diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json" new file mode 100644--- /dev/null +++ "b/model.safetensors.index.json" @@ -0,0 +1,3174 @@ +{ + "metadata": { + "total_size": 54331273208 + }, + "weight_map": { + "language_model.model.hyper_connection_mixer.hc_norm.weight": "model-00001.safetensors", + "language_model.model.hyper_connection_mixer.input_mix_weight_down.weight": "model-00001.safetensors", + "language_model.model.hyper_connection_mixer.input_mix_weight_down.scales": "model-00001.safetensors", + "language_model.model.hyper_connection_mixer.input_mix_weight_down.biases": "model-00001.safetensors", + "language_model.model.hyper_connection_mixer.input_mix_weight_up.weight": "model-00001.safetensors", + "language_model.model.hyper_connection_mixer.input_mix_weight_up.scales": "model-00001.safetensors", + "language_model.model.hyper_connection_mixer.input_mix_weight_up.biases": "model-00001.safetensors", + "language_model.model.layers.0.attn_hyper_connection.block_inject_weight.weight": "model-00001.safetensors", + "language_model.model.layers.0.attn_hyper_connection.hc_norm.weight": "model-00001.safetensors", + "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_down.weight": "model-00001.safetensors", + "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_down.scales": "model-00001.safetensors", + "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_down.biases": "model-00001.safetensors", + "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_up.weight": "model-00001.safetensors", + "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_up.scales": "model-00001.safetensors", + "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_up.biases": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.A_log": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.conv1d.weight": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.dt_bias": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.in_proj_a.weight": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.in_proj_a.scales": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.in_proj_a.biases": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.in_proj_b.weight": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.in_proj_b.scales": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.in_proj_b.biases": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.in_proj_qkv.scales": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.in_proj_qkv.biases": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.in_proj_z.weight": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.in_proj_z.scales": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.in_proj_z.biases": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.norm.weight": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.out_proj.weight": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.out_proj.scales": "model-00001.safetensors", + "language_model.model.layers.0.linear_attn.out_proj.biases": "model-00001.safetensors", + "language_model.model.layers.0.mlp.switch_mlp.gate_proj.weight": "model-00002.safetensors", + "language_model.model.layers.0.mlp.switch_mlp.gate_proj.scales": "model-00002.safetensors", + "language_model.model.layers.0.mlp.switch_mlp.gate_proj.biases": "model-00002.safetensors", + "language_model.model.layers.0.mlp.switch_mlp.up_proj.weight": "model-00002.safetensors", + "language_model.model.layers.0.mlp.switch_mlp.up_proj.scales": "model-00002.safetensors", + "language_model.model.layers.0.mlp.switch_mlp.up_proj.biases": "model-00002.safetensors", + "language_model.model.layers.0.mlp.switch_mlp.down_proj.weight": "model-00003.safetensors", + "language_model.model.layers.0.mlp.switch_mlp.down_proj.scales": "model-00003.safetensors", + "language_model.model.layers.0.mlp.switch_mlp.down_proj.biases": "model-00003.safetensors", + "language_model.model.layers.0.mlp.gate.weight": "model-00003.safetensors", + "language_model.model.layers.0.mlp.gate.scales": "model-00003.safetensors", + "language_model.model.layers.0.mlp.gate.biases": "model-00003.safetensors", + "language_model.model.layers.0.mlp.shared_expert.down_proj.weight": "model-00003.safetensors", + "language_model.model.layers.0.mlp.shared_expert.down_proj.scales": "model-00003.safetensors", + "language_model.model.layers.0.mlp.shared_expert.down_proj.biases": "model-00003.safetensors", + "language_model.model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00003.safetensors", + "language_model.model.layers.0.mlp.shared_expert.gate_proj.scales": "model-00003.safetensors", + "language_model.model.layers.0.mlp.shared_expert.gate_proj.biases": "model-00003.safetensors", + "language_model.model.layers.0.mlp.shared_expert.up_proj.weight": "model-00003.safetensors", + "language_model.model.layers.0.mlp.shared_expert.up_proj.scales": "model-00003.safetensors", + "language_model.model.layers.0.mlp.shared_expert.up_proj.biases": "model-00003.safetensors", + "language_model.model.layers.0.mlp.shared_expert_gate.weight": "model-00003.safetensors", + "language_model.model.layers.0.mlp_hyper_connection.block_inject_weight.weight": "model-00003.safetensors", + "language_model.model.layers.0.mlp_hyper_connection.hc_norm.weight": "model-00003.safetensors", + "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_down.weight": "model-00003.safetensors", + "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_down.scales": "model-00003.safetensors", + "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_down.biases": "model-00003.safetensors", + "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_up.weight": "model-00003.safetensors", + "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_up.scales": "model-00003.safetensors", + "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_up.biases": "model-00003.safetensors", + "language_model.model.layers.1.attn_hyper_connection.block_inject_weight.weight": "model-00003.safetensors", + "language_model.model.layers.1.attn_hyper_connection.hc_norm.weight": "model-00003.safetensors", + "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_down.weight": "model-00003.safetensors", + "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_down.scales": "model-00003.safetensors", + "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_down.biases": "model-00003.safetensors", + "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_up.weight": "model-00003.safetensors", + "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_up.scales": "model-00003.safetensors", + "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_up.biases": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.A_log": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.conv1d.weight": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.dt_bias": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.in_proj_a.weight": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.in_proj_a.scales": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.in_proj_a.biases": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.in_proj_b.weight": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.in_proj_b.scales": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.in_proj_b.biases": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.in_proj_qkv.weight": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.in_proj_qkv.scales": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.in_proj_qkv.biases": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.in_proj_z.weight": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.in_proj_z.scales": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.in_proj_z.biases": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.norm.weight": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.out_proj.weight": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.out_proj.scales": "model-00003.safetensors", + "language_model.model.layers.1.linear_attn.out_proj.biases": "model-00003.safetensors", + "language_model.model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00004.safetensors", + "language_model.model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00004.safetensors", + "language_model.model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00004.safetensors", + "language_model.model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00004.safetensors", + "language_model.model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00004.safetensors", + "language_model.model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00004.safetensors", + "language_model.model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00005.safetensors", + "language_model.model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00005.safetensors", + "language_model.model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00005.safetensors", + "language_model.model.layers.1.mlp.gate.weight": "model-00005.safetensors", + "language_model.model.layers.1.mlp.gate.scales": "model-00005.safetensors", + "language_model.model.layers.1.mlp.gate.biases": "model-00005.safetensors", + "language_model.model.layers.1.mlp.shared_expert.down_proj.weight": "model-00005.safetensors", + "language_model.model.layers.1.mlp.shared_expert.down_proj.scales": "model-00005.safetensors", + "language_model.model.layers.1.mlp.shared_expert.down_proj.biases": "model-00005.safetensors", + "language_model.model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00005.safetensors", + "language_model.model.layers.1.mlp.shared_expert.gate_proj.scales": "model-00005.safetensors", + "language_model.model.layers.1.mlp.shared_expert.gate_proj.biases": "model-00005.safetensors", + "language_model.model.layers.1.mlp.shared_expert.up_proj.weight": "model-00005.safetensors", + "language_model.model.layers.1.mlp.shared_expert.up_proj.scales": "model-00005.safetensors", + "language_model.model.layers.1.mlp.shared_expert.up_proj.biases": "model-00005.safetensors", + "language_model.model.layers.1.mlp.shared_expert_gate.weight": "model-00005.safetensors", + "language_model.model.layers.1.mlp_hyper_connection.block_inject_weight.weight": "model-00005.safetensors", + "language_model.model.layers.1.mlp_hyper_connection.hc_norm.weight": "model-00005.safetensors", + "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_down.weight": "model-00005.safetensors", + "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_down.scales": "model-00005.safetensors", + "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_down.biases": "model-00005.safetensors", + "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_up.weight": "model-00005.safetensors", + "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_up.scales": "model-00005.safetensors", + "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_up.biases": "model-00005.safetensors", + "language_model.model.layers.1.ple.key_proj.weight": "model-00005.safetensors", + "language_model.model.layers.1.ple.key_proj.scales": "model-00005.safetensors", + "language_model.model.layers.1.ple.key_proj.biases": "model-00005.safetensors", + "language_model.model.layers.1.ple.norm_conv.weight": "model-00005.safetensors", + "language_model.model.layers.1.ple.norm_key.weight": "model-00005.safetensors", + "language_model.model.layers.1.ple.norm_query.weight": "model-00005.safetensors", + "language_model.model.layers.1.ple.ple_embedding.layer_multipliers": "model-00005.safetensors", + "language_model.model.layers.1.ple.conv1d.weight": "model-00006.safetensors", + "language_model.model.layers.1.ple.ple_embedding.ngram_heads_offsets": "model-00006.safetensors", + "language_model.model.layers.1.ple.ple_embedding.ngram_heads_vocab_sizes": "model-00006.safetensors", + "language_model.model.layers.1.ple.value_proj.weight": "model-00006.safetensors", + "language_model.model.layers.1.ple.value_proj.scales": "model-00006.safetensors", + "language_model.model.layers.1.ple.value_proj.biases": "model-00006.safetensors", + "language_model.model.layers.10.attn_hyper_connection.block_inject_weight.weight": "model-00006.safetensors", + "language_model.model.layers.10.attn_hyper_connection.hc_norm.weight": "model-00006.safetensors", + "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_down.weight": "model-00006.safetensors", + "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_down.scales": "model-00006.safetensors", + "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_down.biases": "model-00006.safetensors", + "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_up.weight": "model-00006.safetensors", + "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_up.scales": "model-00006.safetensors", + "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_up.biases": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.A_log": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.conv1d.weight": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.dt_bias": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.in_proj_a.weight": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.in_proj_a.scales": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.in_proj_a.biases": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.in_proj_b.weight": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.in_proj_b.scales": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.in_proj_b.biases": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.in_proj_qkv.weight": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.in_proj_qkv.scales": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.in_proj_qkv.biases": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.in_proj_z.weight": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.in_proj_z.scales": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.in_proj_z.biases": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.norm.weight": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.out_proj.weight": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.out_proj.scales": "model-00006.safetensors", + "language_model.model.layers.10.linear_attn.out_proj.biases": "model-00006.safetensors", + "language_model.mtp.hyper_connection_mixer.hc_norm.weight": "model-00006.safetensors", + "language_model.model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00007.safetensors", + "language_model.model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00007.safetensors", + "language_model.model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00007.safetensors", + "language_model.model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00007.safetensors", + "language_model.model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00007.safetensors", + "language_model.model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00007.safetensors", + "language_model.model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00008.safetensors", + "language_model.model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00008.safetensors", + "language_model.model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00008.safetensors", + "language_model.model.layers.10.mlp.gate.weight": "model-00008.safetensors", + "language_model.model.layers.10.mlp.gate.scales": "model-00008.safetensors", + "language_model.model.layers.10.mlp.gate.biases": "model-00008.safetensors", + "language_model.model.layers.10.mlp.shared_expert.down_proj.weight": "model-00008.safetensors", + "language_model.model.layers.10.mlp.shared_expert.down_proj.scales": "model-00008.safetensors", + "language_model.model.layers.10.mlp.shared_expert.down_proj.biases": "model-00008.safetensors", + "language_model.model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00008.safetensors", + "language_model.model.layers.10.mlp.shared_expert.gate_proj.scales": "model-00008.safetensors", + "language_model.model.layers.10.mlp.shared_expert.gate_proj.biases": "model-00008.safetensors", + "language_model.model.layers.10.mlp.shared_expert.up_proj.weight": "model-00008.safetensors", + "language_model.model.layers.10.mlp.shared_expert.up_proj.scales": "model-00008.safetensors", + "language_model.model.layers.10.mlp.shared_expert.up_proj.biases": "model-00008.safetensors", + "language_model.model.layers.10.mlp.shared_expert_gate.weight": "model-00008.safetensors", + "language_model.model.layers.10.mlp_hyper_connection.block_inject_weight.weight": "model-00008.safetensors", + "language_model.model.layers.10.mlp_hyper_connection.hc_norm.weight": "model-00008.safetensors", + "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_down.weight": "model-00008.safetensors", + "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_down.scales": "model-00008.safetensors", + "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_down.biases": "model-00008.safetensors", + "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_up.weight": "model-00008.safetensors", + "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_up.scales": "model-00008.safetensors", + "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_up.biases": "model-00008.safetensors", + "language_model.model.layers.11.attn_hyper_connection.block_inject_weight.weight": "model-00008.safetensors", + "language_model.model.layers.11.attn_hyper_connection.hc_norm.weight": "model-00008.safetensors", + "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_down.weight": "model-00008.safetensors", + "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_down.scales": "model-00008.safetensors", + "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_down.biases": "model-00008.safetensors", + "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_up.weight": "model-00008.safetensors", + "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_up.scales": "model-00008.safetensors", + "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_up.biases": "model-00008.safetensors", + "language_model.model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00009.safetensors", + "language_model.model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00009.safetensors", + "language_model.model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00009.safetensors", + "language_model.model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00009.safetensors", + "language_model.model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00009.safetensors", + "language_model.model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00009.safetensors", + "language_model.model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00010.safetensors", + "language_model.model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00010.safetensors", + "language_model.model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00010.safetensors", + "language_model.model.layers.11.mlp.gate.weight": "model-00010.safetensors", + "language_model.model.layers.11.mlp.gate.scales": "model-00010.safetensors", + "language_model.model.layers.11.mlp.gate.biases": "model-00010.safetensors", + "language_model.model.layers.11.mlp.shared_expert.down_proj.weight": "model-00010.safetensors", + "language_model.model.layers.11.mlp.shared_expert.down_proj.scales": "model-00010.safetensors", + "language_model.model.layers.11.mlp.shared_expert.down_proj.biases": "model-00010.safetensors", + "language_model.model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00010.safetensors", + "language_model.model.layers.11.mlp.shared_expert.gate_proj.scales": "model-00010.safetensors", + "language_model.model.layers.11.mlp.shared_expert.gate_proj.biases": "model-00010.safetensors", + "language_model.model.layers.11.mlp.shared_expert.up_proj.weight": "model-00010.safetensors", + "language_model.model.layers.11.mlp.shared_expert.up_proj.scales": "model-00010.safetensors", + "language_model.model.layers.11.mlp.shared_expert.up_proj.biases": "model-00010.safetensors", + "language_model.model.layers.11.mlp.shared_expert_gate.weight": "model-00010.safetensors", + "language_model.model.layers.11.mlp_hyper_connection.block_inject_weight.weight": "model-00010.safetensors", + "language_model.model.layers.11.mlp_hyper_connection.hc_norm.weight": "model-00010.safetensors", + "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010.safetensors", + "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_down.scales": "model-00010.safetensors", + "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_down.biases": "model-00010.safetensors", + "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010.safetensors", + "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_up.scales": "model-00010.safetensors", + "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_up.biases": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.indexer.index_qk_proj.weight": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.indexer.index_qk_proj.scales": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.indexer.index_qk_proj.biases": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.indexer.k_layernorm.weight": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.indexer.q_layernorm.weight": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.k_norm.weight": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.k_proj.weight": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.k_proj.scales": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.k_proj.biases": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.o_proj.weight": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.o_proj.scales": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.o_proj.biases": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.q_norm.weight": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.q_proj.weight": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.q_proj.scales": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.q_proj.biases": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.v_proj.weight": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.v_proj.scales": "model-00010.safetensors", + "language_model.model.layers.11.self_attn.v_proj.biases": "model-00010.safetensors", + "language_model.model.layers.12.attn_hyper_connection.block_inject_weight.weight": "model-00010.safetensors", + "language_model.model.layers.12.attn_hyper_connection.hc_norm.weight": "model-00010.safetensors", + "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_down.weight": "model-00010.safetensors", + "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_down.scales": "model-00010.safetensors", + "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_down.biases": "model-00010.safetensors", + "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_up.weight": "model-00010.safetensors", + "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_up.scales": "model-00010.safetensors", + "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_up.biases": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.A_log": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.conv1d.weight": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.dt_bias": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.in_proj_a.weight": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.in_proj_a.scales": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.in_proj_a.biases": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.in_proj_b.weight": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.in_proj_b.scales": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.in_proj_b.biases": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.in_proj_qkv.weight": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.in_proj_qkv.scales": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.in_proj_qkv.biases": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.in_proj_z.weight": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.in_proj_z.scales": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.in_proj_z.biases": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.norm.weight": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.out_proj.weight": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.out_proj.scales": "model-00010.safetensors", + "language_model.model.layers.12.linear_attn.out_proj.biases": "model-00010.safetensors", + "language_model.mtp.hyper_connection_mixer.input_mix_weight_down.weight": "model-00010.safetensors", + "language_model.mtp.hyper_connection_mixer.input_mix_weight_down.scales": "model-00010.safetensors", + "language_model.mtp.hyper_connection_mixer.input_mix_weight_down.biases": "model-00010.safetensors", + "language_model.model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00011.safetensors", + "language_model.model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00011.safetensors", + "language_model.model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00011.safetensors", + "language_model.model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00011.safetensors", + "language_model.model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00011.safetensors", + "language_model.model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00011.safetensors", + "language_model.model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00012.safetensors", + "language_model.model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00012.safetensors", + "language_model.model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00012.safetensors", + "language_model.model.layers.12.mlp.gate.weight": "model-00012.safetensors", + "language_model.model.layers.12.mlp.gate.scales": "model-00012.safetensors", + "language_model.model.layers.12.mlp.gate.biases": "model-00012.safetensors", + "language_model.model.layers.12.mlp.shared_expert.down_proj.weight": "model-00012.safetensors", + "language_model.model.layers.12.mlp.shared_expert.down_proj.scales": "model-00012.safetensors", + "language_model.model.layers.12.mlp.shared_expert.down_proj.biases": "model-00012.safetensors", + "language_model.model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00012.safetensors", + "language_model.model.layers.12.mlp.shared_expert.gate_proj.scales": "model-00012.safetensors", + "language_model.model.layers.12.mlp.shared_expert.gate_proj.biases": "model-00012.safetensors", + "language_model.model.layers.12.mlp.shared_expert.up_proj.weight": "model-00012.safetensors", + "language_model.model.layers.12.mlp.shared_expert.up_proj.scales": "model-00012.safetensors", + "language_model.model.layers.12.mlp.shared_expert.up_proj.biases": "model-00012.safetensors", + "language_model.model.layers.12.mlp.shared_expert_gate.weight": "model-00012.safetensors", + "language_model.model.layers.12.mlp_hyper_connection.block_inject_weight.weight": "model-00012.safetensors", + "language_model.model.layers.12.mlp_hyper_connection.hc_norm.weight": "model-00012.safetensors", + "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_down.weight": "model-00012.safetensors", + "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_down.scales": "model-00012.safetensors", + "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_down.biases": "model-00012.safetensors", + "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_up.weight": "model-00012.safetensors", + "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_up.scales": "model-00012.safetensors", + "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_up.biases": "model-00012.safetensors", + "language_model.model.layers.13.attn_hyper_connection.block_inject_weight.weight": "model-00012.safetensors", + "language_model.model.layers.13.attn_hyper_connection.hc_norm.weight": "model-00012.safetensors", + "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_down.weight": "model-00012.safetensors", + "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_down.scales": "model-00012.safetensors", + "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_down.biases": "model-00012.safetensors", + "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_up.weight": "model-00012.safetensors", + "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_up.scales": "model-00012.safetensors", + "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_up.biases": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.A_log": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.conv1d.weight": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.dt_bias": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.in_proj_a.weight": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.in_proj_a.scales": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.in_proj_a.biases": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.in_proj_b.weight": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.in_proj_b.scales": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.in_proj_b.biases": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.in_proj_qkv.weight": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.in_proj_qkv.scales": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.in_proj_qkv.biases": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.in_proj_z.weight": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.in_proj_z.scales": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.in_proj_z.biases": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.norm.weight": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.out_proj.weight": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.out_proj.scales": "model-00012.safetensors", + "language_model.model.layers.13.linear_attn.out_proj.biases": "model-00012.safetensors", + "language_model.mtp.hyper_connection_mixer.input_mix_weight_up.weight": "model-00012.safetensors", + "language_model.mtp.hyper_connection_mixer.input_mix_weight_up.scales": "model-00012.safetensors", + "language_model.mtp.hyper_connection_mixer.input_mix_weight_up.biases": "model-00012.safetensors", + "language_model.model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00013.safetensors", + "language_model.model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00013.safetensors", + "language_model.model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00013.safetensors", + "language_model.model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00013.safetensors", + "language_model.model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00013.safetensors", + "language_model.model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00013.safetensors", + "language_model.model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00014.safetensors", + "language_model.model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00014.safetensors", + "language_model.model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00014.safetensors", + "language_model.model.layers.13.mlp.gate.weight": "model-00014.safetensors", + "language_model.model.layers.13.mlp.gate.scales": "model-00014.safetensors", + "language_model.model.layers.13.mlp.gate.biases": "model-00014.safetensors", + "language_model.model.layers.13.mlp.shared_expert.down_proj.weight": "model-00014.safetensors", + "language_model.model.layers.13.mlp.shared_expert.down_proj.scales": "model-00014.safetensors", + "language_model.model.layers.13.mlp.shared_expert.down_proj.biases": "model-00014.safetensors", + "language_model.model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00014.safetensors", + "language_model.model.layers.13.mlp.shared_expert.gate_proj.scales": "model-00014.safetensors", + "language_model.model.layers.13.mlp.shared_expert.gate_proj.biases": "model-00014.safetensors", + "language_model.model.layers.13.mlp.shared_expert.up_proj.weight": "model-00014.safetensors", + "language_model.model.layers.13.mlp.shared_expert.up_proj.scales": "model-00014.safetensors", + "language_model.model.layers.13.mlp.shared_expert.up_proj.biases": "model-00014.safetensors", + "language_model.model.layers.13.mlp.shared_expert_gate.weight": "model-00014.safetensors", + "language_model.model.layers.13.mlp_hyper_connection.block_inject_weight.weight": "model-00014.safetensors", + "language_model.model.layers.13.mlp_hyper_connection.hc_norm.weight": "model-00014.safetensors", + "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_down.weight": "model-00014.safetensors", + "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_down.scales": "model-00014.safetensors", + "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_down.biases": "model-00014.safetensors", + "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_up.weight": "model-00014.safetensors", + "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_up.scales": "model-00014.safetensors", + "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_up.biases": "model-00014.safetensors", + "language_model.model.layers.14.attn_hyper_connection.block_inject_weight.weight": "model-00014.safetensors", + "language_model.model.layers.14.attn_hyper_connection.hc_norm.weight": "model-00014.safetensors", + "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_down.weight": "model-00014.safetensors", + "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_down.scales": "model-00014.safetensors", + "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_down.biases": "model-00014.safetensors", + "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_up.weight": "model-00014.safetensors", + "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_up.scales": "model-00014.safetensors", + "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_up.biases": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.A_log": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.conv1d.weight": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.dt_bias": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.in_proj_a.weight": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.in_proj_a.scales": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.in_proj_a.biases": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.in_proj_b.weight": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.in_proj_b.scales": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.in_proj_b.biases": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.in_proj_qkv.weight": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.in_proj_qkv.scales": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.in_proj_qkv.biases": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.in_proj_z.weight": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.in_proj_z.scales": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.in_proj_z.biases": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.norm.weight": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.out_proj.weight": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.out_proj.scales": "model-00014.safetensors", + "language_model.model.layers.14.linear_attn.out_proj.biases": "model-00014.safetensors", + "language_model.model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00015.safetensors", + "language_model.model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00015.safetensors", + "language_model.model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00015.safetensors", + "language_model.model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00015.safetensors", + "language_model.model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00015.safetensors", + "language_model.model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00015.safetensors", + "language_model.model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00016.safetensors", + "language_model.model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00016.safetensors", + "language_model.model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00016.safetensors", + "language_model.model.layers.14.mlp.gate.weight": "model-00016.safetensors", + "language_model.model.layers.14.mlp.gate.scales": "model-00016.safetensors", + "language_model.model.layers.14.mlp.gate.biases": "model-00016.safetensors", + "language_model.model.layers.14.mlp.shared_expert.down_proj.weight": "model-00016.safetensors", + "language_model.model.layers.14.mlp.shared_expert.down_proj.scales": "model-00016.safetensors", + "language_model.model.layers.14.mlp.shared_expert.down_proj.biases": "model-00016.safetensors", + "language_model.model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00016.safetensors", + "language_model.model.layers.14.mlp.shared_expert.gate_proj.scales": "model-00016.safetensors", + "language_model.model.layers.14.mlp.shared_expert.gate_proj.biases": "model-00016.safetensors", + "language_model.model.layers.14.mlp.shared_expert.up_proj.weight": "model-00016.safetensors", + "language_model.model.layers.14.mlp.shared_expert.up_proj.scales": "model-00016.safetensors", + "language_model.model.layers.14.mlp.shared_expert.up_proj.biases": "model-00016.safetensors", + "language_model.model.layers.14.mlp.shared_expert_gate.weight": "model-00016.safetensors", + "language_model.model.layers.14.mlp_hyper_connection.block_inject_weight.weight": "model-00016.safetensors", + "language_model.model.layers.14.mlp_hyper_connection.hc_norm.weight": "model-00016.safetensors", + "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_down.weight": "model-00016.safetensors", + "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_down.scales": "model-00016.safetensors", + "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_down.biases": "model-00016.safetensors", + "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_up.weight": "model-00016.safetensors", + "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_up.scales": "model-00016.safetensors", + "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_up.biases": "model-00016.safetensors", + "language_model.model.layers.15.attn_hyper_connection.block_inject_weight.weight": "model-00016.safetensors", + "language_model.model.layers.15.attn_hyper_connection.hc_norm.weight": "model-00016.safetensors", + "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_down.weight": "model-00016.safetensors", + "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_down.scales": "model-00016.safetensors", + "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_down.biases": "model-00016.safetensors", + "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_up.weight": "model-00016.safetensors", + "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_up.scales": "model-00016.safetensors", + "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_up.biases": "model-00016.safetensors", + "language_model.mtp.layers.0.attn_hyper_connection.block_inject_weight.weight": "model-00016.safetensors", + "language_model.model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00017.safetensors", + "language_model.model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00017.safetensors", + "language_model.model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00017.safetensors", + "language_model.model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00017.safetensors", + "language_model.model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00017.safetensors", + "language_model.model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00017.safetensors", + "language_model.model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00018.safetensors", + "language_model.model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00018.safetensors", + "language_model.model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00018.safetensors", + "language_model.model.layers.15.mlp.gate.weight": "model-00018.safetensors", + "language_model.model.layers.15.mlp.gate.scales": "model-00018.safetensors", + "language_model.model.layers.15.mlp.gate.biases": "model-00018.safetensors", + "language_model.model.layers.15.mlp.shared_expert.down_proj.weight": "model-00018.safetensors", + "language_model.model.layers.15.mlp.shared_expert.down_proj.scales": "model-00018.safetensors", + "language_model.model.layers.15.mlp.shared_expert.down_proj.biases": "model-00018.safetensors", + "language_model.model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00018.safetensors", + "language_model.model.layers.15.mlp.shared_expert.gate_proj.scales": "model-00018.safetensors", + "language_model.model.layers.15.mlp.shared_expert.gate_proj.biases": "model-00018.safetensors", + "language_model.model.layers.15.mlp.shared_expert.up_proj.weight": "model-00018.safetensors", + "language_model.model.layers.15.mlp.shared_expert.up_proj.scales": "model-00018.safetensors", + "language_model.model.layers.15.mlp.shared_expert.up_proj.biases": "model-00018.safetensors", + "language_model.model.layers.15.mlp.shared_expert_gate.weight": "model-00018.safetensors", + "language_model.model.layers.15.mlp_hyper_connection.block_inject_weight.weight": "model-00018.safetensors", + "language_model.model.layers.15.mlp_hyper_connection.hc_norm.weight": "model-00018.safetensors", + "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_down.weight": "model-00018.safetensors", + "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_down.scales": "model-00018.safetensors", + "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_down.biases": "model-00018.safetensors", + "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_up.weight": "model-00018.safetensors", + "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_up.scales": "model-00018.safetensors", + "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_up.biases": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.indexer.index_qk_proj.weight": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.indexer.index_qk_proj.scales": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.indexer.index_qk_proj.biases": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.indexer.k_layernorm.weight": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.indexer.q_layernorm.weight": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.k_norm.weight": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.k_proj.weight": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.k_proj.scales": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.k_proj.biases": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.o_proj.weight": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.o_proj.scales": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.o_proj.biases": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.q_norm.weight": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.q_proj.weight": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.q_proj.scales": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.q_proj.biases": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.v_proj.weight": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.v_proj.scales": "model-00018.safetensors", + "language_model.model.layers.15.self_attn.v_proj.biases": "model-00018.safetensors", + "language_model.model.layers.16.attn_hyper_connection.block_inject_weight.weight": "model-00018.safetensors", + "language_model.model.layers.16.attn_hyper_connection.hc_norm.weight": "model-00018.safetensors", + "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_down.weight": "model-00018.safetensors", + "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_down.scales": "model-00018.safetensors", + "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_down.biases": "model-00018.safetensors", + "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_up.weight": "model-00018.safetensors", + "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_up.scales": "model-00018.safetensors", + "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_up.biases": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.A_log": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.conv1d.weight": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.dt_bias": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.in_proj_a.weight": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.in_proj_a.scales": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.in_proj_a.biases": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.in_proj_b.weight": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.in_proj_b.scales": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.in_proj_b.biases": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.in_proj_qkv.weight": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.in_proj_qkv.scales": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.in_proj_qkv.biases": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.in_proj_z.weight": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.in_proj_z.scales": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.in_proj_z.biases": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.norm.weight": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.out_proj.weight": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.out_proj.scales": "model-00018.safetensors", + "language_model.model.layers.16.linear_attn.out_proj.biases": "model-00018.safetensors", + "language_model.mtp.layers.0.attn_hyper_connection.hc_norm.weight": "model-00018.safetensors", + "language_model.model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00019.safetensors", + "language_model.model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00019.safetensors", + "language_model.model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00019.safetensors", + "language_model.model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00019.safetensors", + "language_model.model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00019.safetensors", + "language_model.model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00019.safetensors", + "language_model.model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00020.safetensors", + "language_model.model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00020.safetensors", + "language_model.model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00020.safetensors", + "language_model.model.layers.16.mlp.gate.weight": "model-00020.safetensors", + "language_model.model.layers.16.mlp.gate.scales": "model-00020.safetensors", + "language_model.model.layers.16.mlp.gate.biases": "model-00020.safetensors", + "language_model.model.layers.16.mlp.shared_expert.down_proj.weight": "model-00020.safetensors", + "language_model.model.layers.16.mlp.shared_expert.down_proj.scales": "model-00020.safetensors", + "language_model.model.layers.16.mlp.shared_expert.down_proj.biases": "model-00020.safetensors", + "language_model.model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00020.safetensors", + "language_model.model.layers.16.mlp.shared_expert.gate_proj.scales": "model-00020.safetensors", + "language_model.model.layers.16.mlp.shared_expert.gate_proj.biases": "model-00020.safetensors", + "language_model.model.layers.16.mlp.shared_expert.up_proj.weight": "model-00020.safetensors", + "language_model.model.layers.16.mlp.shared_expert.up_proj.scales": "model-00020.safetensors", + "language_model.model.layers.16.mlp.shared_expert.up_proj.biases": "model-00020.safetensors", + "language_model.model.layers.16.mlp.shared_expert_gate.weight": "model-00020.safetensors", + "language_model.model.layers.16.mlp_hyper_connection.block_inject_weight.weight": "model-00020.safetensors", + "language_model.model.layers.16.mlp_hyper_connection.hc_norm.weight": "model-00020.safetensors", + "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_down.weight": "model-00020.safetensors", + "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_down.scales": "model-00020.safetensors", + "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_down.biases": "model-00020.safetensors", + "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_up.weight": "model-00020.safetensors", + "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_up.scales": "model-00020.safetensors", + "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_up.biases": "model-00020.safetensors", + "language_model.model.layers.17.attn_hyper_connection.block_inject_weight.weight": "model-00020.safetensors", + "language_model.model.layers.17.attn_hyper_connection.hc_norm.weight": "model-00020.safetensors", + "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_down.weight": "model-00020.safetensors", + "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_down.scales": "model-00020.safetensors", + "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_down.biases": "model-00020.safetensors", + "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_up.weight": "model-00020.safetensors", + "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_up.scales": "model-00020.safetensors", + "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_up.biases": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.A_log": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.conv1d.weight": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.dt_bias": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.in_proj_a.weight": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.in_proj_a.scales": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.in_proj_a.biases": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.in_proj_b.weight": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.in_proj_b.scales": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.in_proj_b.biases": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.in_proj_qkv.weight": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.in_proj_qkv.scales": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.in_proj_qkv.biases": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.in_proj_z.weight": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.in_proj_z.scales": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.in_proj_z.biases": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.norm.weight": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.out_proj.weight": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.out_proj.scales": "model-00020.safetensors", + "language_model.model.layers.17.linear_attn.out_proj.biases": "model-00020.safetensors", + "language_model.model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00021.safetensors", + "language_model.model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00021.safetensors", + "language_model.model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00021.safetensors", + "language_model.model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00021.safetensors", + "language_model.model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00021.safetensors", + "language_model.model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00021.safetensors", + "language_model.model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00022.safetensors", + "language_model.model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00022.safetensors", + "language_model.model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00022.safetensors", + "language_model.model.layers.17.mlp.gate.weight": "model-00022.safetensors", + "language_model.model.layers.17.mlp.gate.scales": "model-00022.safetensors", + "language_model.model.layers.17.mlp.gate.biases": "model-00022.safetensors", + "language_model.model.layers.17.mlp.shared_expert.down_proj.weight": "model-00022.safetensors", + "language_model.model.layers.17.mlp.shared_expert.down_proj.scales": "model-00022.safetensors", + "language_model.model.layers.17.mlp.shared_expert.down_proj.biases": "model-00022.safetensors", + "language_model.model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00022.safetensors", + "language_model.model.layers.17.mlp.shared_expert.gate_proj.scales": "model-00022.safetensors", + "language_model.model.layers.17.mlp.shared_expert.gate_proj.biases": "model-00022.safetensors", + "language_model.model.layers.17.mlp.shared_expert.up_proj.weight": "model-00022.safetensors", + "language_model.model.layers.17.mlp.shared_expert.up_proj.scales": "model-00022.safetensors", + "language_model.model.layers.17.mlp.shared_expert.up_proj.biases": "model-00022.safetensors", + "language_model.model.layers.17.mlp.shared_expert_gate.weight": "model-00022.safetensors", + "language_model.model.layers.17.mlp_hyper_connection.block_inject_weight.weight": "model-00022.safetensors", + "language_model.model.layers.17.mlp_hyper_connection.hc_norm.weight": "model-00022.safetensors", + "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_down.weight": "model-00022.safetensors", + "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_down.scales": "model-00022.safetensors", + "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_down.biases": "model-00022.safetensors", + "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_up.weight": "model-00022.safetensors", + "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_up.scales": "model-00022.safetensors", + "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_up.biases": "model-00022.safetensors", + "language_model.model.layers.18.attn_hyper_connection.block_inject_weight.weight": "model-00022.safetensors", + "language_model.model.layers.18.attn_hyper_connection.hc_norm.weight": "model-00022.safetensors", + "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_down.weight": "model-00022.safetensors", + "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_down.scales": "model-00022.safetensors", + "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_down.biases": "model-00022.safetensors", + "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_up.weight": "model-00022.safetensors", + "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_up.scales": "model-00022.safetensors", + "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_up.biases": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.A_log": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.conv1d.weight": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.dt_bias": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.in_proj_a.weight": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.in_proj_a.scales": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.in_proj_a.biases": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.in_proj_b.weight": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.in_proj_b.scales": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.in_proj_b.biases": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.in_proj_qkv.weight": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.in_proj_qkv.scales": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.in_proj_qkv.biases": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.in_proj_z.weight": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.in_proj_z.scales": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.in_proj_z.biases": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.norm.weight": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.out_proj.weight": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.out_proj.scales": "model-00022.safetensors", + "language_model.model.layers.18.linear_attn.out_proj.biases": "model-00022.safetensors", + "language_model.mtp.layers.0.attn_hyper_connection.input_mix_weight_down.weight": "model-00022.safetensors", + "language_model.mtp.layers.0.attn_hyper_connection.input_mix_weight_down.scales": "model-00022.safetensors", + "language_model.mtp.layers.0.attn_hyper_connection.input_mix_weight_down.biases": "model-00022.safetensors", + "language_model.model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00023.safetensors", + "language_model.model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00023.safetensors", + "language_model.model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00023.safetensors", + "language_model.model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00023.safetensors", + "language_model.model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00023.safetensors", + "language_model.model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00023.safetensors", + "language_model.model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00024.safetensors", + "language_model.model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00024.safetensors", + "language_model.model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00024.safetensors", + "language_model.model.layers.18.mlp.gate.weight": "model-00024.safetensors", + "language_model.model.layers.18.mlp.gate.scales": "model-00024.safetensors", + "language_model.model.layers.18.mlp.gate.biases": "model-00024.safetensors", + "language_model.model.layers.18.mlp.shared_expert.down_proj.weight": "model-00024.safetensors", + "language_model.model.layers.18.mlp.shared_expert.down_proj.scales": "model-00024.safetensors", + "language_model.model.layers.18.mlp.shared_expert.down_proj.biases": "model-00024.safetensors", + "language_model.model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00024.safetensors", + "language_model.model.layers.18.mlp.shared_expert.gate_proj.scales": "model-00024.safetensors", + "language_model.model.layers.18.mlp.shared_expert.gate_proj.biases": "model-00024.safetensors", + "language_model.model.layers.18.mlp.shared_expert.up_proj.weight": "model-00024.safetensors", + "language_model.model.layers.18.mlp.shared_expert.up_proj.scales": "model-00024.safetensors", + "language_model.model.layers.18.mlp.shared_expert.up_proj.biases": "model-00024.safetensors", + "language_model.model.layers.18.mlp.shared_expert_gate.weight": "model-00024.safetensors", + "language_model.model.layers.18.mlp_hyper_connection.block_inject_weight.weight": "model-00024.safetensors", + "language_model.model.layers.18.mlp_hyper_connection.hc_norm.weight": "model-00024.safetensors", + "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_down.weight": "model-00024.safetensors", + "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_down.scales": "model-00024.safetensors", + "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_down.biases": "model-00024.safetensors", + "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_up.weight": "model-00024.safetensors", + "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_up.scales": "model-00024.safetensors", + "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_up.biases": "model-00024.safetensors", + "language_model.model.layers.19.attn_hyper_connection.block_inject_weight.weight": "model-00024.safetensors", + "language_model.model.layers.19.attn_hyper_connection.hc_norm.weight": "model-00024.safetensors", + "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_down.weight": "model-00024.safetensors", + "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_down.scales": "model-00024.safetensors", + "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_down.biases": "model-00024.safetensors", + "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_up.weight": "model-00024.safetensors", + "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_up.scales": "model-00024.safetensors", + "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_up.biases": "model-00024.safetensors", + "language_model.model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00025.safetensors", + "language_model.model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00025.safetensors", + "language_model.model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00025.safetensors", + "language_model.model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00025.safetensors", + "language_model.model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00025.safetensors", + "language_model.model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00025.safetensors", + "language_model.model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00026.safetensors", + "language_model.model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00026.safetensors", + "language_model.model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00026.safetensors", + "language_model.model.layers.19.mlp.gate.weight": "model-00026.safetensors", + "language_model.model.layers.19.mlp.gate.scales": "model-00026.safetensors", + "language_model.model.layers.19.mlp.gate.biases": "model-00026.safetensors", + "language_model.model.layers.19.mlp.shared_expert.down_proj.weight": "model-00026.safetensors", + "language_model.model.layers.19.mlp.shared_expert.down_proj.scales": "model-00026.safetensors", + "language_model.model.layers.19.mlp.shared_expert.down_proj.biases": "model-00026.safetensors", + "language_model.model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00026.safetensors", + "language_model.model.layers.19.mlp.shared_expert.gate_proj.scales": "model-00026.safetensors", + "language_model.model.layers.19.mlp.shared_expert.gate_proj.biases": "model-00026.safetensors", + "language_model.model.layers.19.mlp.shared_expert.up_proj.weight": "model-00026.safetensors", + "language_model.model.layers.19.mlp.shared_expert.up_proj.scales": "model-00026.safetensors", + "language_model.model.layers.19.mlp.shared_expert.up_proj.biases": "model-00026.safetensors", + "language_model.model.layers.19.mlp.shared_expert_gate.weight": "model-00026.safetensors", + "language_model.model.layers.19.mlp_hyper_connection.block_inject_weight.weight": "model-00026.safetensors", + "language_model.model.layers.19.mlp_hyper_connection.hc_norm.weight": "model-00026.safetensors", + "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_down.weight": "model-00026.safetensors", + "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_down.scales": "model-00026.safetensors", + "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_down.biases": "model-00026.safetensors", + "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_up.weight": "model-00026.safetensors", + "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_up.scales": "model-00026.safetensors", + "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_up.biases": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.indexer.index_qk_proj.weight": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.indexer.index_qk_proj.scales": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.indexer.index_qk_proj.biases": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.indexer.k_layernorm.weight": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.indexer.q_layernorm.weight": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.k_norm.weight": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.k_proj.weight": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.k_proj.scales": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.k_proj.biases": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.o_proj.weight": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.o_proj.scales": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.o_proj.biases": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.q_norm.weight": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.q_proj.weight": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.q_proj.scales": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.q_proj.biases": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.v_proj.weight": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.v_proj.scales": "model-00026.safetensors", + "language_model.model.layers.19.self_attn.v_proj.biases": "model-00026.safetensors", + "language_model.model.layers.2.attn_hyper_connection.block_inject_weight.weight": "model-00026.safetensors", + "language_model.model.layers.2.attn_hyper_connection.hc_norm.weight": "model-00026.safetensors", + "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_down.weight": "model-00026.safetensors", + "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_down.scales": "model-00026.safetensors", + "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_down.biases": "model-00026.safetensors", + "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_up.weight": "model-00026.safetensors", + "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_up.scales": "model-00026.safetensors", + "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_up.biases": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.A_log": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.conv1d.weight": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.dt_bias": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.in_proj_a.weight": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.in_proj_a.scales": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.in_proj_a.biases": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.in_proj_b.weight": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.in_proj_b.scales": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.in_proj_b.biases": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.in_proj_qkv.weight": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.in_proj_qkv.scales": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.in_proj_qkv.biases": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.in_proj_z.weight": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.in_proj_z.scales": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.in_proj_z.biases": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.norm.weight": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.out_proj.weight": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.out_proj.scales": "model-00026.safetensors", + "language_model.model.layers.2.linear_attn.out_proj.biases": "model-00026.safetensors", + "language_model.mtp.layers.0.attn_hyper_connection.input_mix_weight_up.weight": "model-00026.safetensors", + "language_model.mtp.layers.0.attn_hyper_connection.input_mix_weight_up.scales": "model-00026.safetensors", + "language_model.mtp.layers.0.attn_hyper_connection.input_mix_weight_up.biases": "model-00026.safetensors", + "language_model.model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00027.safetensors", + "language_model.model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00027.safetensors", + "language_model.model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00027.safetensors", + "language_model.model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00027.safetensors", + "language_model.model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00027.safetensors", + "language_model.model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00027.safetensors", + "language_model.model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00028.safetensors", + "language_model.model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00028.safetensors", + "language_model.model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00028.safetensors", + "language_model.model.layers.2.mlp.gate.weight": "model-00028.safetensors", + "language_model.model.layers.2.mlp.gate.scales": "model-00028.safetensors", + "language_model.model.layers.2.mlp.gate.biases": "model-00028.safetensors", + "language_model.model.layers.2.mlp.shared_expert.down_proj.weight": "model-00028.safetensors", + "language_model.model.layers.2.mlp.shared_expert.down_proj.scales": "model-00028.safetensors", + "language_model.model.layers.2.mlp.shared_expert.down_proj.biases": "model-00028.safetensors", + "language_model.model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00028.safetensors", + "language_model.model.layers.2.mlp.shared_expert.gate_proj.scales": "model-00028.safetensors", + "language_model.model.layers.2.mlp.shared_expert.gate_proj.biases": "model-00028.safetensors", + "language_model.model.layers.2.mlp.shared_expert.up_proj.weight": "model-00028.safetensors", + "language_model.model.layers.2.mlp.shared_expert.up_proj.scales": "model-00028.safetensors", + "language_model.model.layers.2.mlp.shared_expert.up_proj.biases": "model-00028.safetensors", + "language_model.model.layers.2.mlp.shared_expert_gate.weight": "model-00028.safetensors", + "language_model.model.layers.2.mlp_hyper_connection.block_inject_weight.weight": "model-00028.safetensors", + "language_model.model.layers.2.mlp_hyper_connection.hc_norm.weight": "model-00028.safetensors", + "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_down.weight": "model-00028.safetensors", + "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_down.scales": "model-00028.safetensors", + "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_down.biases": "model-00028.safetensors", + "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_up.weight": "model-00028.safetensors", + "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_up.scales": "model-00028.safetensors", + "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_up.biases": "model-00028.safetensors", + "language_model.model.layers.20.attn_hyper_connection.block_inject_weight.weight": "model-00028.safetensors", + "language_model.model.layers.20.attn_hyper_connection.hc_norm.weight": "model-00028.safetensors", + "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_down.weight": "model-00028.safetensors", + "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_down.scales": "model-00028.safetensors", + "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_down.biases": "model-00028.safetensors", + "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_up.weight": "model-00028.safetensors", + "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_up.scales": "model-00028.safetensors", + "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_up.biases": "model-00028.safetensors", + "language_model.model.layers.20.linear_attn.A_log": "model-00028.safetensors", + "language_model.model.layers.20.linear_attn.conv1d.weight": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.dt_bias": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.in_proj_a.weight": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.in_proj_a.scales": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.in_proj_a.biases": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.in_proj_b.weight": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.in_proj_b.scales": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.in_proj_b.biases": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.in_proj_qkv.weight": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.in_proj_qkv.scales": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.in_proj_qkv.biases": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.in_proj_z.weight": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.in_proj_z.scales": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.in_proj_z.biases": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.norm.weight": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.out_proj.weight": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.out_proj.scales": "model-00029.safetensors", + "language_model.model.layers.20.linear_attn.out_proj.biases": "model-00029.safetensors", + "language_model.mtp.layers.0.mlp.switch_mlp.gate_proj.weight": "model-00029.safetensors", + "language_model.mtp.layers.0.mlp.switch_mlp.gate_proj.scales": "model-00029.safetensors", + "language_model.mtp.layers.0.mlp.switch_mlp.gate_proj.biases": "model-00029.safetensors", + "language_model.mtp.layers.0.mlp.switch_mlp.up_proj.weight": "model-00029.safetensors", + "language_model.mtp.layers.0.mlp.switch_mlp.up_proj.scales": "model-00029.safetensors", + "language_model.mtp.layers.0.mlp.switch_mlp.up_proj.biases": "model-00029.safetensors", + "language_model.model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00030.safetensors", + "language_model.model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00030.safetensors", + "language_model.model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00030.safetensors", + "language_model.model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00030.safetensors", + "language_model.model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00030.safetensors", + "language_model.model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00030.safetensors", + "language_model.model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00031.safetensors", + "language_model.model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00031.safetensors", + "language_model.model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00031.safetensors", + "language_model.model.layers.20.mlp.gate.weight": "model-00031.safetensors", + "language_model.model.layers.20.mlp.gate.scales": "model-00031.safetensors", + "language_model.model.layers.20.mlp.gate.biases": "model-00031.safetensors", + "language_model.model.layers.20.mlp.shared_expert.down_proj.weight": "model-00031.safetensors", + "language_model.model.layers.20.mlp.shared_expert.down_proj.scales": "model-00031.safetensors", + "language_model.model.layers.20.mlp.shared_expert.down_proj.biases": "model-00031.safetensors", + "language_model.model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00031.safetensors", + "language_model.model.layers.20.mlp.shared_expert.gate_proj.scales": "model-00031.safetensors", + "language_model.model.layers.20.mlp.shared_expert.gate_proj.biases": "model-00031.safetensors", + "language_model.model.layers.20.mlp.shared_expert.up_proj.weight": "model-00031.safetensors", + "language_model.model.layers.20.mlp.shared_expert.up_proj.scales": "model-00031.safetensors", + "language_model.model.layers.20.mlp.shared_expert.up_proj.biases": "model-00031.safetensors", + "language_model.model.layers.20.mlp.shared_expert_gate.weight": "model-00031.safetensors", + "language_model.model.layers.20.mlp_hyper_connection.block_inject_weight.weight": "model-00031.safetensors", + "language_model.model.layers.20.mlp_hyper_connection.hc_norm.weight": "model-00031.safetensors", + "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_down.weight": "model-00031.safetensors", + "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_down.scales": "model-00031.safetensors", + "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_down.biases": "model-00031.safetensors", + "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_up.weight": "model-00031.safetensors", + "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_up.scales": "model-00031.safetensors", + "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_up.biases": "model-00031.safetensors", + "language_model.model.layers.21.attn_hyper_connection.block_inject_weight.weight": "model-00031.safetensors", + "language_model.model.layers.21.attn_hyper_connection.hc_norm.weight": "model-00031.safetensors", + "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_down.weight": "model-00031.safetensors", + "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_down.scales": "model-00031.safetensors", + "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_down.biases": "model-00031.safetensors", + "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_up.weight": "model-00031.safetensors", + "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_up.scales": "model-00031.safetensors", + "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_up.biases": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.A_log": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.conv1d.weight": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.dt_bias": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.in_proj_a.weight": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.in_proj_a.scales": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.in_proj_a.biases": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.in_proj_b.weight": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.in_proj_b.scales": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.in_proj_b.biases": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.in_proj_qkv.weight": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.in_proj_qkv.scales": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.in_proj_qkv.biases": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.in_proj_z.weight": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.in_proj_z.scales": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.in_proj_z.biases": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.norm.weight": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.out_proj.weight": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.out_proj.scales": "model-00031.safetensors", + "language_model.model.layers.21.linear_attn.out_proj.biases": "model-00031.safetensors", + "language_model.mtp.layers.0.mlp.switch_mlp.down_proj.weight": "model-00031.safetensors", + "language_model.mtp.layers.0.mlp.switch_mlp.down_proj.scales": "model-00031.safetensors", + "language_model.mtp.layers.0.mlp.switch_mlp.down_proj.biases": "model-00031.safetensors", + "language_model.model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00032.safetensors", + "language_model.model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00032.safetensors", + "language_model.model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00032.safetensors", + "language_model.model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00032.safetensors", + "language_model.model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00032.safetensors", + "language_model.model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00032.safetensors", + "language_model.model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00033.safetensors", + "language_model.model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00033.safetensors", + "language_model.model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00033.safetensors", + "language_model.model.layers.21.mlp.gate.weight": "model-00033.safetensors", + "language_model.model.layers.21.mlp.gate.scales": "model-00033.safetensors", + "language_model.model.layers.21.mlp.gate.biases": "model-00033.safetensors", + "language_model.model.layers.21.mlp.shared_expert.down_proj.weight": "model-00033.safetensors", + "language_model.model.layers.21.mlp.shared_expert.down_proj.scales": "model-00033.safetensors", + "language_model.model.layers.21.mlp.shared_expert.down_proj.biases": "model-00033.safetensors", + "language_model.model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00033.safetensors", + "language_model.model.layers.21.mlp.shared_expert.gate_proj.scales": "model-00033.safetensors", + "language_model.model.layers.21.mlp.shared_expert.gate_proj.biases": "model-00033.safetensors", + "language_model.model.layers.21.mlp.shared_expert.up_proj.weight": "model-00033.safetensors", + "language_model.model.layers.21.mlp.shared_expert.up_proj.scales": "model-00033.safetensors", + "language_model.model.layers.21.mlp.shared_expert.up_proj.biases": "model-00033.safetensors", + "language_model.model.layers.21.mlp.shared_expert_gate.weight": "model-00033.safetensors", + "language_model.model.layers.21.mlp_hyper_connection.block_inject_weight.weight": "model-00033.safetensors", + "language_model.model.layers.21.mlp_hyper_connection.hc_norm.weight": "model-00033.safetensors", + "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_down.weight": "model-00033.safetensors", + "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_down.scales": "model-00033.safetensors", + "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_down.biases": "model-00033.safetensors", + "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_up.weight": "model-00033.safetensors", + "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_up.scales": "model-00033.safetensors", + "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_up.biases": "model-00033.safetensors", + "language_model.model.layers.22.attn_hyper_connection.block_inject_weight.weight": "model-00033.safetensors", + "language_model.model.layers.22.attn_hyper_connection.hc_norm.weight": "model-00033.safetensors", + "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_down.weight": "model-00033.safetensors", + "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_down.scales": "model-00033.safetensors", + "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_down.biases": "model-00033.safetensors", + "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_up.weight": "model-00033.safetensors", + "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_up.scales": "model-00033.safetensors", + "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_up.biases": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.A_log": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.conv1d.weight": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.dt_bias": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.in_proj_a.weight": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.in_proj_a.scales": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.in_proj_a.biases": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.in_proj_b.weight": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.in_proj_b.scales": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.in_proj_b.biases": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.in_proj_qkv.weight": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.in_proj_qkv.scales": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.in_proj_qkv.biases": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.in_proj_z.weight": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.in_proj_z.scales": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.in_proj_z.biases": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.norm.weight": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.out_proj.weight": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.out_proj.scales": "model-00033.safetensors", + "language_model.model.layers.22.linear_attn.out_proj.biases": "model-00033.safetensors", + "language_model.model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00034.safetensors", + "language_model.model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00034.safetensors", + "language_model.model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00034.safetensors", + "language_model.model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00034.safetensors", + "language_model.model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00034.safetensors", + "language_model.model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00034.safetensors", + "language_model.model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00035.safetensors", + "language_model.model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00035.safetensors", + "language_model.model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00035.safetensors", + "language_model.model.layers.22.mlp.gate.weight": "model-00035.safetensors", + "language_model.model.layers.22.mlp.gate.scales": "model-00035.safetensors", + "language_model.model.layers.22.mlp.gate.biases": "model-00035.safetensors", + "language_model.model.layers.22.mlp.shared_expert.down_proj.weight": "model-00035.safetensors", + "language_model.model.layers.22.mlp.shared_expert.down_proj.scales": "model-00035.safetensors", + "language_model.model.layers.22.mlp.shared_expert.down_proj.biases": "model-00035.safetensors", + "language_model.model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00035.safetensors", + "language_model.model.layers.22.mlp.shared_expert.gate_proj.scales": "model-00035.safetensors", + "language_model.model.layers.22.mlp.shared_expert.gate_proj.biases": "model-00035.safetensors", + "language_model.model.layers.22.mlp.shared_expert.up_proj.weight": "model-00035.safetensors", + "language_model.model.layers.22.mlp.shared_expert.up_proj.scales": "model-00035.safetensors", + "language_model.model.layers.22.mlp.shared_expert.up_proj.biases": "model-00035.safetensors", + "language_model.model.layers.22.mlp.shared_expert_gate.weight": "model-00035.safetensors", + "language_model.model.layers.22.mlp_hyper_connection.block_inject_weight.weight": "model-00035.safetensors", + "language_model.model.layers.22.mlp_hyper_connection.hc_norm.weight": "model-00035.safetensors", + "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_down.weight": "model-00035.safetensors", + "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_down.scales": "model-00035.safetensors", + "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_down.biases": "model-00035.safetensors", + "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_up.weight": "model-00035.safetensors", + "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_up.scales": "model-00035.safetensors", + "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_up.biases": "model-00035.safetensors", + "language_model.model.layers.23.attn_hyper_connection.block_inject_weight.weight": "model-00035.safetensors", + "language_model.model.layers.23.attn_hyper_connection.hc_norm.weight": "model-00035.safetensors", + "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_down.weight": "model-00035.safetensors", + "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_down.scales": "model-00035.safetensors", + "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_down.biases": "model-00035.safetensors", + "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_up.weight": "model-00035.safetensors", + "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_up.scales": "model-00035.safetensors", + "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_up.biases": "model-00035.safetensors", + "language_model.mtp.layers.0.mlp.gate.weight": "model-00035.safetensors", + "language_model.mtp.layers.0.mlp.gate.scales": "model-00035.safetensors", + "language_model.mtp.layers.0.mlp.gate.biases": "model-00035.safetensors", + "language_model.model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00036.safetensors", + "language_model.model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00036.safetensors", + "language_model.model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00036.safetensors", + "language_model.model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00036.safetensors", + "language_model.model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00036.safetensors", + "language_model.model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00036.safetensors", + "language_model.model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00037.safetensors", + "language_model.model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00037.safetensors", + "language_model.model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00037.safetensors", + "language_model.model.layers.23.mlp.gate.weight": "model-00037.safetensors", + "language_model.model.layers.23.mlp.gate.scales": "model-00037.safetensors", + "language_model.model.layers.23.mlp.gate.biases": "model-00037.safetensors", + "language_model.model.layers.23.mlp.shared_expert.down_proj.weight": "model-00037.safetensors", + "language_model.model.layers.23.mlp.shared_expert.down_proj.scales": "model-00037.safetensors", + "language_model.model.layers.23.mlp.shared_expert.down_proj.biases": "model-00037.safetensors", + "language_model.model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00037.safetensors", + "language_model.model.layers.23.mlp.shared_expert.gate_proj.scales": "model-00037.safetensors", + "language_model.model.layers.23.mlp.shared_expert.gate_proj.biases": "model-00037.safetensors", + "language_model.model.layers.23.mlp.shared_expert.up_proj.weight": "model-00037.safetensors", + "language_model.model.layers.23.mlp.shared_expert.up_proj.scales": "model-00037.safetensors", + "language_model.model.layers.23.mlp.shared_expert.up_proj.biases": "model-00037.safetensors", + "language_model.model.layers.23.mlp.shared_expert_gate.weight": "model-00037.safetensors", + "language_model.model.layers.23.mlp_hyper_connection.block_inject_weight.weight": "model-00037.safetensors", + "language_model.model.layers.23.mlp_hyper_connection.hc_norm.weight": "model-00037.safetensors", + "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_down.weight": "model-00037.safetensors", + "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_down.scales": "model-00037.safetensors", + "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_down.biases": "model-00037.safetensors", + "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_up.weight": "model-00037.safetensors", + "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_up.scales": "model-00037.safetensors", + "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_up.biases": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.indexer.index_qk_proj.weight": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.indexer.index_qk_proj.scales": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.indexer.index_qk_proj.biases": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.indexer.k_layernorm.weight": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.indexer.q_layernorm.weight": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.k_norm.weight": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.k_proj.weight": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.k_proj.scales": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.k_proj.biases": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.o_proj.weight": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.o_proj.scales": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.o_proj.biases": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.q_norm.weight": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.q_proj.weight": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.q_proj.scales": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.q_proj.biases": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.v_proj.weight": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.v_proj.scales": "model-00037.safetensors", + "language_model.model.layers.23.self_attn.v_proj.biases": "model-00037.safetensors", + "language_model.model.layers.24.attn_hyper_connection.block_inject_weight.weight": "model-00037.safetensors", + "language_model.model.layers.24.attn_hyper_connection.hc_norm.weight": "model-00037.safetensors", + "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_down.weight": "model-00037.safetensors", + "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_down.scales": "model-00037.safetensors", + "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_down.biases": "model-00037.safetensors", + "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_up.weight": "model-00037.safetensors", + "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_up.scales": "model-00037.safetensors", + "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_up.biases": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.A_log": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.conv1d.weight": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.dt_bias": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.in_proj_a.weight": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.in_proj_a.scales": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.in_proj_a.biases": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.in_proj_b.weight": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.in_proj_b.scales": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.in_proj_b.biases": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.in_proj_qkv.weight": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.in_proj_qkv.scales": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.in_proj_qkv.biases": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.in_proj_z.weight": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.in_proj_z.scales": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.in_proj_z.biases": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.norm.weight": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.out_proj.weight": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.out_proj.scales": "model-00037.safetensors", + "language_model.model.layers.24.linear_attn.out_proj.biases": "model-00037.safetensors", + "language_model.model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00038.safetensors", + "language_model.model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00038.safetensors", + "language_model.model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00038.safetensors", + "language_model.model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00038.safetensors", + "language_model.model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00038.safetensors", + "language_model.model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00038.safetensors", + "language_model.model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00039.safetensors", + "language_model.model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00039.safetensors", + "language_model.model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00039.safetensors", + "language_model.model.layers.24.mlp.gate.weight": "model-00039.safetensors", + "language_model.model.layers.24.mlp.gate.scales": "model-00039.safetensors", + "language_model.model.layers.24.mlp.gate.biases": "model-00039.safetensors", + "language_model.model.layers.24.mlp.shared_expert.down_proj.weight": "model-00039.safetensors", + "language_model.model.layers.24.mlp.shared_expert.down_proj.scales": "model-00039.safetensors", + "language_model.model.layers.24.mlp.shared_expert.down_proj.biases": "model-00039.safetensors", + "language_model.model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00039.safetensors", + "language_model.model.layers.24.mlp.shared_expert.gate_proj.scales": "model-00039.safetensors", + "language_model.model.layers.24.mlp.shared_expert.gate_proj.biases": "model-00039.safetensors", + "language_model.model.layers.24.mlp.shared_expert.up_proj.weight": "model-00039.safetensors", + "language_model.model.layers.24.mlp.shared_expert.up_proj.scales": "model-00039.safetensors", + "language_model.model.layers.24.mlp.shared_expert.up_proj.biases": "model-00039.safetensors", + "language_model.model.layers.24.mlp.shared_expert_gate.weight": "model-00039.safetensors", + "language_model.model.layers.24.mlp_hyper_connection.block_inject_weight.weight": "model-00039.safetensors", + "language_model.model.layers.24.mlp_hyper_connection.hc_norm.weight": "model-00039.safetensors", + "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_down.weight": "model-00039.safetensors", + "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_down.scales": "model-00039.safetensors", + "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_down.biases": "model-00039.safetensors", + "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_up.weight": "model-00039.safetensors", + "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_up.scales": "model-00039.safetensors", + "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_up.biases": "model-00039.safetensors", + "language_model.model.layers.25.attn_hyper_connection.block_inject_weight.weight": "model-00039.safetensors", + "language_model.model.layers.25.attn_hyper_connection.hc_norm.weight": "model-00039.safetensors", + "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_down.weight": "model-00039.safetensors", + "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_down.scales": "model-00039.safetensors", + "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_down.biases": "model-00039.safetensors", + "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_up.weight": "model-00039.safetensors", + "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_up.scales": "model-00039.safetensors", + "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_up.biases": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.A_log": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.conv1d.weight": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.dt_bias": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.in_proj_a.weight": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.in_proj_a.scales": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.in_proj_a.biases": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.in_proj_b.weight": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.in_proj_b.scales": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.in_proj_b.biases": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.in_proj_qkv.weight": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.in_proj_qkv.scales": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.in_proj_qkv.biases": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.in_proj_z.weight": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.in_proj_z.scales": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.in_proj_z.biases": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.norm.weight": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.out_proj.weight": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.out_proj.scales": "model-00039.safetensors", + "language_model.model.layers.25.linear_attn.out_proj.biases": "model-00039.safetensors", + "language_model.mtp.layers.0.mlp.shared_expert_gate.weight": "model-00039.safetensors", + "language_model.model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00040.safetensors", + "language_model.model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00040.safetensors", + "language_model.model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00040.safetensors", + "language_model.model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00040.safetensors", + "language_model.model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00040.safetensors", + "language_model.model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00040.safetensors", + "language_model.model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00041.safetensors", + "language_model.model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00041.safetensors", + "language_model.model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00041.safetensors", + "language_model.model.layers.25.mlp.gate.weight": "model-00041.safetensors", + "language_model.model.layers.25.mlp.gate.scales": "model-00041.safetensors", + "language_model.model.layers.25.mlp.gate.biases": "model-00041.safetensors", + "language_model.model.layers.25.mlp.shared_expert.down_proj.weight": "model-00041.safetensors", + "language_model.model.layers.25.mlp.shared_expert.down_proj.scales": "model-00041.safetensors", + "language_model.model.layers.25.mlp.shared_expert.down_proj.biases": "model-00041.safetensors", + "language_model.model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00041.safetensors", + "language_model.model.layers.25.mlp.shared_expert.gate_proj.scales": "model-00041.safetensors", + "language_model.model.layers.25.mlp.shared_expert.gate_proj.biases": "model-00041.safetensors", + "language_model.model.layers.25.mlp.shared_expert.up_proj.weight": "model-00041.safetensors", + "language_model.model.layers.25.mlp.shared_expert.up_proj.scales": "model-00041.safetensors", + "language_model.model.layers.25.mlp.shared_expert.up_proj.biases": "model-00041.safetensors", + "language_model.model.layers.25.mlp.shared_expert_gate.weight": "model-00041.safetensors", + "language_model.model.layers.25.mlp_hyper_connection.block_inject_weight.weight": "model-00041.safetensors", + "language_model.model.layers.25.mlp_hyper_connection.hc_norm.weight": "model-00041.safetensors", + "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_down.weight": "model-00041.safetensors", + "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_down.scales": "model-00041.safetensors", + "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_down.biases": "model-00041.safetensors", + "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_up.weight": "model-00041.safetensors", + "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_up.scales": "model-00041.safetensors", + "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_up.biases": "model-00041.safetensors", + "language_model.model.layers.26.attn_hyper_connection.block_inject_weight.weight": "model-00041.safetensors", + "language_model.model.layers.26.attn_hyper_connection.hc_norm.weight": "model-00041.safetensors", + "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_down.weight": "model-00041.safetensors", + "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_down.scales": "model-00041.safetensors", + "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_down.biases": "model-00041.safetensors", + "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_up.weight": "model-00041.safetensors", + "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_up.scales": "model-00041.safetensors", + "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_up.biases": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.A_log": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.conv1d.weight": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.dt_bias": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.in_proj_a.weight": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.in_proj_a.scales": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.in_proj_a.biases": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.in_proj_b.weight": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.in_proj_b.scales": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.in_proj_b.biases": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.in_proj_qkv.weight": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.in_proj_qkv.scales": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.in_proj_qkv.biases": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.in_proj_z.weight": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.in_proj_z.scales": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.in_proj_z.biases": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.norm.weight": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.out_proj.weight": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.out_proj.scales": "model-00041.safetensors", + "language_model.model.layers.26.linear_attn.out_proj.biases": "model-00041.safetensors", + "language_model.mtp.layers.0.mlp.shared_expert.gate_proj.weight": "model-00041.safetensors", + "language_model.mtp.layers.0.mlp.shared_expert.gate_proj.scales": "model-00041.safetensors", + "language_model.mtp.layers.0.mlp.shared_expert.gate_proj.biases": "model-00041.safetensors", + "language_model.mtp.layers.0.mlp.shared_expert.up_proj.weight": "model-00041.safetensors", + "language_model.mtp.layers.0.mlp.shared_expert.up_proj.scales": "model-00041.safetensors", + "language_model.mtp.layers.0.mlp.shared_expert.up_proj.biases": "model-00041.safetensors", + "language_model.model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00042.safetensors", + "language_model.model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00042.safetensors", + "language_model.model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00042.safetensors", + "language_model.model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00042.safetensors", + "language_model.model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00042.safetensors", + "language_model.model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00042.safetensors", + "language_model.model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00043.safetensors", + "language_model.model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00043.safetensors", + "language_model.model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00043.safetensors", + "language_model.model.layers.26.mlp.gate.weight": "model-00043.safetensors", + "language_model.model.layers.26.mlp.gate.scales": "model-00043.safetensors", + "language_model.model.layers.26.mlp.gate.biases": "model-00043.safetensors", + "language_model.model.layers.26.mlp.shared_expert.down_proj.weight": "model-00043.safetensors", + "language_model.model.layers.26.mlp.shared_expert.down_proj.scales": "model-00043.safetensors", + "language_model.model.layers.26.mlp.shared_expert.down_proj.biases": "model-00043.safetensors", + "language_model.model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00043.safetensors", + "language_model.model.layers.26.mlp.shared_expert.gate_proj.scales": "model-00043.safetensors", + "language_model.model.layers.26.mlp.shared_expert.gate_proj.biases": "model-00043.safetensors", + "language_model.model.layers.26.mlp.shared_expert.up_proj.weight": "model-00043.safetensors", + "language_model.model.layers.26.mlp.shared_expert.up_proj.scales": "model-00043.safetensors", + "language_model.model.layers.26.mlp.shared_expert.up_proj.biases": "model-00043.safetensors", + "language_model.model.layers.26.mlp.shared_expert_gate.weight": "model-00043.safetensors", + "language_model.model.layers.26.mlp_hyper_connection.block_inject_weight.weight": "model-00043.safetensors", + "language_model.model.layers.26.mlp_hyper_connection.hc_norm.weight": "model-00043.safetensors", + "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_down.weight": "model-00043.safetensors", + "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_down.scales": "model-00043.safetensors", + "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_down.biases": "model-00043.safetensors", + "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_up.weight": "model-00043.safetensors", + "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_up.scales": "model-00043.safetensors", + "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_up.biases": "model-00043.safetensors", + "language_model.model.layers.27.attn_hyper_connection.block_inject_weight.weight": "model-00043.safetensors", + "language_model.model.layers.27.attn_hyper_connection.hc_norm.weight": "model-00043.safetensors", + "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_down.weight": "model-00043.safetensors", + "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_down.scales": "model-00043.safetensors", + "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_down.biases": "model-00043.safetensors", + "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_up.weight": "model-00043.safetensors", + "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_up.scales": "model-00043.safetensors", + "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_up.biases": "model-00043.safetensors", + "language_model.model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00044.safetensors", + "language_model.model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00044.safetensors", + "language_model.model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00044.safetensors", + "language_model.model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00044.safetensors", + "language_model.model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00044.safetensors", + "language_model.model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00044.safetensors", + "language_model.model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00045.safetensors", + "language_model.model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00045.safetensors", + "language_model.model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00045.safetensors", + "language_model.model.layers.27.mlp.gate.weight": "model-00045.safetensors", + "language_model.model.layers.27.mlp.gate.scales": "model-00045.safetensors", + "language_model.model.layers.27.mlp.gate.biases": "model-00045.safetensors", + "language_model.model.layers.27.mlp.shared_expert.down_proj.weight": "model-00045.safetensors", + "language_model.model.layers.27.mlp.shared_expert.down_proj.scales": "model-00045.safetensors", + "language_model.model.layers.27.mlp.shared_expert.down_proj.biases": "model-00045.safetensors", + "language_model.model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00045.safetensors", + "language_model.model.layers.27.mlp.shared_expert.gate_proj.scales": "model-00045.safetensors", + "language_model.model.layers.27.mlp.shared_expert.gate_proj.biases": "model-00045.safetensors", + "language_model.model.layers.27.mlp.shared_expert.up_proj.weight": "model-00045.safetensors", + "language_model.model.layers.27.mlp.shared_expert.up_proj.scales": "model-00045.safetensors", + "language_model.model.layers.27.mlp.shared_expert.up_proj.biases": "model-00045.safetensors", + "language_model.model.layers.27.mlp.shared_expert_gate.weight": "model-00045.safetensors", + "language_model.model.layers.27.mlp_hyper_connection.block_inject_weight.weight": "model-00045.safetensors", + "language_model.model.layers.27.mlp_hyper_connection.hc_norm.weight": "model-00045.safetensors", + "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_down.weight": "model-00045.safetensors", + "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_down.scales": "model-00045.safetensors", + "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_down.biases": "model-00045.safetensors", + "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_up.weight": "model-00045.safetensors", + "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_up.scales": "model-00045.safetensors", + "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_up.biases": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.indexer.index_qk_proj.weight": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.indexer.index_qk_proj.scales": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.indexer.index_qk_proj.biases": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.indexer.k_layernorm.weight": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.indexer.q_layernorm.weight": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.k_norm.weight": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.k_proj.weight": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.k_proj.scales": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.k_proj.biases": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.o_proj.weight": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.o_proj.scales": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.o_proj.biases": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.q_norm.weight": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.q_proj.weight": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.q_proj.scales": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.q_proj.biases": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.v_proj.weight": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.v_proj.scales": "model-00045.safetensors", + "language_model.model.layers.27.self_attn.v_proj.biases": "model-00045.safetensors", + "language_model.model.layers.28.attn_hyper_connection.block_inject_weight.weight": "model-00045.safetensors", + "language_model.model.layers.28.attn_hyper_connection.hc_norm.weight": "model-00045.safetensors", + "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_down.weight": "model-00045.safetensors", + "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_down.scales": "model-00045.safetensors", + "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_down.biases": "model-00045.safetensors", + "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_up.weight": "model-00045.safetensors", + "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_up.scales": "model-00045.safetensors", + "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_up.biases": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.A_log": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.conv1d.weight": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.dt_bias": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.in_proj_a.weight": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.in_proj_a.scales": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.in_proj_a.biases": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.in_proj_b.weight": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.in_proj_b.scales": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.in_proj_b.biases": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.in_proj_qkv.weight": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.in_proj_qkv.scales": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.in_proj_qkv.biases": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.in_proj_z.weight": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.in_proj_z.scales": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.in_proj_z.biases": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.norm.weight": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.out_proj.weight": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.out_proj.scales": "model-00045.safetensors", + "language_model.model.layers.28.linear_attn.out_proj.biases": "model-00045.safetensors", + "language_model.mtp.layers.0.mlp.shared_expert.down_proj.weight": "model-00045.safetensors", + "language_model.mtp.layers.0.mlp.shared_expert.down_proj.scales": "model-00045.safetensors", + "language_model.mtp.layers.0.mlp.shared_expert.down_proj.biases": "model-00045.safetensors", + "language_model.model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00046.safetensors", + "language_model.model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00046.safetensors", + "language_model.model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00046.safetensors", + "language_model.model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00046.safetensors", + "language_model.model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00046.safetensors", + "language_model.model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00046.safetensors", + "language_model.model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00047.safetensors", + "language_model.model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00047.safetensors", + "language_model.model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00047.safetensors", + "language_model.model.layers.28.mlp.gate.weight": "model-00047.safetensors", + "language_model.model.layers.28.mlp.gate.scales": "model-00047.safetensors", + "language_model.model.layers.28.mlp.gate.biases": "model-00047.safetensors", + "language_model.model.layers.28.mlp.shared_expert.down_proj.weight": "model-00047.safetensors", + "language_model.model.layers.28.mlp.shared_expert.down_proj.scales": "model-00047.safetensors", + "language_model.model.layers.28.mlp.shared_expert.down_proj.biases": "model-00047.safetensors", + "language_model.model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00047.safetensors", + "language_model.model.layers.28.mlp.shared_expert.gate_proj.scales": "model-00047.safetensors", + "language_model.model.layers.28.mlp.shared_expert.gate_proj.biases": "model-00047.safetensors", + "language_model.model.layers.28.mlp.shared_expert.up_proj.weight": "model-00047.safetensors", + "language_model.model.layers.28.mlp.shared_expert.up_proj.scales": "model-00047.safetensors", + "language_model.model.layers.28.mlp.shared_expert.up_proj.biases": "model-00047.safetensors", + "language_model.model.layers.28.mlp.shared_expert_gate.weight": "model-00047.safetensors", + "language_model.model.layers.28.mlp_hyper_connection.block_inject_weight.weight": "model-00047.safetensors", + "language_model.model.layers.28.mlp_hyper_connection.hc_norm.weight": "model-00047.safetensors", + "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_down.weight": "model-00047.safetensors", + "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_down.scales": "model-00047.safetensors", + "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_down.biases": "model-00047.safetensors", + "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_up.weight": "model-00047.safetensors", + "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_up.scales": "model-00047.safetensors", + "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_up.biases": "model-00047.safetensors", + "language_model.model.layers.29.attn_hyper_connection.block_inject_weight.weight": "model-00047.safetensors", + "language_model.model.layers.29.attn_hyper_connection.hc_norm.weight": "model-00047.safetensors", + "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_down.weight": "model-00047.safetensors", + "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_down.scales": "model-00047.safetensors", + "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_down.biases": "model-00047.safetensors", + "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_up.weight": "model-00047.safetensors", + "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_up.scales": "model-00047.safetensors", + "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_up.biases": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.A_log": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.conv1d.weight": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.dt_bias": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.in_proj_a.weight": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.in_proj_a.scales": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.in_proj_a.biases": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.in_proj_b.weight": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.in_proj_b.scales": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.in_proj_b.biases": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.in_proj_qkv.weight": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.in_proj_qkv.scales": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.in_proj_qkv.biases": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.in_proj_z.weight": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.in_proj_z.scales": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.in_proj_z.biases": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.norm.weight": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.out_proj.weight": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.out_proj.scales": "model-00047.safetensors", + "language_model.model.layers.29.linear_attn.out_proj.biases": "model-00047.safetensors", + "language_model.mtp.layers.0.mlp_hyper_connection.block_inject_weight.weight": "model-00047.safetensors", + "language_model.model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00048.safetensors", + "language_model.model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00048.safetensors", + "language_model.model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00048.safetensors", + "language_model.model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00048.safetensors", + "language_model.model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00048.safetensors", + "language_model.model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00048.safetensors", + "language_model.model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00049.safetensors", + "language_model.model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00049.safetensors", + "language_model.model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00049.safetensors", + "language_model.model.layers.29.mlp.gate.weight": "model-00049.safetensors", + "language_model.model.layers.29.mlp.gate.scales": "model-00049.safetensors", + "language_model.model.layers.29.mlp.gate.biases": "model-00049.safetensors", + "language_model.model.layers.29.mlp.shared_expert.down_proj.weight": "model-00049.safetensors", + "language_model.model.layers.29.mlp.shared_expert.down_proj.scales": "model-00049.safetensors", + "language_model.model.layers.29.mlp.shared_expert.down_proj.biases": "model-00049.safetensors", + "language_model.model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00049.safetensors", + "language_model.model.layers.29.mlp.shared_expert.gate_proj.scales": "model-00049.safetensors", + "language_model.model.layers.29.mlp.shared_expert.gate_proj.biases": "model-00049.safetensors", + "language_model.model.layers.29.mlp.shared_expert.up_proj.weight": "model-00049.safetensors", + "language_model.model.layers.29.mlp.shared_expert.up_proj.scales": "model-00049.safetensors", + "language_model.model.layers.29.mlp.shared_expert.up_proj.biases": "model-00049.safetensors", + "language_model.model.layers.29.mlp.shared_expert_gate.weight": "model-00049.safetensors", + "language_model.model.layers.29.mlp_hyper_connection.block_inject_weight.weight": "model-00049.safetensors", + "language_model.model.layers.29.mlp_hyper_connection.hc_norm.weight": "model-00049.safetensors", + "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_down.weight": "model-00049.safetensors", + "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_down.scales": "model-00049.safetensors", + "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_down.biases": "model-00049.safetensors", + "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_up.weight": "model-00049.safetensors", + "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_up.scales": "model-00049.safetensors", + "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_up.biases": "model-00049.safetensors", + "language_model.model.layers.3.attn_hyper_connection.block_inject_weight.weight": "model-00049.safetensors", + "language_model.model.layers.3.attn_hyper_connection.hc_norm.weight": "model-00049.safetensors", + "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_down.weight": "model-00049.safetensors", + "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_down.scales": "model-00049.safetensors", + "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_down.biases": "model-00049.safetensors", + "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_up.weight": "model-00049.safetensors", + "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_up.scales": "model-00049.safetensors", + "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_up.biases": "model-00049.safetensors", + "language_model.model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00050.safetensors", + "language_model.model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00050.safetensors", + "language_model.model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00050.safetensors", + "language_model.model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00050.safetensors", + "language_model.model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00050.safetensors", + "language_model.model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00050.safetensors", + "language_model.model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00051.safetensors", + "language_model.model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00051.safetensors", + "language_model.model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00051.safetensors", + "language_model.model.layers.3.mlp.gate.weight": "model-00051.safetensors", + "language_model.model.layers.3.mlp.gate.scales": "model-00051.safetensors", + "language_model.model.layers.3.mlp.gate.biases": "model-00051.safetensors", + "language_model.model.layers.3.mlp.shared_expert.down_proj.weight": "model-00051.safetensors", + "language_model.model.layers.3.mlp.shared_expert.down_proj.scales": "model-00051.safetensors", + "language_model.model.layers.3.mlp.shared_expert.down_proj.biases": "model-00051.safetensors", + "language_model.model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00051.safetensors", + "language_model.model.layers.3.mlp.shared_expert.gate_proj.scales": "model-00051.safetensors", + "language_model.model.layers.3.mlp.shared_expert.gate_proj.biases": "model-00051.safetensors", + "language_model.model.layers.3.mlp.shared_expert.up_proj.weight": "model-00051.safetensors", + "language_model.model.layers.3.mlp.shared_expert.up_proj.scales": "model-00051.safetensors", + "language_model.model.layers.3.mlp.shared_expert.up_proj.biases": "model-00051.safetensors", + "language_model.model.layers.3.mlp.shared_expert_gate.weight": "model-00051.safetensors", + "language_model.model.layers.3.mlp_hyper_connection.block_inject_weight.weight": "model-00051.safetensors", + "language_model.model.layers.3.mlp_hyper_connection.hc_norm.weight": "model-00051.safetensors", + "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_down.weight": "model-00051.safetensors", + "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_down.scales": "model-00051.safetensors", + "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_down.biases": "model-00051.safetensors", + "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_up.weight": "model-00051.safetensors", + "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_up.scales": "model-00051.safetensors", + "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_up.biases": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.indexer.index_qk_proj.weight": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.indexer.index_qk_proj.scales": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.indexer.index_qk_proj.biases": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.indexer.k_layernorm.weight": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.indexer.q_layernorm.weight": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.k_norm.weight": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.k_proj.weight": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.k_proj.scales": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.k_proj.biases": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.o_proj.weight": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.o_proj.scales": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.o_proj.biases": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.q_norm.weight": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.q_proj.weight": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.q_proj.scales": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.q_proj.biases": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.v_proj.weight": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.v_proj.scales": "model-00051.safetensors", + "language_model.model.layers.3.self_attn.v_proj.biases": "model-00051.safetensors", + "language_model.model.layers.30.attn_hyper_connection.block_inject_weight.weight": "model-00051.safetensors", + "language_model.model.layers.30.attn_hyper_connection.hc_norm.weight": "model-00051.safetensors", + "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_down.weight": "model-00051.safetensors", + "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_down.scales": "model-00051.safetensors", + "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_down.biases": "model-00051.safetensors", + "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_up.weight": "model-00051.safetensors", + "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_up.scales": "model-00051.safetensors", + "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_up.biases": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.A_log": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.conv1d.weight": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.dt_bias": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.in_proj_a.weight": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.in_proj_a.scales": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.in_proj_a.biases": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.in_proj_b.weight": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.in_proj_b.scales": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.in_proj_b.biases": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.in_proj_qkv.weight": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.in_proj_qkv.scales": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.in_proj_qkv.biases": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.in_proj_z.weight": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.in_proj_z.scales": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.in_proj_z.biases": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.norm.weight": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.out_proj.weight": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.out_proj.scales": "model-00051.safetensors", + "language_model.model.layers.30.linear_attn.out_proj.biases": "model-00051.safetensors", + "language_model.mtp.layers.0.mlp_hyper_connection.hc_norm.weight": "model-00051.safetensors", + "language_model.model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00052.safetensors", + "language_model.model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00052.safetensors", + "language_model.model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00052.safetensors", + "language_model.model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00052.safetensors", + "language_model.model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00052.safetensors", + "language_model.model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00052.safetensors", + "language_model.model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00053.safetensors", + "language_model.model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00053.safetensors", + "language_model.model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00053.safetensors", + "language_model.model.layers.30.mlp.gate.weight": "model-00053.safetensors", + "language_model.model.layers.30.mlp.gate.scales": "model-00053.safetensors", + "language_model.model.layers.30.mlp.gate.biases": "model-00053.safetensors", + "language_model.model.layers.30.mlp.shared_expert.down_proj.weight": "model-00053.safetensors", + "language_model.model.layers.30.mlp.shared_expert.down_proj.scales": "model-00053.safetensors", + "language_model.model.layers.30.mlp.shared_expert.down_proj.biases": "model-00053.safetensors", + "language_model.model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00053.safetensors", + "language_model.model.layers.30.mlp.shared_expert.gate_proj.scales": "model-00053.safetensors", + "language_model.model.layers.30.mlp.shared_expert.gate_proj.biases": "model-00053.safetensors", + "language_model.model.layers.30.mlp.shared_expert.up_proj.weight": "model-00053.safetensors", + "language_model.model.layers.30.mlp.shared_expert.up_proj.scales": "model-00053.safetensors", + "language_model.model.layers.30.mlp.shared_expert.up_proj.biases": "model-00053.safetensors", + "language_model.model.layers.30.mlp.shared_expert_gate.weight": "model-00053.safetensors", + "language_model.model.layers.30.mlp_hyper_connection.block_inject_weight.weight": "model-00053.safetensors", + "language_model.model.layers.30.mlp_hyper_connection.hc_norm.weight": "model-00053.safetensors", + "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_down.weight": "model-00053.safetensors", + "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_down.scales": "model-00053.safetensors", + "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_down.biases": "model-00053.safetensors", + "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_up.weight": "model-00053.safetensors", + "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_up.scales": "model-00053.safetensors", + "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_up.biases": "model-00053.safetensors", + "language_model.model.layers.31.attn_hyper_connection.block_inject_weight.weight": "model-00053.safetensors", + "language_model.model.layers.31.attn_hyper_connection.hc_norm.weight": "model-00053.safetensors", + "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_down.weight": "model-00053.safetensors", + "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_down.scales": "model-00053.safetensors", + "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_down.biases": "model-00053.safetensors", + "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_up.weight": "model-00053.safetensors", + "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_up.scales": "model-00053.safetensors", + "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_up.biases": "model-00053.safetensors", + "language_model.model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00054.safetensors", + "language_model.model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00054.safetensors", + "language_model.model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00054.safetensors", + "language_model.model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00054.safetensors", + "language_model.model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00054.safetensors", + "language_model.model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00054.safetensors", + "language_model.model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00055.safetensors", + "language_model.model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00055.safetensors", + "language_model.model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00055.safetensors", + "language_model.model.layers.31.mlp.gate.weight": "model-00055.safetensors", + "language_model.model.layers.31.mlp.gate.scales": "model-00055.safetensors", + "language_model.model.layers.31.mlp.gate.biases": "model-00055.safetensors", + "language_model.model.layers.31.mlp.shared_expert.down_proj.weight": "model-00055.safetensors", + "language_model.model.layers.31.mlp.shared_expert.down_proj.scales": "model-00055.safetensors", + "language_model.model.layers.31.mlp.shared_expert.down_proj.biases": "model-00055.safetensors", + "language_model.model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00055.safetensors", + "language_model.model.layers.31.mlp.shared_expert.gate_proj.scales": "model-00055.safetensors", + "language_model.model.layers.31.mlp.shared_expert.gate_proj.biases": "model-00055.safetensors", + "language_model.model.layers.31.mlp.shared_expert.up_proj.weight": "model-00055.safetensors", + "language_model.model.layers.31.mlp.shared_expert.up_proj.scales": "model-00055.safetensors", + "language_model.model.layers.31.mlp.shared_expert.up_proj.biases": "model-00055.safetensors", + "language_model.model.layers.31.mlp.shared_expert_gate.weight": "model-00055.safetensors", + "language_model.model.layers.31.mlp_hyper_connection.block_inject_weight.weight": "model-00055.safetensors", + "language_model.model.layers.31.mlp_hyper_connection.hc_norm.weight": "model-00055.safetensors", + "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_down.weight": "model-00055.safetensors", + "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_down.scales": "model-00055.safetensors", + "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_down.biases": "model-00055.safetensors", + "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_up.weight": "model-00055.safetensors", + "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_up.scales": "model-00055.safetensors", + "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_up.biases": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.indexer.index_qk_proj.weight": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.indexer.index_qk_proj.scales": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.indexer.index_qk_proj.biases": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.indexer.k_layernorm.weight": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.indexer.q_layernorm.weight": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.k_norm.weight": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.k_proj.weight": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.k_proj.scales": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.k_proj.biases": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.o_proj.weight": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.o_proj.scales": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.o_proj.biases": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.q_norm.weight": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.q_proj.weight": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.q_proj.scales": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.q_proj.biases": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.v_proj.weight": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.v_proj.scales": "model-00055.safetensors", + "language_model.model.layers.31.self_attn.v_proj.biases": "model-00055.safetensors", + "language_model.model.layers.32.attn_hyper_connection.block_inject_weight.weight": "model-00055.safetensors", + "language_model.model.layers.32.attn_hyper_connection.hc_norm.weight": "model-00055.safetensors", + "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_down.weight": "model-00055.safetensors", + "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_down.scales": "model-00055.safetensors", + "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_down.biases": "model-00055.safetensors", + "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_up.weight": "model-00055.safetensors", + "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_up.scales": "model-00055.safetensors", + "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_up.biases": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.A_log": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.conv1d.weight": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.dt_bias": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.in_proj_a.weight": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.in_proj_a.scales": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.in_proj_a.biases": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.in_proj_b.weight": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.in_proj_b.scales": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.in_proj_b.biases": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.in_proj_qkv.weight": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.in_proj_qkv.scales": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.in_proj_qkv.biases": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.in_proj_z.weight": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.in_proj_z.scales": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.in_proj_z.biases": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.norm.weight": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.out_proj.weight": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.out_proj.scales": "model-00055.safetensors", + "language_model.model.layers.32.linear_attn.out_proj.biases": "model-00055.safetensors", + "language_model.mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.weight": "model-00055.safetensors", + "language_model.mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.scales": "model-00055.safetensors", + "language_model.mtp.layers.0.mlp_hyper_connection.input_mix_weight_down.biases": "model-00055.safetensors", + "language_model.model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00056.safetensors", + "language_model.model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00056.safetensors", + "language_model.model.layers.32.mlp.switch_mlp.gate_proj.biases": "model-00056.safetensors", + "language_model.model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00056.safetensors", + "language_model.model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00056.safetensors", + "language_model.model.layers.32.mlp.switch_mlp.up_proj.biases": "model-00056.safetensors", + "language_model.model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00057.safetensors", + "language_model.model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00057.safetensors", + "language_model.model.layers.32.mlp.switch_mlp.down_proj.biases": "model-00057.safetensors", + "language_model.model.layers.32.mlp.gate.weight": "model-00057.safetensors", + "language_model.model.layers.32.mlp.gate.scales": "model-00057.safetensors", + "language_model.model.layers.32.mlp.gate.biases": "model-00057.safetensors", + "language_model.model.layers.32.mlp.shared_expert.down_proj.weight": "model-00057.safetensors", + "language_model.model.layers.32.mlp.shared_expert.down_proj.scales": "model-00057.safetensors", + "language_model.model.layers.32.mlp.shared_expert.down_proj.biases": "model-00057.safetensors", + "language_model.model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00057.safetensors", + "language_model.model.layers.32.mlp.shared_expert.gate_proj.scales": "model-00057.safetensors", + "language_model.model.layers.32.mlp.shared_expert.gate_proj.biases": "model-00057.safetensors", + "language_model.model.layers.32.mlp.shared_expert.up_proj.weight": "model-00057.safetensors", + "language_model.model.layers.32.mlp.shared_expert.up_proj.scales": "model-00057.safetensors", + "language_model.model.layers.32.mlp.shared_expert.up_proj.biases": "model-00057.safetensors", + "language_model.model.layers.32.mlp.shared_expert_gate.weight": "model-00057.safetensors", + "language_model.model.layers.32.mlp_hyper_connection.block_inject_weight.weight": "model-00057.safetensors", + "language_model.model.layers.32.mlp_hyper_connection.hc_norm.weight": "model-00057.safetensors", + "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_down.weight": "model-00057.safetensors", + "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_down.scales": "model-00057.safetensors", + "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_down.biases": "model-00057.safetensors", + "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_up.weight": "model-00057.safetensors", + "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_up.scales": "model-00057.safetensors", + "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_up.biases": "model-00057.safetensors", + "language_model.model.layers.33.attn_hyper_connection.block_inject_weight.weight": "model-00057.safetensors", + "language_model.model.layers.33.attn_hyper_connection.hc_norm.weight": "model-00057.safetensors", + "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_down.weight": "model-00057.safetensors", + "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_down.scales": "model-00057.safetensors", + "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_down.biases": "model-00057.safetensors", + "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_up.weight": "model-00057.safetensors", + "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_up.scales": "model-00057.safetensors", + "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_up.biases": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.A_log": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.conv1d.weight": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.dt_bias": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.in_proj_a.weight": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.in_proj_a.scales": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.in_proj_a.biases": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.in_proj_b.weight": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.in_proj_b.scales": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.in_proj_b.biases": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.in_proj_qkv.weight": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.in_proj_qkv.scales": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.in_proj_qkv.biases": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.in_proj_z.weight": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.in_proj_z.scales": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.in_proj_z.biases": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.norm.weight": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.out_proj.weight": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.out_proj.scales": "model-00057.safetensors", + "language_model.model.layers.33.linear_attn.out_proj.biases": "model-00057.safetensors", + "language_model.mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.weight": "model-00057.safetensors", + "language_model.mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.scales": "model-00057.safetensors", + "language_model.mtp.layers.0.mlp_hyper_connection.input_mix_weight_up.biases": "model-00057.safetensors", + "language_model.model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00058.safetensors", + "language_model.model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00058.safetensors", + "language_model.model.layers.33.mlp.switch_mlp.gate_proj.biases": "model-00058.safetensors", + "language_model.model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00058.safetensors", + "language_model.model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00058.safetensors", + "language_model.model.layers.33.mlp.switch_mlp.up_proj.biases": "model-00058.safetensors", + "language_model.model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00059.safetensors", + "language_model.model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00059.safetensors", + "language_model.model.layers.33.mlp.switch_mlp.down_proj.biases": "model-00059.safetensors", + "language_model.model.layers.33.mlp.gate.weight": "model-00059.safetensors", + "language_model.model.layers.33.mlp.gate.scales": "model-00059.safetensors", + "language_model.model.layers.33.mlp.gate.biases": "model-00059.safetensors", + "language_model.model.layers.33.mlp.shared_expert.down_proj.weight": "model-00059.safetensors", + "language_model.model.layers.33.mlp.shared_expert.down_proj.scales": "model-00059.safetensors", + "language_model.model.layers.33.mlp.shared_expert.down_proj.biases": "model-00059.safetensors", + "language_model.model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00059.safetensors", + "language_model.model.layers.33.mlp.shared_expert.gate_proj.scales": "model-00059.safetensors", + "language_model.model.layers.33.mlp.shared_expert.gate_proj.biases": "model-00059.safetensors", + "language_model.model.layers.33.mlp.shared_expert.up_proj.weight": "model-00059.safetensors", + "language_model.model.layers.33.mlp.shared_expert.up_proj.scales": "model-00059.safetensors", + "language_model.model.layers.33.mlp.shared_expert.up_proj.biases": "model-00059.safetensors", + "language_model.model.layers.33.mlp.shared_expert_gate.weight": "model-00059.safetensors", + "language_model.model.layers.33.mlp_hyper_connection.block_inject_weight.weight": "model-00059.safetensors", + "language_model.model.layers.33.mlp_hyper_connection.hc_norm.weight": "model-00059.safetensors", + "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_down.weight": "model-00059.safetensors", + "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_down.scales": "model-00059.safetensors", + "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_down.biases": "model-00059.safetensors", + "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_up.weight": "model-00059.safetensors", + "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_up.scales": "model-00059.safetensors", + "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_up.biases": "model-00059.safetensors", + "language_model.model.layers.34.attn_hyper_connection.block_inject_weight.weight": "model-00059.safetensors", + "language_model.model.layers.34.attn_hyper_connection.hc_norm.weight": "model-00059.safetensors", + "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_down.weight": "model-00059.safetensors", + "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_down.scales": "model-00059.safetensors", + "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_down.biases": "model-00059.safetensors", + "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_up.weight": "model-00059.safetensors", + "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_up.scales": "model-00059.safetensors", + "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_up.biases": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.A_log": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.conv1d.weight": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.dt_bias": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.in_proj_a.weight": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.in_proj_a.scales": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.in_proj_a.biases": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.in_proj_b.weight": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.in_proj_b.scales": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.in_proj_b.biases": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.in_proj_qkv.weight": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.in_proj_qkv.scales": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.in_proj_qkv.biases": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.in_proj_z.weight": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.in_proj_z.scales": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.in_proj_z.biases": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.norm.weight": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.out_proj.weight": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.out_proj.scales": "model-00059.safetensors", + "language_model.model.layers.34.linear_attn.out_proj.biases": "model-00059.safetensors", + "language_model.mtp.layers.0.self_attn.indexer.index_qk_proj.weight": "model-00059.safetensors", + "language_model.mtp.layers.0.self_attn.indexer.index_qk_proj.scales": "model-00059.safetensors", + "language_model.mtp.layers.0.self_attn.indexer.index_qk_proj.biases": "model-00059.safetensors", + "language_model.model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00060.safetensors", + "language_model.model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00060.safetensors", + "language_model.model.layers.34.mlp.switch_mlp.gate_proj.biases": "model-00060.safetensors", + "language_model.model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00060.safetensors", + "language_model.model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00060.safetensors", + "language_model.model.layers.34.mlp.switch_mlp.up_proj.biases": "model-00060.safetensors", + "language_model.model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00061.safetensors", + "language_model.model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00061.safetensors", + "language_model.model.layers.34.mlp.switch_mlp.down_proj.biases": "model-00061.safetensors", + "language_model.model.layers.34.mlp.gate.weight": "model-00061.safetensors", + "language_model.model.layers.34.mlp.gate.scales": "model-00061.safetensors", + "language_model.model.layers.34.mlp.gate.biases": "model-00061.safetensors", + "language_model.model.layers.34.mlp.shared_expert.down_proj.weight": "model-00061.safetensors", + "language_model.model.layers.34.mlp.shared_expert.down_proj.scales": "model-00061.safetensors", + "language_model.model.layers.34.mlp.shared_expert.down_proj.biases": "model-00061.safetensors", + "language_model.model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00061.safetensors", + "language_model.model.layers.34.mlp.shared_expert.gate_proj.scales": "model-00061.safetensors", + "language_model.model.layers.34.mlp.shared_expert.gate_proj.biases": "model-00061.safetensors", + "language_model.model.layers.34.mlp.shared_expert.up_proj.weight": "model-00061.safetensors", + "language_model.model.layers.34.mlp.shared_expert.up_proj.scales": "model-00061.safetensors", + "language_model.model.layers.34.mlp.shared_expert.up_proj.biases": "model-00061.safetensors", + "language_model.model.layers.34.mlp.shared_expert_gate.weight": "model-00061.safetensors", + "language_model.model.layers.34.mlp_hyper_connection.block_inject_weight.weight": "model-00061.safetensors", + "language_model.model.layers.34.mlp_hyper_connection.hc_norm.weight": "model-00061.safetensors", + "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_down.weight": "model-00061.safetensors", + "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_down.scales": "model-00061.safetensors", + "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_down.biases": "model-00061.safetensors", + "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_up.weight": "model-00061.safetensors", + "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_up.scales": "model-00061.safetensors", + "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_up.biases": "model-00061.safetensors", + "language_model.model.layers.35.attn_hyper_connection.block_inject_weight.weight": "model-00061.safetensors", + "language_model.model.layers.35.attn_hyper_connection.hc_norm.weight": "model-00061.safetensors", + "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_down.weight": "model-00061.safetensors", + "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_down.scales": "model-00061.safetensors", + "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_down.biases": "model-00061.safetensors", + "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_up.weight": "model-00061.safetensors", + "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_up.scales": "model-00061.safetensors", + "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_up.biases": "model-00061.safetensors", + "language_model.model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00062.safetensors", + "language_model.model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00062.safetensors", + "language_model.model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00062.safetensors", + "language_model.model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00062.safetensors", + "language_model.model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00062.safetensors", + "language_model.model.layers.35.mlp.switch_mlp.up_proj.biases": "model-00062.safetensors", + "language_model.model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00063.safetensors", + "language_model.model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00063.safetensors", + "language_model.model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00063.safetensors", + "language_model.model.layers.35.mlp.gate.weight": "model-00063.safetensors", + "language_model.model.layers.35.mlp.gate.scales": "model-00063.safetensors", + "language_model.model.layers.35.mlp.gate.biases": "model-00063.safetensors", + "language_model.model.layers.35.mlp.shared_expert.down_proj.weight": "model-00063.safetensors", + "language_model.model.layers.35.mlp.shared_expert.down_proj.scales": "model-00063.safetensors", + "language_model.model.layers.35.mlp.shared_expert.down_proj.biases": "model-00063.safetensors", + "language_model.model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00063.safetensors", + "language_model.model.layers.35.mlp.shared_expert.gate_proj.scales": "model-00063.safetensors", + "language_model.model.layers.35.mlp.shared_expert.gate_proj.biases": "model-00063.safetensors", + "language_model.model.layers.35.mlp.shared_expert.up_proj.weight": "model-00063.safetensors", + "language_model.model.layers.35.mlp.shared_expert.up_proj.scales": "model-00063.safetensors", + "language_model.model.layers.35.mlp.shared_expert.up_proj.biases": "model-00063.safetensors", + "language_model.model.layers.35.mlp.shared_expert_gate.weight": "model-00063.safetensors", + "language_model.model.layers.35.mlp_hyper_connection.block_inject_weight.weight": "model-00063.safetensors", + "language_model.model.layers.35.mlp_hyper_connection.hc_norm.weight": "model-00063.safetensors", + "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_down.weight": "model-00063.safetensors", + "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_down.scales": "model-00063.safetensors", + "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_down.biases": "model-00063.safetensors", + "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_up.weight": "model-00063.safetensors", + "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_up.scales": "model-00063.safetensors", + "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_up.biases": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.indexer.index_qk_proj.weight": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.indexer.index_qk_proj.scales": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.indexer.index_qk_proj.biases": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.indexer.k_layernorm.weight": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.indexer.q_layernorm.weight": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.k_norm.weight": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.k_proj.weight": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.k_proj.scales": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.k_proj.biases": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.o_proj.weight": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.o_proj.scales": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.o_proj.biases": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.q_norm.weight": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.q_proj.weight": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.q_proj.scales": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.q_proj.biases": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.v_proj.weight": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.v_proj.scales": "model-00063.safetensors", + "language_model.model.layers.35.self_attn.v_proj.biases": "model-00063.safetensors", + "language_model.model.layers.36.attn_hyper_connection.block_inject_weight.weight": "model-00063.safetensors", + "language_model.model.layers.36.attn_hyper_connection.hc_norm.weight": "model-00063.safetensors", + "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_down.weight": "model-00063.safetensors", + "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_down.scales": "model-00063.safetensors", + "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_down.biases": "model-00063.safetensors", + "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_up.weight": "model-00063.safetensors", + "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_up.scales": "model-00063.safetensors", + "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_up.biases": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.A_log": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.conv1d.weight": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.dt_bias": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.in_proj_a.weight": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.in_proj_a.scales": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.in_proj_a.biases": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.in_proj_b.weight": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.in_proj_b.scales": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.in_proj_b.biases": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.in_proj_qkv.weight": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.in_proj_qkv.scales": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.in_proj_qkv.biases": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.in_proj_z.weight": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.in_proj_z.scales": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.in_proj_z.biases": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.norm.weight": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.out_proj.weight": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.out_proj.scales": "model-00063.safetensors", + "language_model.model.layers.36.linear_attn.out_proj.biases": "model-00063.safetensors", + "language_model.mtp.layers.0.self_attn.indexer.k_layernorm.weight": "model-00063.safetensors", + "language_model.model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00064.safetensors", + "language_model.model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00064.safetensors", + "language_model.model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00064.safetensors", + "language_model.model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00064.safetensors", + "language_model.model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00064.safetensors", + "language_model.model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00064.safetensors", + "language_model.model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00065.safetensors", + "language_model.model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00065.safetensors", + "language_model.model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00065.safetensors", + "language_model.model.layers.36.mlp.gate.weight": "model-00065.safetensors", + "language_model.model.layers.36.mlp.gate.scales": "model-00065.safetensors", + "language_model.model.layers.36.mlp.gate.biases": "model-00065.safetensors", + "language_model.model.layers.36.mlp.shared_expert.down_proj.weight": "model-00065.safetensors", + "language_model.model.layers.36.mlp.shared_expert.down_proj.scales": "model-00065.safetensors", + "language_model.model.layers.36.mlp.shared_expert.down_proj.biases": "model-00065.safetensors", + "language_model.model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00065.safetensors", + "language_model.model.layers.36.mlp.shared_expert.gate_proj.scales": "model-00065.safetensors", + "language_model.model.layers.36.mlp.shared_expert.gate_proj.biases": "model-00065.safetensors", + "language_model.model.layers.36.mlp.shared_expert.up_proj.weight": "model-00065.safetensors", + "language_model.model.layers.36.mlp.shared_expert.up_proj.scales": "model-00065.safetensors", + "language_model.model.layers.36.mlp.shared_expert.up_proj.biases": "model-00065.safetensors", + "language_model.model.layers.36.mlp.shared_expert_gate.weight": "model-00065.safetensors", + "language_model.model.layers.36.mlp_hyper_connection.block_inject_weight.weight": "model-00065.safetensors", + "language_model.model.layers.36.mlp_hyper_connection.hc_norm.weight": "model-00065.safetensors", + "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_down.weight": "model-00065.safetensors", + "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_down.scales": "model-00065.safetensors", + "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_down.biases": "model-00065.safetensors", + "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_up.weight": "model-00065.safetensors", + "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_up.scales": "model-00065.safetensors", + "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_up.biases": "model-00065.safetensors", + "language_model.model.layers.37.attn_hyper_connection.block_inject_weight.weight": "model-00065.safetensors", + "language_model.model.layers.37.attn_hyper_connection.hc_norm.weight": "model-00065.safetensors", + "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_down.weight": "model-00065.safetensors", + "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_down.scales": "model-00065.safetensors", + "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_down.biases": "model-00065.safetensors", + "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_up.weight": "model-00065.safetensors", + "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_up.scales": "model-00065.safetensors", + "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_up.biases": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.A_log": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.conv1d.weight": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.dt_bias": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.in_proj_a.weight": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.in_proj_a.scales": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.in_proj_a.biases": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.in_proj_b.weight": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.in_proj_b.scales": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.in_proj_b.biases": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.in_proj_qkv.weight": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.in_proj_qkv.scales": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.in_proj_qkv.biases": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.in_proj_z.weight": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.in_proj_z.scales": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.in_proj_z.biases": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.norm.weight": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.out_proj.weight": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.out_proj.scales": "model-00065.safetensors", + "language_model.model.layers.37.linear_attn.out_proj.biases": "model-00065.safetensors", + "language_model.model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00066.safetensors", + "language_model.model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00066.safetensors", + "language_model.model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-00066.safetensors", + "language_model.model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00066.safetensors", + "language_model.model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00066.safetensors", + "language_model.model.layers.37.mlp.switch_mlp.up_proj.biases": "model-00066.safetensors", + "language_model.model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00067.safetensors", + "language_model.model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00067.safetensors", + "language_model.model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00067.safetensors", + "language_model.model.layers.37.mlp.gate.weight": "model-00067.safetensors", + "language_model.model.layers.37.mlp.gate.scales": "model-00067.safetensors", + "language_model.model.layers.37.mlp.gate.biases": "model-00067.safetensors", + "language_model.model.layers.37.mlp.shared_expert.down_proj.weight": "model-00067.safetensors", + "language_model.model.layers.37.mlp.shared_expert.down_proj.scales": "model-00067.safetensors", + "language_model.model.layers.37.mlp.shared_expert.down_proj.biases": "model-00067.safetensors", + "language_model.model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00067.safetensors", + "language_model.model.layers.37.mlp.shared_expert.gate_proj.scales": "model-00067.safetensors", + "language_model.model.layers.37.mlp.shared_expert.gate_proj.biases": "model-00067.safetensors", + "language_model.model.layers.37.mlp.shared_expert.up_proj.weight": "model-00067.safetensors", + "language_model.model.layers.37.mlp.shared_expert.up_proj.scales": "model-00067.safetensors", + "language_model.model.layers.37.mlp.shared_expert.up_proj.biases": "model-00067.safetensors", + "language_model.model.layers.37.mlp.shared_expert_gate.weight": "model-00067.safetensors", + "language_model.model.layers.37.mlp_hyper_connection.block_inject_weight.weight": "model-00067.safetensors", + "language_model.model.layers.37.mlp_hyper_connection.hc_norm.weight": "model-00067.safetensors", + "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_down.weight": "model-00067.safetensors", + "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_down.scales": "model-00067.safetensors", + "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_down.biases": "model-00067.safetensors", + "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_up.weight": "model-00067.safetensors", + "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_up.scales": "model-00067.safetensors", + "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_up.biases": "model-00067.safetensors", + "language_model.model.layers.38.attn_hyper_connection.block_inject_weight.weight": "model-00067.safetensors", + "language_model.model.layers.38.attn_hyper_connection.hc_norm.weight": "model-00067.safetensors", + "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_down.weight": "model-00067.safetensors", + "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_down.scales": "model-00067.safetensors", + "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_down.biases": "model-00067.safetensors", + "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_up.weight": "model-00067.safetensors", + "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_up.scales": "model-00067.safetensors", + "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_up.biases": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.A_log": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.conv1d.weight": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.dt_bias": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.in_proj_a.weight": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.in_proj_a.scales": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.in_proj_a.biases": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.in_proj_b.weight": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.in_proj_b.scales": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.in_proj_b.biases": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.in_proj_qkv.weight": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.in_proj_qkv.scales": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.in_proj_qkv.biases": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.in_proj_z.weight": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.in_proj_z.scales": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.in_proj_z.biases": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.norm.weight": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.out_proj.weight": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.out_proj.scales": "model-00067.safetensors", + "language_model.model.layers.38.linear_attn.out_proj.biases": "model-00067.safetensors", + "language_model.model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00068.safetensors", + "language_model.model.layers.38.mlp.switch_mlp.gate_proj.scales": "model-00068.safetensors", + "language_model.model.layers.38.mlp.switch_mlp.gate_proj.biases": "model-00068.safetensors", + "language_model.model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00068.safetensors", + "language_model.model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00068.safetensors", + "language_model.model.layers.38.mlp.switch_mlp.up_proj.biases": "model-00068.safetensors", + "language_model.model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00069.safetensors", + "language_model.model.layers.38.mlp.switch_mlp.down_proj.scales": "model-00069.safetensors", + "language_model.model.layers.38.mlp.switch_mlp.down_proj.biases": "model-00069.safetensors", + "language_model.model.layers.38.mlp.gate.weight": "model-00069.safetensors", + "language_model.model.layers.38.mlp.gate.scales": "model-00069.safetensors", + "language_model.model.layers.38.mlp.gate.biases": "model-00069.safetensors", + "language_model.model.layers.38.mlp.shared_expert.down_proj.weight": "model-00069.safetensors", + "language_model.model.layers.38.mlp.shared_expert.down_proj.scales": "model-00069.safetensors", + "language_model.model.layers.38.mlp.shared_expert.down_proj.biases": "model-00069.safetensors", + "language_model.model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00069.safetensors", + "language_model.model.layers.38.mlp.shared_expert.gate_proj.scales": "model-00069.safetensors", + "language_model.model.layers.38.mlp.shared_expert.gate_proj.biases": "model-00069.safetensors", + "language_model.model.layers.38.mlp.shared_expert.up_proj.weight": "model-00069.safetensors", + "language_model.model.layers.38.mlp.shared_expert.up_proj.scales": "model-00069.safetensors", + "language_model.model.layers.38.mlp.shared_expert.up_proj.biases": "model-00069.safetensors", + "language_model.model.layers.38.mlp.shared_expert_gate.weight": "model-00069.safetensors", + "language_model.model.layers.38.mlp_hyper_connection.block_inject_weight.weight": "model-00069.safetensors", + "language_model.model.layers.38.mlp_hyper_connection.hc_norm.weight": "model-00069.safetensors", + "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_down.weight": "model-00069.safetensors", + "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_down.scales": "model-00069.safetensors", + "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_down.biases": "model-00069.safetensors", + "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_up.weight": "model-00069.safetensors", + "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_up.scales": "model-00069.safetensors", + "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_up.biases": "model-00069.safetensors", + "language_model.model.layers.39.attn_hyper_connection.block_inject_weight.weight": "model-00069.safetensors", + "language_model.model.layers.39.attn_hyper_connection.hc_norm.weight": "model-00069.safetensors", + "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_down.weight": "model-00069.safetensors", + "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_down.scales": "model-00069.safetensors", + "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_down.biases": "model-00069.safetensors", + "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_up.weight": "model-00069.safetensors", + "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_up.scales": "model-00069.safetensors", + "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_up.biases": "model-00069.safetensors", + "language_model.mtp.layers.0.self_attn.indexer.q_layernorm.weight": "model-00069.safetensors", + "language_model.model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00070.safetensors", + "language_model.model.layers.39.mlp.switch_mlp.gate_proj.scales": "model-00070.safetensors", + "language_model.model.layers.39.mlp.switch_mlp.gate_proj.biases": "model-00070.safetensors", + "language_model.model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00070.safetensors", + "language_model.model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00070.safetensors", + "language_model.model.layers.39.mlp.switch_mlp.up_proj.biases": "model-00070.safetensors", + "language_model.model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00071.safetensors", + "language_model.model.layers.39.mlp.switch_mlp.down_proj.scales": "model-00071.safetensors", + "language_model.model.layers.39.mlp.switch_mlp.down_proj.biases": "model-00071.safetensors", + "language_model.model.layers.39.mlp.gate.weight": "model-00071.safetensors", + "language_model.model.layers.39.mlp.gate.scales": "model-00071.safetensors", + "language_model.model.layers.39.mlp.gate.biases": "model-00071.safetensors", + "language_model.model.layers.39.mlp.shared_expert.down_proj.weight": "model-00071.safetensors", + "language_model.model.layers.39.mlp.shared_expert.down_proj.scales": "model-00071.safetensors", + "language_model.model.layers.39.mlp.shared_expert.down_proj.biases": "model-00071.safetensors", + "language_model.model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00071.safetensors", + "language_model.model.layers.39.mlp.shared_expert.gate_proj.scales": "model-00071.safetensors", + "language_model.model.layers.39.mlp.shared_expert.gate_proj.biases": "model-00071.safetensors", + "language_model.model.layers.39.mlp.shared_expert.up_proj.weight": "model-00071.safetensors", + "language_model.model.layers.39.mlp.shared_expert.up_proj.scales": "model-00071.safetensors", + "language_model.model.layers.39.mlp.shared_expert.up_proj.biases": "model-00071.safetensors", + "language_model.model.layers.39.mlp.shared_expert_gate.weight": "model-00071.safetensors", + "language_model.model.layers.39.mlp_hyper_connection.block_inject_weight.weight": "model-00071.safetensors", + "language_model.model.layers.39.mlp_hyper_connection.hc_norm.weight": "model-00071.safetensors", + "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_down.weight": "model-00071.safetensors", + "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_down.scales": "model-00071.safetensors", + "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_down.biases": "model-00071.safetensors", + "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_up.weight": "model-00071.safetensors", + "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_up.scales": "model-00071.safetensors", + "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_up.biases": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.indexer.index_qk_proj.weight": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.indexer.index_qk_proj.scales": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.indexer.index_qk_proj.biases": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.indexer.k_layernorm.weight": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.indexer.q_layernorm.weight": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.k_norm.weight": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.k_proj.weight": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.k_proj.scales": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.k_proj.biases": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.o_proj.weight": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.o_proj.scales": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.o_proj.biases": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.q_norm.weight": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.q_proj.weight": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.q_proj.scales": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.q_proj.biases": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.v_proj.weight": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.v_proj.scales": "model-00071.safetensors", + "language_model.model.layers.39.self_attn.v_proj.biases": "model-00071.safetensors", + "language_model.model.layers.4.attn_hyper_connection.block_inject_weight.weight": "model-00071.safetensors", + "language_model.model.layers.4.attn_hyper_connection.hc_norm.weight": "model-00071.safetensors", + "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_down.weight": "model-00071.safetensors", + "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_down.scales": "model-00071.safetensors", + "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_down.biases": "model-00071.safetensors", + "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_up.weight": "model-00071.safetensors", + "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_up.scales": "model-00071.safetensors", + "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_up.biases": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.A_log": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.conv1d.weight": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.dt_bias": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.in_proj_a.weight": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.in_proj_a.scales": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.in_proj_a.biases": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.in_proj_b.weight": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.in_proj_b.scales": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.in_proj_b.biases": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.in_proj_qkv.weight": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.in_proj_qkv.scales": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.in_proj_qkv.biases": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.in_proj_z.weight": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.in_proj_z.scales": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.in_proj_z.biases": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.norm.weight": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.out_proj.weight": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.out_proj.scales": "model-00071.safetensors", + "language_model.model.layers.4.linear_attn.out_proj.biases": "model-00071.safetensors", + "language_model.mtp.layers.0.self_attn.k_norm.weight": "model-00071.safetensors", + "language_model.model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00072.safetensors", + "language_model.model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00072.safetensors", + "language_model.model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00072.safetensors", + "language_model.model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00072.safetensors", + "language_model.model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00072.safetensors", + "language_model.model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00072.safetensors", + "language_model.model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00073.safetensors", + "language_model.model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00073.safetensors", + "language_model.model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00073.safetensors", + "language_model.model.layers.4.mlp.gate.weight": "model-00073.safetensors", + "language_model.model.layers.4.mlp.gate.scales": "model-00073.safetensors", + "language_model.model.layers.4.mlp.gate.biases": "model-00073.safetensors", + "language_model.model.layers.4.mlp.shared_expert.down_proj.weight": "model-00073.safetensors", + "language_model.model.layers.4.mlp.shared_expert.down_proj.scales": "model-00073.safetensors", + "language_model.model.layers.4.mlp.shared_expert.down_proj.biases": "model-00073.safetensors", + "language_model.model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00073.safetensors", + "language_model.model.layers.4.mlp.shared_expert.gate_proj.scales": "model-00073.safetensors", + "language_model.model.layers.4.mlp.shared_expert.gate_proj.biases": "model-00073.safetensors", + "language_model.model.layers.4.mlp.shared_expert.up_proj.weight": "model-00073.safetensors", + "language_model.model.layers.4.mlp.shared_expert.up_proj.scales": "model-00073.safetensors", + "language_model.model.layers.4.mlp.shared_expert.up_proj.biases": "model-00073.safetensors", + "language_model.model.layers.4.mlp.shared_expert_gate.weight": "model-00073.safetensors", + "language_model.model.layers.4.mlp_hyper_connection.block_inject_weight.weight": "model-00073.safetensors", + "language_model.model.layers.4.mlp_hyper_connection.hc_norm.weight": "model-00073.safetensors", + "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_down.weight": "model-00073.safetensors", + "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_down.scales": "model-00073.safetensors", + "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_down.biases": "model-00073.safetensors", + "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_up.weight": "model-00073.safetensors", + "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_up.scales": "model-00073.safetensors", + "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_up.biases": "model-00073.safetensors", + "language_model.model.layers.40.attn_hyper_connection.block_inject_weight.weight": "model-00073.safetensors", + "language_model.model.layers.40.attn_hyper_connection.hc_norm.weight": "model-00073.safetensors", + "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_down.weight": "model-00073.safetensors", + "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_down.scales": "model-00073.safetensors", + "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_down.biases": "model-00073.safetensors", + "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_up.weight": "model-00073.safetensors", + "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_up.scales": "model-00073.safetensors", + "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_up.biases": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.A_log": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.conv1d.weight": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.dt_bias": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.in_proj_a.weight": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.in_proj_a.scales": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.in_proj_a.biases": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.in_proj_b.weight": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.in_proj_b.scales": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.in_proj_b.biases": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.in_proj_qkv.weight": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.in_proj_qkv.scales": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.in_proj_qkv.biases": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.in_proj_z.weight": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.in_proj_z.scales": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.in_proj_z.biases": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.norm.weight": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.out_proj.weight": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.out_proj.scales": "model-00073.safetensors", + "language_model.model.layers.40.linear_attn.out_proj.biases": "model-00073.safetensors", + "language_model.model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00074.safetensors", + "language_model.model.layers.40.mlp.switch_mlp.gate_proj.scales": "model-00074.safetensors", + "language_model.model.layers.40.mlp.switch_mlp.gate_proj.biases": "model-00074.safetensors", + "language_model.model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00074.safetensors", + "language_model.model.layers.40.mlp.switch_mlp.up_proj.scales": "model-00074.safetensors", + "language_model.model.layers.40.mlp.switch_mlp.up_proj.biases": "model-00074.safetensors", + "language_model.model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00075.safetensors", + "language_model.model.layers.40.mlp.switch_mlp.down_proj.scales": "model-00075.safetensors", + "language_model.model.layers.40.mlp.switch_mlp.down_proj.biases": "model-00075.safetensors", + "language_model.model.layers.40.mlp.gate.weight": "model-00075.safetensors", + "language_model.model.layers.40.mlp.gate.scales": "model-00075.safetensors", + "language_model.model.layers.40.mlp.gate.biases": "model-00075.safetensors", + "language_model.model.layers.40.mlp.shared_expert.down_proj.weight": "model-00075.safetensors", + "language_model.model.layers.40.mlp.shared_expert.down_proj.scales": "model-00075.safetensors", + "language_model.model.layers.40.mlp.shared_expert.down_proj.biases": "model-00075.safetensors", + "language_model.model.layers.40.mlp.shared_expert.gate_proj.weight": "model-00075.safetensors", + "language_model.model.layers.40.mlp.shared_expert.gate_proj.scales": "model-00075.safetensors", + "language_model.model.layers.40.mlp.shared_expert.gate_proj.biases": "model-00075.safetensors", + "language_model.model.layers.40.mlp.shared_expert.up_proj.weight": "model-00075.safetensors", + "language_model.model.layers.40.mlp.shared_expert.up_proj.scales": "model-00075.safetensors", + "language_model.model.layers.40.mlp.shared_expert.up_proj.biases": "model-00075.safetensors", + "language_model.model.layers.40.mlp.shared_expert_gate.weight": "model-00075.safetensors", + "language_model.model.layers.40.mlp_hyper_connection.block_inject_weight.weight": "model-00075.safetensors", + "language_model.model.layers.40.mlp_hyper_connection.hc_norm.weight": "model-00075.safetensors", + "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_down.weight": "model-00075.safetensors", + "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_down.scales": "model-00075.safetensors", + "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_down.biases": "model-00075.safetensors", + "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_up.weight": "model-00075.safetensors", + "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_up.scales": "model-00075.safetensors", + "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_up.biases": "model-00075.safetensors", + "language_model.model.layers.41.attn_hyper_connection.block_inject_weight.weight": "model-00075.safetensors", + "language_model.model.layers.41.attn_hyper_connection.hc_norm.weight": "model-00075.safetensors", + "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_down.weight": "model-00075.safetensors", + "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_down.scales": "model-00075.safetensors", + "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_down.biases": "model-00075.safetensors", + "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_up.weight": "model-00075.safetensors", + "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_up.scales": "model-00075.safetensors", + "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_up.biases": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.A_log": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.conv1d.weight": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.dt_bias": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.in_proj_a.weight": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.in_proj_a.scales": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.in_proj_a.biases": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.in_proj_b.weight": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.in_proj_b.scales": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.in_proj_b.biases": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.in_proj_qkv.weight": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.in_proj_qkv.scales": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.in_proj_qkv.biases": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.in_proj_z.weight": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.in_proj_z.scales": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.in_proj_z.biases": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.norm.weight": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.out_proj.weight": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.out_proj.scales": "model-00075.safetensors", + "language_model.model.layers.41.linear_attn.out_proj.biases": "model-00075.safetensors", + "language_model.mtp.layers.0.self_attn.o_proj.weight": "model-00075.safetensors", + "language_model.mtp.layers.0.self_attn.o_proj.scales": "model-00075.safetensors", + "language_model.mtp.layers.0.self_attn.o_proj.biases": "model-00075.safetensors", + "language_model.model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00076.safetensors", + "language_model.model.layers.41.mlp.switch_mlp.gate_proj.scales": "model-00076.safetensors", + "language_model.model.layers.41.mlp.switch_mlp.gate_proj.biases": "model-00076.safetensors", + "language_model.model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00076.safetensors", + "language_model.model.layers.41.mlp.switch_mlp.up_proj.scales": "model-00076.safetensors", + "language_model.model.layers.41.mlp.switch_mlp.up_proj.biases": "model-00076.safetensors", + "language_model.model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00077.safetensors", + "language_model.model.layers.41.mlp.switch_mlp.down_proj.scales": "model-00077.safetensors", + "language_model.model.layers.41.mlp.switch_mlp.down_proj.biases": "model-00077.safetensors", + "language_model.model.layers.41.mlp.gate.weight": "model-00077.safetensors", + "language_model.model.layers.41.mlp.gate.scales": "model-00077.safetensors", + "language_model.model.layers.41.mlp.gate.biases": "model-00077.safetensors", + "language_model.model.layers.41.mlp.shared_expert.down_proj.weight": "model-00077.safetensors", + "language_model.model.layers.41.mlp.shared_expert.down_proj.scales": "model-00077.safetensors", + "language_model.model.layers.41.mlp.shared_expert.down_proj.biases": "model-00077.safetensors", + "language_model.model.layers.41.mlp.shared_expert.gate_proj.weight": "model-00077.safetensors", + "language_model.model.layers.41.mlp.shared_expert.gate_proj.scales": "model-00077.safetensors", + "language_model.model.layers.41.mlp.shared_expert.gate_proj.biases": "model-00077.safetensors", + "language_model.model.layers.41.mlp.shared_expert.up_proj.weight": "model-00077.safetensors", + "language_model.model.layers.41.mlp.shared_expert.up_proj.scales": "model-00077.safetensors", + "language_model.model.layers.41.mlp.shared_expert.up_proj.biases": "model-00077.safetensors", + "language_model.model.layers.41.mlp.shared_expert_gate.weight": "model-00077.safetensors", + "language_model.model.layers.41.mlp_hyper_connection.block_inject_weight.weight": "model-00077.safetensors", + "language_model.model.layers.41.mlp_hyper_connection.hc_norm.weight": "model-00077.safetensors", + "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_down.weight": "model-00077.safetensors", + "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_down.scales": "model-00077.safetensors", + "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_down.biases": "model-00077.safetensors", + "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_up.weight": "model-00077.safetensors", + "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_up.scales": "model-00077.safetensors", + "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_up.biases": "model-00077.safetensors", + "language_model.model.layers.42.attn_hyper_connection.block_inject_weight.weight": "model-00077.safetensors", + "language_model.model.layers.42.attn_hyper_connection.hc_norm.weight": "model-00077.safetensors", + "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_down.weight": "model-00077.safetensors", + "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_down.scales": "model-00077.safetensors", + "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_down.biases": "model-00077.safetensors", + "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_up.weight": "model-00077.safetensors", + "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_up.scales": "model-00077.safetensors", + "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_up.biases": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.A_log": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.conv1d.weight": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.dt_bias": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.in_proj_a.weight": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.in_proj_a.scales": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.in_proj_a.biases": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.in_proj_b.weight": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.in_proj_b.scales": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.in_proj_b.biases": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.in_proj_qkv.weight": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.in_proj_qkv.scales": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.in_proj_qkv.biases": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.in_proj_z.weight": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.in_proj_z.scales": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.in_proj_z.biases": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.norm.weight": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.out_proj.weight": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.out_proj.scales": "model-00077.safetensors", + "language_model.model.layers.42.linear_attn.out_proj.biases": "model-00077.safetensors", + "language_model.mtp.layers.0.self_attn.k_proj.weight": "model-00077.safetensors", + "language_model.mtp.layers.0.self_attn.k_proj.scales": "model-00077.safetensors", + "language_model.mtp.layers.0.self_attn.k_proj.biases": "model-00077.safetensors", + "language_model.mtp.layers.0.self_attn.q_proj.weight": "model-00077.safetensors", + "language_model.mtp.layers.0.self_attn.q_proj.scales": "model-00077.safetensors", + "language_model.mtp.layers.0.self_attn.q_proj.biases": "model-00077.safetensors", + "language_model.mtp.layers.0.self_attn.v_proj.weight": "model-00077.safetensors", + "language_model.mtp.layers.0.self_attn.v_proj.scales": "model-00077.safetensors", + "language_model.mtp.layers.0.self_attn.v_proj.biases": "model-00077.safetensors", + "language_model.model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00078.safetensors", + "language_model.model.layers.42.mlp.switch_mlp.gate_proj.scales": "model-00078.safetensors", + "language_model.model.layers.42.mlp.switch_mlp.gate_proj.biases": "model-00078.safetensors", + "language_model.model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00078.safetensors", + "language_model.model.layers.42.mlp.switch_mlp.up_proj.scales": "model-00078.safetensors", + "language_model.model.layers.42.mlp.switch_mlp.up_proj.biases": "model-00078.safetensors", + "language_model.model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00079.safetensors", + "language_model.model.layers.42.mlp.switch_mlp.down_proj.scales": "model-00079.safetensors", + "language_model.model.layers.42.mlp.switch_mlp.down_proj.biases": "model-00079.safetensors", + "language_model.model.layers.42.mlp.gate.weight": "model-00079.safetensors", + "language_model.model.layers.42.mlp.gate.scales": "model-00079.safetensors", + "language_model.model.layers.42.mlp.gate.biases": "model-00079.safetensors", + "language_model.model.layers.42.mlp.shared_expert.down_proj.weight": "model-00079.safetensors", + "language_model.model.layers.42.mlp.shared_expert.down_proj.scales": "model-00079.safetensors", + "language_model.model.layers.42.mlp.shared_expert.down_proj.biases": "model-00079.safetensors", + "language_model.model.layers.42.mlp.shared_expert.gate_proj.weight": "model-00079.safetensors", + "language_model.model.layers.42.mlp.shared_expert.gate_proj.scales": "model-00079.safetensors", + "language_model.model.layers.42.mlp.shared_expert.gate_proj.biases": "model-00079.safetensors", + "language_model.model.layers.42.mlp.shared_expert.up_proj.weight": "model-00079.safetensors", + "language_model.model.layers.42.mlp.shared_expert.up_proj.scales": "model-00079.safetensors", + "language_model.model.layers.42.mlp.shared_expert.up_proj.biases": "model-00079.safetensors", + "language_model.model.layers.42.mlp.shared_expert_gate.weight": "model-00079.safetensors", + "language_model.model.layers.42.mlp_hyper_connection.block_inject_weight.weight": "model-00079.safetensors", + "language_model.model.layers.42.mlp_hyper_connection.hc_norm.weight": "model-00079.safetensors", + "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_down.weight": "model-00079.safetensors", + "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_down.scales": "model-00079.safetensors", + "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_down.biases": "model-00079.safetensors", + "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_up.weight": "model-00079.safetensors", + "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_up.scales": "model-00079.safetensors", + "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_up.biases": "model-00079.safetensors", + "language_model.model.layers.43.attn_hyper_connection.block_inject_weight.weight": "model-00079.safetensors", + "language_model.model.layers.43.attn_hyper_connection.hc_norm.weight": "model-00079.safetensors", + "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_down.weight": "model-00079.safetensors", + "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_down.scales": "model-00079.safetensors", + "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_down.biases": "model-00079.safetensors", + "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_up.weight": "model-00079.safetensors", + "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_up.scales": "model-00079.safetensors", + "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_up.biases": "model-00079.safetensors", + "language_model.model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00080.safetensors", + "language_model.model.layers.43.mlp.switch_mlp.gate_proj.scales": "model-00080.safetensors", + "language_model.model.layers.43.mlp.switch_mlp.gate_proj.biases": "model-00080.safetensors", + "language_model.model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00080.safetensors", + "language_model.model.layers.43.mlp.switch_mlp.up_proj.scales": "model-00080.safetensors", + "language_model.model.layers.43.mlp.switch_mlp.up_proj.biases": "model-00080.safetensors", + "language_model.model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00081.safetensors", + "language_model.model.layers.43.mlp.switch_mlp.down_proj.scales": "model-00081.safetensors", + "language_model.model.layers.43.mlp.switch_mlp.down_proj.biases": "model-00081.safetensors", + "language_model.model.layers.43.mlp.gate.weight": "model-00081.safetensors", + "language_model.model.layers.43.mlp.gate.scales": "model-00081.safetensors", + "language_model.model.layers.43.mlp.gate.biases": "model-00081.safetensors", + "language_model.model.layers.43.mlp.shared_expert.down_proj.weight": "model-00081.safetensors", + "language_model.model.layers.43.mlp.shared_expert.down_proj.scales": "model-00081.safetensors", + "language_model.model.layers.43.mlp.shared_expert.down_proj.biases": "model-00081.safetensors", + "language_model.model.layers.43.mlp.shared_expert.gate_proj.weight": "model-00081.safetensors", + "language_model.model.layers.43.mlp.shared_expert.gate_proj.scales": "model-00081.safetensors", + "language_model.model.layers.43.mlp.shared_expert.gate_proj.biases": "model-00081.safetensors", + "language_model.model.layers.43.mlp.shared_expert.up_proj.weight": "model-00081.safetensors", + "language_model.model.layers.43.mlp.shared_expert.up_proj.scales": "model-00081.safetensors", + "language_model.model.layers.43.mlp.shared_expert.up_proj.biases": "model-00081.safetensors", + "language_model.model.layers.43.mlp.shared_expert_gate.weight": "model-00081.safetensors", + "language_model.model.layers.43.mlp_hyper_connection.block_inject_weight.weight": "model-00081.safetensors", + "language_model.model.layers.43.mlp_hyper_connection.hc_norm.weight": "model-00081.safetensors", + "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_down.weight": "model-00081.safetensors", + "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_down.scales": "model-00081.safetensors", + "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_down.biases": "model-00081.safetensors", + "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_up.weight": "model-00081.safetensors", + "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_up.scales": "model-00081.safetensors", + "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_up.biases": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.indexer.index_qk_proj.weight": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.indexer.index_qk_proj.scales": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.indexer.index_qk_proj.biases": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.indexer.k_layernorm.weight": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.indexer.q_layernorm.weight": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.k_norm.weight": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.k_proj.weight": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.k_proj.scales": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.k_proj.biases": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.o_proj.weight": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.o_proj.scales": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.o_proj.biases": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.q_norm.weight": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.q_proj.weight": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.q_proj.scales": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.q_proj.biases": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.v_proj.weight": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.v_proj.scales": "model-00081.safetensors", + "language_model.model.layers.43.self_attn.v_proj.biases": "model-00081.safetensors", + "language_model.model.layers.44.attn_hyper_connection.block_inject_weight.weight": "model-00081.safetensors", + "language_model.model.layers.44.attn_hyper_connection.hc_norm.weight": "model-00081.safetensors", + "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_down.weight": "model-00081.safetensors", + "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_down.scales": "model-00081.safetensors", + "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_down.biases": "model-00081.safetensors", + "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_up.weight": "model-00081.safetensors", + "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_up.scales": "model-00081.safetensors", + "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_up.biases": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.A_log": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.conv1d.weight": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.dt_bias": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.in_proj_a.weight": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.in_proj_a.scales": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.in_proj_a.biases": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.in_proj_b.weight": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.in_proj_b.scales": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.in_proj_b.biases": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.in_proj_qkv.weight": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.in_proj_qkv.scales": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.in_proj_qkv.biases": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.in_proj_z.weight": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.in_proj_z.scales": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.in_proj_z.biases": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.norm.weight": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.out_proj.weight": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.out_proj.scales": "model-00081.safetensors", + "language_model.model.layers.44.linear_attn.out_proj.biases": "model-00081.safetensors", + "language_model.mtp.layers.0.self_attn.q_norm.weight": "model-00081.safetensors", + "language_model.model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00082.safetensors", + "language_model.model.layers.44.mlp.switch_mlp.gate_proj.scales": "model-00082.safetensors", + "language_model.model.layers.44.mlp.switch_mlp.gate_proj.biases": "model-00082.safetensors", + "language_model.model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00082.safetensors", + "language_model.model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00082.safetensors", + "language_model.model.layers.44.mlp.switch_mlp.up_proj.biases": "model-00082.safetensors", + "language_model.model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00083.safetensors", + "language_model.model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00083.safetensors", + "language_model.model.layers.44.mlp.switch_mlp.down_proj.biases": "model-00083.safetensors", + "language_model.model.layers.44.mlp.gate.weight": "model-00083.safetensors", + "language_model.model.layers.44.mlp.gate.scales": "model-00083.safetensors", + "language_model.model.layers.44.mlp.gate.biases": "model-00083.safetensors", + "language_model.model.layers.44.mlp.shared_expert.down_proj.weight": "model-00083.safetensors", + "language_model.model.layers.44.mlp.shared_expert.down_proj.scales": "model-00083.safetensors", + "language_model.model.layers.44.mlp.shared_expert.down_proj.biases": "model-00083.safetensors", + "language_model.model.layers.44.mlp.shared_expert.gate_proj.weight": "model-00083.safetensors", + "language_model.model.layers.44.mlp.shared_expert.gate_proj.scales": "model-00083.safetensors", + "language_model.model.layers.44.mlp.shared_expert.gate_proj.biases": "model-00083.safetensors", + "language_model.model.layers.44.mlp.shared_expert.up_proj.weight": "model-00083.safetensors", + "language_model.model.layers.44.mlp.shared_expert.up_proj.scales": "model-00083.safetensors", + "language_model.model.layers.44.mlp.shared_expert.up_proj.biases": "model-00083.safetensors", + "language_model.model.layers.44.mlp.shared_expert_gate.weight": "model-00083.safetensors", + "language_model.model.layers.44.mlp_hyper_connection.block_inject_weight.weight": "model-00083.safetensors", + "language_model.model.layers.44.mlp_hyper_connection.hc_norm.weight": "model-00083.safetensors", + "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_down.weight": "model-00083.safetensors", + "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_down.scales": "model-00083.safetensors", + "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_down.biases": "model-00083.safetensors", + "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_up.weight": "model-00083.safetensors", + "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_up.scales": "model-00083.safetensors", + "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_up.biases": "model-00083.safetensors", + "language_model.model.layers.45.attn_hyper_connection.block_inject_weight.weight": "model-00083.safetensors", + "language_model.model.layers.45.attn_hyper_connection.hc_norm.weight": "model-00083.safetensors", + "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_down.weight": "model-00083.safetensors", + "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_down.scales": "model-00083.safetensors", + "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_down.biases": "model-00083.safetensors", + "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_up.weight": "model-00083.safetensors", + "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_up.scales": "model-00083.safetensors", + "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_up.biases": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.A_log": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.conv1d.weight": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.dt_bias": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.in_proj_a.weight": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.in_proj_a.scales": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.in_proj_a.biases": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.in_proj_b.weight": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.in_proj_b.scales": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.in_proj_b.biases": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.in_proj_qkv.weight": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.in_proj_qkv.scales": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.in_proj_qkv.biases": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.in_proj_z.weight": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.in_proj_z.scales": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.in_proj_z.biases": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.norm.weight": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.out_proj.weight": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.out_proj.scales": "model-00083.safetensors", + "language_model.model.layers.45.linear_attn.out_proj.biases": "model-00083.safetensors", + "language_model.mtp.pre_fc_norm_embedding.weight": "model-00083.safetensors", + "language_model.model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00084.safetensors", + "language_model.model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00084.safetensors", + "language_model.model.layers.45.mlp.switch_mlp.gate_proj.biases": "model-00084.safetensors", + "language_model.model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00084.safetensors", + "language_model.model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00084.safetensors", + "language_model.model.layers.45.mlp.switch_mlp.up_proj.biases": "model-00084.safetensors", + "language_model.model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00085.safetensors", + "language_model.model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00085.safetensors", + "language_model.model.layers.45.mlp.switch_mlp.down_proj.biases": "model-00085.safetensors", + "language_model.model.layers.45.mlp.gate.weight": "model-00085.safetensors", + "language_model.model.layers.45.mlp.gate.scales": "model-00085.safetensors", + "language_model.model.layers.45.mlp.gate.biases": "model-00085.safetensors", + "language_model.model.layers.45.mlp.shared_expert.down_proj.weight": "model-00085.safetensors", + "language_model.model.layers.45.mlp.shared_expert.down_proj.scales": "model-00085.safetensors", + "language_model.model.layers.45.mlp.shared_expert.down_proj.biases": "model-00085.safetensors", + "language_model.model.layers.45.mlp.shared_expert.gate_proj.weight": "model-00085.safetensors", + "language_model.model.layers.45.mlp.shared_expert.gate_proj.scales": "model-00085.safetensors", + "language_model.model.layers.45.mlp.shared_expert.gate_proj.biases": "model-00085.safetensors", + "language_model.model.layers.45.mlp.shared_expert.up_proj.weight": "model-00085.safetensors", + "language_model.model.layers.45.mlp.shared_expert.up_proj.scales": "model-00085.safetensors", + "language_model.model.layers.45.mlp.shared_expert.up_proj.biases": "model-00085.safetensors", + "language_model.model.layers.45.mlp.shared_expert_gate.weight": "model-00085.safetensors", + "language_model.model.layers.45.mlp_hyper_connection.block_inject_weight.weight": "model-00085.safetensors", + "language_model.model.layers.45.mlp_hyper_connection.hc_norm.weight": "model-00085.safetensors", + "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_down.weight": "model-00085.safetensors", + "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_down.scales": "model-00085.safetensors", + "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_down.biases": "model-00085.safetensors", + "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_up.weight": "model-00085.safetensors", + "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_up.scales": "model-00085.safetensors", + "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_up.biases": "model-00085.safetensors", + "language_model.model.layers.46.attn_hyper_connection.block_inject_weight.weight": "model-00085.safetensors", + "language_model.model.layers.46.attn_hyper_connection.hc_norm.weight": "model-00085.safetensors", + "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_down.weight": "model-00085.safetensors", + "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_down.scales": "model-00085.safetensors", + "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_down.biases": "model-00085.safetensors", + "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_up.weight": "model-00085.safetensors", + "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_up.scales": "model-00085.safetensors", + "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_up.biases": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.A_log": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.conv1d.weight": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.dt_bias": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.in_proj_a.weight": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.in_proj_a.scales": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.in_proj_a.biases": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.in_proj_b.weight": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.in_proj_b.scales": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.in_proj_b.biases": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.in_proj_qkv.weight": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.in_proj_qkv.scales": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.in_proj_qkv.biases": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.in_proj_z.weight": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.in_proj_z.scales": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.in_proj_z.biases": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.norm.weight": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.out_proj.weight": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.out_proj.scales": "model-00085.safetensors", + "language_model.model.layers.46.linear_attn.out_proj.biases": "model-00085.safetensors", + "language_model.model.layers.46.mlp.switch_mlp.gate_proj.weight": "model-00086.safetensors", + "language_model.model.layers.46.mlp.switch_mlp.gate_proj.scales": "model-00086.safetensors", + "language_model.model.layers.46.mlp.switch_mlp.gate_proj.biases": "model-00086.safetensors", + "language_model.model.layers.46.mlp.switch_mlp.up_proj.weight": "model-00086.safetensors", + "language_model.model.layers.46.mlp.switch_mlp.up_proj.scales": "model-00086.safetensors", + "language_model.model.layers.46.mlp.switch_mlp.up_proj.biases": "model-00086.safetensors", + "language_model.model.layers.46.mlp.switch_mlp.down_proj.weight": "model-00087.safetensors", + "language_model.model.layers.46.mlp.switch_mlp.down_proj.scales": "model-00087.safetensors", + "language_model.model.layers.46.mlp.switch_mlp.down_proj.biases": "model-00087.safetensors", + "language_model.model.layers.46.mlp.gate.weight": "model-00087.safetensors", + "language_model.model.layers.46.mlp.gate.scales": "model-00087.safetensors", + "language_model.model.layers.46.mlp.gate.biases": "model-00087.safetensors", + "language_model.model.layers.46.mlp.shared_expert.down_proj.weight": "model-00087.safetensors", + "language_model.model.layers.46.mlp.shared_expert.down_proj.scales": "model-00087.safetensors", + "language_model.model.layers.46.mlp.shared_expert.down_proj.biases": "model-00087.safetensors", + "language_model.model.layers.46.mlp.shared_expert.gate_proj.weight": "model-00087.safetensors", + "language_model.model.layers.46.mlp.shared_expert.gate_proj.scales": "model-00087.safetensors", + "language_model.model.layers.46.mlp.shared_expert.gate_proj.biases": "model-00087.safetensors", + "language_model.model.layers.46.mlp.shared_expert.up_proj.weight": "model-00087.safetensors", + "language_model.model.layers.46.mlp.shared_expert.up_proj.scales": "model-00087.safetensors", + "language_model.model.layers.46.mlp.shared_expert.up_proj.biases": "model-00087.safetensors", + "language_model.model.layers.46.mlp.shared_expert_gate.weight": "model-00087.safetensors", + "language_model.model.layers.46.mlp_hyper_connection.block_inject_weight.weight": "model-00087.safetensors", + "language_model.model.layers.46.mlp_hyper_connection.hc_norm.weight": "model-00087.safetensors", + "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_down.weight": "model-00087.safetensors", + "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_down.scales": "model-00087.safetensors", + "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_down.biases": "model-00087.safetensors", + "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_up.weight": "model-00087.safetensors", + "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_up.scales": "model-00087.safetensors", + "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_up.biases": "model-00087.safetensors", + "language_model.model.layers.47.attn_hyper_connection.block_inject_weight.weight": "model-00087.safetensors", + "language_model.model.layers.47.attn_hyper_connection.hc_norm.weight": "model-00087.safetensors", + "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_down.weight": "model-00087.safetensors", + "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_down.scales": "model-00087.safetensors", + "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_down.biases": "model-00087.safetensors", + "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_up.weight": "model-00087.safetensors", + "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_up.scales": "model-00087.safetensors", + "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_up.biases": "model-00087.safetensors", + "language_model.mtp.pre_fc_norm_hidden.weight": "model-00087.safetensors", + "language_model.model.layers.47.mlp.switch_mlp.gate_proj.weight": "model-00088.safetensors", + "language_model.model.layers.47.mlp.switch_mlp.gate_proj.scales": "model-00088.safetensors", + "language_model.model.layers.47.mlp.switch_mlp.gate_proj.biases": "model-00088.safetensors", + "language_model.model.layers.47.mlp.switch_mlp.up_proj.weight": "model-00088.safetensors", + "language_model.model.layers.47.mlp.switch_mlp.up_proj.scales": "model-00088.safetensors", + "language_model.model.layers.47.mlp.switch_mlp.up_proj.biases": "model-00088.safetensors", + "language_model.model.layers.47.mlp.switch_mlp.down_proj.weight": "model-00089.safetensors", + "language_model.model.layers.47.mlp.switch_mlp.down_proj.scales": "model-00089.safetensors", + "language_model.model.layers.47.mlp.switch_mlp.down_proj.biases": "model-00089.safetensors", + "language_model.model.layers.47.mlp.gate.weight": "model-00089.safetensors", + "language_model.model.layers.47.mlp.gate.scales": "model-00089.safetensors", + "language_model.model.layers.47.mlp.gate.biases": "model-00089.safetensors", + "language_model.model.layers.47.mlp.shared_expert.down_proj.weight": "model-00089.safetensors", + "language_model.model.layers.47.mlp.shared_expert.down_proj.scales": "model-00089.safetensors", + "language_model.model.layers.47.mlp.shared_expert.down_proj.biases": "model-00089.safetensors", + "language_model.model.layers.47.mlp.shared_expert.gate_proj.weight": "model-00089.safetensors", + "language_model.model.layers.47.mlp.shared_expert.gate_proj.scales": "model-00089.safetensors", + "language_model.model.layers.47.mlp.shared_expert.gate_proj.biases": "model-00089.safetensors", + "language_model.model.layers.47.mlp.shared_expert.up_proj.weight": "model-00089.safetensors", + "language_model.model.layers.47.mlp.shared_expert.up_proj.scales": "model-00089.safetensors", + "language_model.model.layers.47.mlp.shared_expert.up_proj.biases": "model-00089.safetensors", + "language_model.model.layers.47.mlp.shared_expert_gate.weight": "model-00089.safetensors", + "language_model.model.layers.47.mlp_hyper_connection.block_inject_weight.weight": "model-00089.safetensors", + "language_model.model.layers.47.mlp_hyper_connection.hc_norm.weight": "model-00089.safetensors", + "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_down.weight": "model-00089.safetensors", + "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_down.scales": "model-00089.safetensors", + "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_down.biases": "model-00089.safetensors", + "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_up.weight": "model-00089.safetensors", + "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_up.scales": "model-00089.safetensors", + "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_up.biases": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.indexer.index_qk_proj.weight": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.indexer.index_qk_proj.scales": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.indexer.index_qk_proj.biases": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.indexer.k_layernorm.weight": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.indexer.q_layernorm.weight": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.k_norm.weight": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.k_proj.weight": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.k_proj.scales": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.k_proj.biases": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.o_proj.weight": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.o_proj.scales": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.o_proj.biases": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.q_norm.weight": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.q_proj.weight": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.q_proj.scales": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.q_proj.biases": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.v_proj.weight": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.v_proj.scales": "model-00089.safetensors", + "language_model.model.layers.47.self_attn.v_proj.biases": "model-00089.safetensors", + "language_model.model.layers.5.attn_hyper_connection.block_inject_weight.weight": "model-00089.safetensors", + "language_model.model.layers.5.attn_hyper_connection.hc_norm.weight": "model-00089.safetensors", + "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_down.weight": "model-00089.safetensors", + "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_down.scales": "model-00089.safetensors", + "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_down.biases": "model-00089.safetensors", + "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_up.weight": "model-00089.safetensors", + "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_up.scales": "model-00089.safetensors", + "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_up.biases": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.A_log": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.conv1d.weight": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.dt_bias": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.in_proj_a.weight": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.in_proj_a.scales": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.in_proj_a.biases": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.in_proj_b.weight": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.in_proj_b.scales": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.in_proj_b.biases": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.in_proj_qkv.weight": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.in_proj_qkv.scales": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.in_proj_qkv.biases": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.in_proj_z.weight": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.in_proj_z.scales": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.in_proj_z.biases": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.norm.weight": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.out_proj.weight": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.out_proj.scales": "model-00089.safetensors", + "language_model.model.layers.5.linear_attn.out_proj.biases": "model-00089.safetensors", + "language_model.mtp.fc_embedding.weight": "model-00089.safetensors", + "language_model.mtp.fc_embedding.scales": "model-00089.safetensors", + "language_model.mtp.fc_embedding.biases": "model-00089.safetensors", + "language_model.model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00090.safetensors", + "language_model.model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00090.safetensors", + "language_model.model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00090.safetensors", + "language_model.model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00090.safetensors", + "language_model.model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00090.safetensors", + "language_model.model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00090.safetensors", + "language_model.model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00091.safetensors", + "language_model.model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00091.safetensors", + "language_model.model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00091.safetensors", + "language_model.model.layers.5.mlp.gate.weight": "model-00091.safetensors", + "language_model.model.layers.5.mlp.gate.scales": "model-00091.safetensors", + "language_model.model.layers.5.mlp.gate.biases": "model-00091.safetensors", + "language_model.model.layers.5.mlp.shared_expert.down_proj.weight": "model-00091.safetensors", + "language_model.model.layers.5.mlp.shared_expert.down_proj.scales": "model-00091.safetensors", + "language_model.model.layers.5.mlp.shared_expert.down_proj.biases": "model-00091.safetensors", + "language_model.model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00091.safetensors", + "language_model.model.layers.5.mlp.shared_expert.gate_proj.scales": "model-00091.safetensors", + "language_model.model.layers.5.mlp.shared_expert.gate_proj.biases": "model-00091.safetensors", + "language_model.model.layers.5.mlp.shared_expert.up_proj.weight": "model-00091.safetensors", + "language_model.model.layers.5.mlp.shared_expert.up_proj.scales": "model-00091.safetensors", + "language_model.model.layers.5.mlp.shared_expert.up_proj.biases": "model-00091.safetensors", + "language_model.model.layers.5.mlp.shared_expert_gate.weight": "model-00091.safetensors", + "language_model.model.layers.5.mlp_hyper_connection.block_inject_weight.weight": "model-00091.safetensors", + "language_model.model.layers.5.mlp_hyper_connection.hc_norm.weight": "model-00091.safetensors", + "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_down.weight": "model-00091.safetensors", + "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_down.scales": "model-00091.safetensors", + "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_down.biases": "model-00091.safetensors", + "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_up.weight": "model-00091.safetensors", + "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_up.scales": "model-00091.safetensors", + "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_up.biases": "model-00091.safetensors", + "language_model.model.layers.6.attn_hyper_connection.block_inject_weight.weight": "model-00091.safetensors", + "language_model.model.layers.6.attn_hyper_connection.hc_norm.weight": "model-00091.safetensors", + "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_down.weight": "model-00091.safetensors", + "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_down.scales": "model-00091.safetensors", + "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_down.biases": "model-00091.safetensors", + "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_up.weight": "model-00091.safetensors", + "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_up.scales": "model-00091.safetensors", + "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_up.biases": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.A_log": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.conv1d.weight": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.dt_bias": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.in_proj_a.weight": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.in_proj_a.scales": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.in_proj_a.biases": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.in_proj_b.weight": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.in_proj_b.scales": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.in_proj_b.biases": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.in_proj_qkv.weight": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.in_proj_qkv.scales": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.in_proj_qkv.biases": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.in_proj_z.weight": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.in_proj_z.scales": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.in_proj_z.biases": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.norm.weight": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.out_proj.weight": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.out_proj.scales": "model-00091.safetensors", + "language_model.model.layers.6.linear_attn.out_proj.biases": "model-00091.safetensors", + "language_model.model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00092.safetensors", + "language_model.model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00092.safetensors", + "language_model.model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00092.safetensors", + "language_model.model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00092.safetensors", + "language_model.model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00092.safetensors", + "language_model.model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00092.safetensors", + "language_model.model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00093.safetensors", + "language_model.model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00093.safetensors", + "language_model.model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00093.safetensors", + "language_model.model.layers.6.mlp.gate.weight": "model-00093.safetensors", + "language_model.model.layers.6.mlp.gate.scales": "model-00093.safetensors", + "language_model.model.layers.6.mlp.gate.biases": "model-00093.safetensors", + "language_model.model.layers.6.mlp.shared_expert.down_proj.weight": "model-00093.safetensors", + "language_model.model.layers.6.mlp.shared_expert.down_proj.scales": "model-00093.safetensors", + "language_model.model.layers.6.mlp.shared_expert.down_proj.biases": "model-00093.safetensors", + "language_model.model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00093.safetensors", + "language_model.model.layers.6.mlp.shared_expert.gate_proj.scales": "model-00093.safetensors", + "language_model.model.layers.6.mlp.shared_expert.gate_proj.biases": "model-00093.safetensors", + "language_model.model.layers.6.mlp.shared_expert.up_proj.weight": "model-00093.safetensors", + "language_model.model.layers.6.mlp.shared_expert.up_proj.scales": "model-00093.safetensors", + "language_model.model.layers.6.mlp.shared_expert.up_proj.biases": "model-00093.safetensors", + "language_model.model.layers.6.mlp.shared_expert_gate.weight": "model-00093.safetensors", + "language_model.model.layers.6.mlp_hyper_connection.block_inject_weight.weight": "model-00093.safetensors", + "language_model.model.layers.6.mlp_hyper_connection.hc_norm.weight": "model-00093.safetensors", + "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_down.weight": "model-00093.safetensors", + "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_down.scales": "model-00093.safetensors", + "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_down.biases": "model-00093.safetensors", + "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_up.weight": "model-00093.safetensors", + "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_up.scales": "model-00093.safetensors", + "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_up.biases": "model-00093.safetensors", + "language_model.model.layers.7.attn_hyper_connection.block_inject_weight.weight": "model-00093.safetensors", + "language_model.model.layers.7.attn_hyper_connection.hc_norm.weight": "model-00093.safetensors", + "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_down.weight": "model-00093.safetensors", + "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_down.scales": "model-00093.safetensors", + "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_down.biases": "model-00093.safetensors", + "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_up.weight": "model-00093.safetensors", + "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_up.scales": "model-00093.safetensors", + "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_up.biases": "model-00093.safetensors", + "language_model.mtp.fc_hidden.weight": "model-00093.safetensors", + "language_model.mtp.fc_hidden.scales": "model-00093.safetensors", + "language_model.mtp.fc_hidden.biases": "model-00093.safetensors", + "language_model.model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00094.safetensors", + "language_model.model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00094.safetensors", + "language_model.model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00094.safetensors", + "language_model.model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00094.safetensors", + "language_model.model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00094.safetensors", + "language_model.model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00094.safetensors", + "language_model.model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00095.safetensors", + "language_model.model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00095.safetensors", + "language_model.model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00095.safetensors", + "language_model.model.layers.7.mlp.gate.weight": "model-00095.safetensors", + "language_model.model.layers.7.mlp.gate.scales": "model-00095.safetensors", + "language_model.model.layers.7.mlp.gate.biases": "model-00095.safetensors", + "language_model.model.layers.7.mlp.shared_expert.down_proj.weight": "model-00095.safetensors", + "language_model.model.layers.7.mlp.shared_expert.down_proj.scales": "model-00095.safetensors", + "language_model.model.layers.7.mlp.shared_expert.down_proj.biases": "model-00095.safetensors", + "language_model.model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00095.safetensors", + "language_model.model.layers.7.mlp.shared_expert.gate_proj.scales": "model-00095.safetensors", + "language_model.model.layers.7.mlp.shared_expert.gate_proj.biases": "model-00095.safetensors", + "language_model.model.layers.7.mlp.shared_expert.up_proj.weight": "model-00095.safetensors", + "language_model.model.layers.7.mlp.shared_expert.up_proj.scales": "model-00095.safetensors", + "language_model.model.layers.7.mlp.shared_expert.up_proj.biases": "model-00095.safetensors", + "language_model.model.layers.7.mlp.shared_expert_gate.weight": "model-00095.safetensors", + "language_model.model.layers.7.mlp_hyper_connection.block_inject_weight.weight": "model-00095.safetensors", + "language_model.model.layers.7.mlp_hyper_connection.hc_norm.weight": "model-00095.safetensors", + "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_down.weight": "model-00095.safetensors", + "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_down.scales": "model-00095.safetensors", + "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_down.biases": "model-00095.safetensors", + "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_up.weight": "model-00095.safetensors", + "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_up.scales": "model-00095.safetensors", + "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_up.biases": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.indexer.index_qk_proj.weight": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.indexer.index_qk_proj.scales": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.indexer.index_qk_proj.biases": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.indexer.k_layernorm.weight": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.indexer.q_layernorm.weight": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.k_norm.weight": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.k_proj.weight": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.k_proj.scales": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.k_proj.biases": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.o_proj.weight": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.o_proj.scales": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.o_proj.biases": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.q_norm.weight": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.q_proj.weight": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.q_proj.scales": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.q_proj.biases": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.v_proj.weight": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.v_proj.scales": "model-00095.safetensors", + "language_model.model.layers.7.self_attn.v_proj.biases": "model-00095.safetensors", + "language_model.model.layers.8.attn_hyper_connection.block_inject_weight.weight": "model-00095.safetensors", + "language_model.model.layers.8.attn_hyper_connection.hc_norm.weight": "model-00095.safetensors", + "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_down.weight": "model-00095.safetensors", + "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_down.scales": "model-00095.safetensors", + "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_down.biases": "model-00095.safetensors", + "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_up.weight": "model-00095.safetensors", + "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_up.scales": "model-00095.safetensors", + "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_up.biases": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.A_log": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.conv1d.weight": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.dt_bias": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.in_proj_a.weight": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.in_proj_a.scales": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.in_proj_a.biases": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.in_proj_b.weight": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.in_proj_b.scales": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.in_proj_b.biases": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.in_proj_qkv.scales": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.in_proj_qkv.biases": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.in_proj_z.weight": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.in_proj_z.scales": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.in_proj_z.biases": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.norm.weight": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.out_proj.weight": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.out_proj.scales": "model-00095.safetensors", + "language_model.model.layers.8.linear_attn.out_proj.biases": "model-00095.safetensors", + "language_model.model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00096.safetensors", + "language_model.model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00096.safetensors", + "language_model.model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00096.safetensors", + "language_model.model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00096.safetensors", + "language_model.model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00096.safetensors", + "language_model.model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00096.safetensors", + "language_model.model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00097.safetensors", + "language_model.model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00097.safetensors", + "language_model.model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00097.safetensors", + "language_model.model.layers.8.mlp.gate.weight": "model-00097.safetensors", + "language_model.model.layers.8.mlp.gate.scales": "model-00097.safetensors", + "language_model.model.layers.8.mlp.gate.biases": "model-00097.safetensors", + "language_model.model.layers.8.mlp.shared_expert.down_proj.weight": "model-00097.safetensors", + "language_model.model.layers.8.mlp.shared_expert.down_proj.scales": "model-00097.safetensors", + "language_model.model.layers.8.mlp.shared_expert.down_proj.biases": "model-00097.safetensors", + "language_model.model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00097.safetensors", + "language_model.model.layers.8.mlp.shared_expert.gate_proj.scales": "model-00097.safetensors", + "language_model.model.layers.8.mlp.shared_expert.gate_proj.biases": "model-00097.safetensors", + "language_model.model.layers.8.mlp.shared_expert.up_proj.weight": "model-00097.safetensors", + "language_model.model.layers.8.mlp.shared_expert.up_proj.scales": "model-00097.safetensors", + "language_model.model.layers.8.mlp.shared_expert.up_proj.biases": "model-00097.safetensors", + "language_model.model.layers.8.mlp.shared_expert_gate.weight": "model-00097.safetensors", + "language_model.model.layers.8.mlp_hyper_connection.block_inject_weight.weight": "model-00097.safetensors", + "language_model.model.layers.8.mlp_hyper_connection.hc_norm.weight": "model-00097.safetensors", + "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_down.weight": "model-00097.safetensors", + "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_down.scales": "model-00097.safetensors", + "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_down.biases": "model-00097.safetensors", + "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_up.weight": "model-00097.safetensors", + "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_up.scales": "model-00097.safetensors", + "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_up.biases": "model-00097.safetensors", + "language_model.model.layers.9.attn_hyper_connection.block_inject_weight.weight": "model-00097.safetensors", + "language_model.model.layers.9.attn_hyper_connection.hc_norm.weight": "model-00097.safetensors", + "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_down.weight": "model-00097.safetensors", + "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_down.scales": "model-00097.safetensors", + "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_down.biases": "model-00097.safetensors", + "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_up.weight": "model-00097.safetensors", + "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_up.scales": "model-00097.safetensors", + "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_up.biases": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.A_log": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.conv1d.weight": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.dt_bias": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.in_proj_a.weight": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.in_proj_a.scales": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.in_proj_a.biases": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.in_proj_b.weight": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.in_proj_b.scales": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.in_proj_b.biases": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.in_proj_qkv.weight": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.in_proj_qkv.scales": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.in_proj_qkv.biases": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.in_proj_z.weight": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.in_proj_z.scales": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.in_proj_z.biases": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.norm.weight": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.out_proj.weight": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.out_proj.scales": "model-00097.safetensors", + "language_model.model.layers.9.linear_attn.out_proj.biases": "model-00097.safetensors", + "language_model.model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00098.safetensors", + "language_model.model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00098.safetensors", + "language_model.model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00098.safetensors", + "language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00098.safetensors", + "language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00098.safetensors", + "language_model.model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00098.safetensors", + "language_model.model.embed_tokens.weight": "model-00099.safetensors", + "language_model.model.embed_tokens.scales": "model-00099.safetensors", + "language_model.model.embed_tokens.biases": "model-00099.safetensors", + "language_model.model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00099.safetensors", + "language_model.model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00099.safetensors", + "language_model.model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00099.safetensors", + "language_model.model.layers.9.mlp.gate.weight": "model-00099.safetensors", + "language_model.model.layers.9.mlp.gate.scales": "model-00099.safetensors", + "language_model.model.layers.9.mlp.gate.biases": "model-00099.safetensors", + "language_model.model.layers.9.mlp.shared_expert.down_proj.weight": "model-00099.safetensors", + "language_model.model.layers.9.mlp.shared_expert.down_proj.scales": "model-00099.safetensors", + "language_model.model.layers.9.mlp.shared_expert.down_proj.biases": "model-00099.safetensors", + "language_model.model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00099.safetensors", + "language_model.model.layers.9.mlp.shared_expert.gate_proj.scales": "model-00099.safetensors", + "language_model.model.layers.9.mlp.shared_expert.gate_proj.biases": "model-00099.safetensors", + "language_model.model.layers.9.mlp.shared_expert.up_proj.weight": "model-00099.safetensors", + "language_model.model.layers.9.mlp.shared_expert.up_proj.scales": "model-00099.safetensors", + "language_model.model.layers.9.mlp.shared_expert.up_proj.biases": "model-00099.safetensors", + "language_model.model.layers.9.mlp.shared_expert_gate.weight": "model-00099.safetensors", + "language_model.model.layers.9.mlp_hyper_connection.block_inject_weight.weight": "model-00099.safetensors", + "language_model.model.layers.9.mlp_hyper_connection.hc_norm.weight": "model-00099.safetensors", + "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_down.weight": "model-00099.safetensors", + "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_down.scales": "model-00099.safetensors", + "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_down.biases": "model-00099.safetensors", + "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_up.weight": "model-00099.safetensors", + "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_up.scales": "model-00099.safetensors", + "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_up.biases": "model-00099.safetensors", + "language_model.lm_head.weight": "model-00100.safetensors", + "language_model.lm_head.scales": "model-00100.safetensors", + "language_model.lm_head.biases": "model-00100.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.0.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.0.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.0.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.0.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.1.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.1.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.1.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.1.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.10.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.10.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.10.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.10.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.11.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.11.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.11.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.11.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.12.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.12.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.12.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.12.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.13.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.13.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.13.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.13.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.14.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.14.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.14.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.14.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.15.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.15.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.15.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.15.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.16.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.16.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.16.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.16.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.17.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.17.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.17.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.17.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.18.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.18.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.18.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.18.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.19.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.19.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.19.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.19.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.2.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.2.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.2.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.2.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.20.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.20.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.20.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.20.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.21.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.21.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.21.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.21.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.22.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.22.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.22.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.22.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.23.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.23.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.23.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.23.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.24.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.24.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.24.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.24.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.24.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.24.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.24.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.24.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.24.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.24.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.24.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.24.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.25.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.25.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.25.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.25.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.25.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.25.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.25.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.25.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.25.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.25.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.25.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.25.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.26.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.26.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.26.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.26.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.26.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.26.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.26.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.26.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.26.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.26.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.26.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.26.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.3.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.3.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.3.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.3.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.4.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.4.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.4.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.4.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.5.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.5.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.5.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.5.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.6.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.6.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.6.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.6.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.7.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.7.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.7.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.7.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.8.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.8.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.8.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.8.norm2.weight": "model-vision.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-vision.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-vision.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-vision.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-vision.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-vision.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-vision.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-vision.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-vision.safetensors", + "model.visual.blocks.9.norm1.bias": "model-vision.safetensors", + "model.visual.blocks.9.norm1.weight": "model-vision.safetensors", + "model.visual.blocks.9.norm2.bias": "model-vision.safetensors", + "model.visual.blocks.9.norm2.weight": "model-vision.safetensors", + "model.visual.merger.linear_fc1.bias": "model-vision.safetensors", + "model.visual.merger.linear_fc1.weight": "model-vision.safetensors", + "model.visual.merger.linear_fc2.bias": "model-vision.safetensors", + "model.visual.merger.linear_fc2.weight": "model-vision.safetensors", + "model.visual.merger.norm.bias": "model-vision.safetensors", + "model.visual.merger.norm.weight": "model-vision.safetensors", + "model.visual.patch_embed.proj.bias": "model-vision.safetensors", + "model.visual.patch_embed.proj.weight": "model-vision.safetensors", + "model.visual.pos_embed.weight": "model-vision.safetensors" + } +} \ No newline at end of file