.attn_hyper_connection.block_inject_weight.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.7.attn_hyper_connection.hc_norm.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.7.attn_hyper_connection.input_mix_weight_down.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.7.attn_hyper_connection.input_mix_weight_up.weight": "model-00124-of-00131.safetensors",
    "model.language_model.layers.7.mlp.experts.down_proj": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00125-of-00131.safetensors",
    "model.language_model.layers.7.mlp.gate.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.mlp.shared_expert.down_proj.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.mlp.shared_expert.up_proj.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.mlp.shared_expert_gate.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.mlp_hyper_connection.block_inject_weight.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.mlp_hyper_connection.hc_norm.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_down.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_up.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.self_attn.indexer.index_qk_proj.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.self_attn.indexer.k_layernorm.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.self_attn.indexer.q_layernorm.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.attn_hyper_connection.block_inject_weight.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.attn_hyper_connection.hc_norm.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.attn_hyper_connection.input_mix_weight_down.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.attn_hyper_connection.input_mix_weight_up.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.linear_attn.A_log": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.linear_attn.dt_bias": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.linear_attn.norm.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00126-of-00131.safetensors",
    "model.language_model.layers.8.mlp.experts.down_proj": "model-00128-of-00131.safetensors",
    "model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00127-of-00131.safetensors",
    "model.language_model.layers.8.mlp.gate.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.8.mlp.shared_expert.down_proj.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.8.mlp.shared_expert.up_proj.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.8.mlp.shared_expert_gate.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.8.mlp_hyper_connection.block_inject_weight.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.8.mlp_hyper_connection.hc_norm.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.8.mlp_hyper_connection.input_mix_weight_down.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.8.mlp_hyper_connection.input_mix_weight_up.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.attn_hyper_connection.block_inject_weight.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.attn_hyper_connection.hc_norm.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.attn_hyper_connection.input_mix_weight_down.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.attn_hyper_connection.input_mix_weight_up.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.linear_attn.A_log": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.linear_attn.dt_bias": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.linear_attn.norm.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00128-of-00131.safetensors",
    "model.language_model.layers.9.mlp.experts.down_proj": "model-00130-of-00131.safetensors",
    "model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00129-of-00131.safetensors",
    "model.language_model.layers.9.mlp.gate.weight": "model-00130-of-00131.safetensors",
    "model.language_model.layers.9.mlp.shared_expert.down_proj.weight": "model-00130-of-00131.safetensors",
    "model.language_model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00130-of-00131.safetensors",
    "model.language_model.layers.9.mlp.shared_expert.up_proj.weight": "model-00130-of-00131.safetensors",
    "model.language_model.layers.9.mlp.shared_expert_gate.weight": "model-00130-of-00131.safetensors",
    "model.language_model.layers.9.mlp_hyper_connection.block_inject_weight.weight": "model-00130-of-00131.safetensors",
    "model.language_model.layers.9.mlp_hyper_connection.hc_norm.weight": "model-00130-of-00131.safetensors",
    "model.language_model.layers.9.mlp_hyper_connection.input_mix_weight_down.weight": "model-00130-of-00131.safetensors",
    "model.language_model.layers.9.mlp_hyper_connection.input_mix_weight_up.weight": "model-00130-of-00131.safetensors",
    "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.0.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.0.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.0.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.0.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.1.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.1.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.1.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.1.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.10.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.10.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.10.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.10.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.11.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.11.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.11.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.11.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.12.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.12.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.12.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.12.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.13.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.13.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.13.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.13.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.14.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.14.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.14.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.14.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.15.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.15.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.15.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.15.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.16.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.16.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.16.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.16.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.17.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.17.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.17.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.17.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.18.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.18.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.18.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.18.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.19.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.19.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.19.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.19.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.2.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.2.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.2.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.2.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.20.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.20.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.20.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.20.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.21.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.21.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.21.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.21.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.22.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.22.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.22.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.22.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.23.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.23.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.23.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.23.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.24.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.24.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.24.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.24.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.25.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.25.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.25.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.25.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.26.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.26.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.26.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.26.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.3.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.3.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.3.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.3.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.4.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.4.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.4.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.4.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.5.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.5.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.5.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.5.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.6.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.6.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.6.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.6.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.7.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.7.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.7.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.7.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.8.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.8.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.8.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.8.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.9.norm1.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.9.norm1.weight": "model-00001-of-00131.safetensors",
    "model.visual.blocks.9.norm2.bias": "model-00001-of-00131.safetensors",
    "model.visual.blocks.9.norm2.weight": "model-00001-of-00131.safetensors",
    "model.visual.merger.linear_fc1.bias": "model-00001-of-00131.safetensors",
    "model.visual.merger.linear_fc1.weight": "model-00001-of-00131.safetensors",
    "model.visual.merger.linear_fc2.bias": "model-00001-of-00131.safetensors",
    "model.visual.merger.linear_fc2.weight": "model-00001-of-00131.safetensors",
    "model.visual.merger.norm.bias": "model-00001-of-00131.safetensors",
    "model.visual.merger.norm.weight": "model-00001-of-00131.safetensors",
    "model.visual.patch_embed.proj.bias": "model-00001-of-00131.safetensors",
    "model.visual.patch_embed.proj.weight": "model-00001-of-00131.safetensors",
    "model.visual.pos_embed.weight": "model-00001-of-00131.safetensors",
    "mtp.fc_embedding.weight": "model-00120-of-00131.safetensors",
    "mtp.fc_hidden.weight": "model-00124-of-00131.safetensors",
    "mtp.hyper_connection_mixer.hc_norm.weight": "model-00037-of-00131.safetensors",
    "mtp.hyper_connection_mixer.input_mix_weight_down.weight": "model-00041-of-00131.safetensors",
    "mtp.hyper_connection_mixer.input_mix_weight_up.weight": "model-00043-of-00131.safetensors",
    "mtp.layers.0.attn_hyper_connection.block_inject_weight.weight": "model-00047-of-00131.safetensors",
    "mtp.layers.0.attn_hyper_connection.hc_norm.weight": "model-00049-of-00131.safetensors",
    "mtp.layers.0.attn_hyper_connection.input_mix_weight_down.weight": "model-00053-of-00131.safetensors",
    "mtp.layers.0.attn_hyper_connection.input_mix_weight_up.weight": "model-00057-of-00131.safetensors",
    "mtp.layers.0.mlp.experts.down_proj": "model-00062-of-00131.safetensors",
    "mtp.layers.0.mlp.experts.gate_up_proj": "model-00060-of-00131.safetensors",
    "mtp.layers.0.mlp.gate.weight": "model-00066-of-00131.safetensors",
    "mtp.layers.0.mlp.shared_expert.down_proj.weight": "model-00076-of-00131.safetensors",
    "mtp.layers.0.mlp.shared_expert.gate_proj.weight": "model-00072-of-00131.safetensors",
    "mtp.layers.0.mlp.shared_expert.up_proj.weight": "model-00072-of-00131.safetensors",
    "mtp.layers.0.mlp.shared_expert_gate.weight": "model-00070-of-00131.safetensors",
    "mtp.layers.0.mlp_hyper_connection.block_inject_weight.weight": "model-00078-of-00131.safetensors",
    "mtp.layers.0.mlp_hyper_connection.hc_norm.weight": "model-00082-of-00131.safetensors",
    "mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.weight": "model-00086-of-00131.safetensors",
    "mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.weight": "model-00088-of-00131.safetensors",
    "mtp.layers.0.self_attn.indexer.index_qk_proj.weight": "model-00090-of-00131.safetensors",
    "mtp.layers.0.self_attn.indexer.k_layernorm.weight": "model-00094-of-00131.safetensors",
    "mtp.layers.0.self_attn.indexer.q_layernorm.weight": "model-00100-of-00131.safetensors",
    "mtp.layers.0.self_attn.k_norm.weight": "model-00102-of-00131.safetensors",
    "mtp.layers.0.self_attn.k_proj.weight": "model-00108-of-00131.safetensors",
    "mtp.layers.0.self_attn.o_proj.weight": "model-00106-of-00131.safetensors",
    "mtp.layers.0.self_attn.q_norm.weight": "model-00112-of-00131.safetensors",
    "mtp.layers.0.self_attn.q_proj.weight": "model-00108-of-00131.safetensors",
    "mtp.layers.0.self_attn.v_proj.weight": "model-00108-of-00131.safetensors",
    "mtp.pre_fc_norm_embedding.weight": "model-00114-of-00131.safetensors",
    "mtp.pre_fc_norm_hidden.weight": "model-00118-of-00131.safetensors"
  }
}
