{
 "metadata": {
  "total_size": 102506904440
 },
 "weight_map": {
  "lm_head.weight": "model-00001-of-00027.safetensors",
  "lm_head.scales": "model-00001-of-00027.safetensors",
  "lm_head.biases": "model-00001-of-00027.safetensors",
  "model.embed_tokens.weight": "model-00001-of-00027.safetensors",
  "model.embed_tokens.scales": "model-00001-of-00027.safetensors",
  "model.embed_tokens.biases": "model-00001-of-00027.safetensors",
  "model.layers.0.attn_hc.hc_base": "model-00001-of-00027.safetensors",
  "model.layers.0.attn_hc.hc_fn": "model-00001-of-00027.safetensors",
  "model.layers.0.attn_hc.hc_scale": "model-00001-of-00027.safetensors",
  "model.layers.0.ffn_hc.hc_base": "model-00001-of-00027.safetensors",
  "model.layers.0.ffn_hc.hc_fn": "model-00001-of-00027.safetensors",
  "model.layers.0.ffn_hc.hc_scale": "model-00001-of-00027.safetensors",
  "model.layers.0.input_layernorm.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.mlp.down_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.mlp.down_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.0.mlp.down_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.0.mlp.up_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.mlp.up_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.0.mlp.up_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.A_log": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.b_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.dt_bias": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.f_a_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.f_b_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.g_a_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.g_b_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.k_conv1d": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.o_norm": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.q_conv1d": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.v_conv1d": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.1.attn_hc.hc_base": "model-00001-of-00027.safetensors",
  "model.layers.1.attn_hc.hc_fn": "model-00001-of-00027.safetensors",
  "model.layers.1.attn_hc.hc_scale": "model-00001-of-00027.safetensors",
  "model.layers.1.ffn_hc.hc_base": "model-00001-of-00027.safetensors",
  "model.layers.1.ffn_hc.hc_fn": "model-00001-of-00027.safetensors",
  "model.layers.1.ffn_hc.hc_scale": "model-00001-of-00027.safetensors",
  "model.layers.1.input_layernorm.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.mlp.down_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.mlp.down_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.1.mlp.down_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.1.mlp.up_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.mlp.up_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.1.mlp.up_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.A_log": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.b_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.dt_bias": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.f_a_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.f_b_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.g_a_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.g_b_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.k_conv1d": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.o_norm": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.q_conv1d": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.v_conv1d": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.10.attn_hc.hc_base": "model-00001-of-00027.safetensors",
  "model.layers.10.attn_hc.hc_fn": "model-00001-of-00027.safetensors",
  "model.layers.10.attn_hc.hc_scale": "model-00001-of-00027.safetensors",
  "model.layers.10.ffn_hc.hc_base": "model-00001-of-00027.safetensors",
  "model.layers.10.ffn_hc.hc_fn": "model-00001-of-00027.safetensors",
  "model.layers.10.ffn_hc.hc_scale": "model-00001-of-00027.safetensors",
  "model.layers.10.input_layernorm.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.e_score_correction_bias": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.gate.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.shared_experts.down_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.shared_experts.down_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.shared_experts.gate_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.shared_experts.gate_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.shared_experts.up_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.shared_experts.up_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.A_log": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.b_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.dt_bias": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.f_a_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.f_b_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.g_a_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.g_b_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.k_conv1d": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.o_norm": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.q_conv1d": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.v_conv1d": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.11.attn_hc.hc_base": "model-00001-of-00027.safetensors",
  "model.layers.11.attn_hc.hc_fn": "model-00001-of-00027.safetensors",
  "model.layers.11.attn_hc.hc_scale": "model-00001-of-00027.safetensors",
  "model.layers.11.ffn_hc.hc_base": "model-00001-of-00027.safetensors",
  "model.layers.11.ffn_hc.hc_fn": "model-00001-of-00027.safetensors",
  "model.layers.11.ffn_hc.hc_scale": "model-00001-of-00027.safetensors",
  "model.layers.11.input_layernorm.weight": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.e_score_correction_bias": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.gate.weight": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.shared_experts.down_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.shared_experts.down_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.shared_experts.gate_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.shared_experts.gate_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.shared_experts.up_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.shared_experts.up_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00001-of-00027.safetensors",
  "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00002-of-00027.safetensors",
  "model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00002-of-00027.safetensors",
  "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.index_kpool_compress_ape": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.index_kpool_compress_gate": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.k_norm.bias": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.k_norm.weight": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.weights_proj.weight": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.weights_proj.scales": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.weights_proj.biases": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.wk.weight": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.wk.scales": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.wk.biases": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.wq_b.weight": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.wq_b.scales": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.indexer.wq_b.biases": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.kv_a_layernorm.weight": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.kv_b_proj.weight": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.kv_b_proj.scales": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.kv_b_proj.biases": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.o_proj.scales": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.o_proj.biases": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.q_a_layernorm.weight": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.q_a_proj.weight": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.q_a_proj.scales": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.q_a_proj.biases": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.q_b_proj.weight": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.q_b_proj.scales": "model-00002-of-00027.safetensors",
  "model.layers.11.self_attn.q_b_proj.biases": "model-00002-of-00027.safetensors",
  "model.layers.12.attn_hc.hc_base": "model-00002-of-00027.safetensors",
  "model.layers.12.attn_hc.hc_fn": "model-00002-of-00027.safetensors",
  "model.layers.12.attn_hc.hc_scale": "model-00002-of-00027.safetensors",
  "model.layers.12.ffn_hc.hc_base": "model-00002-of-00027.safetensors",
  "model.layers.12.ffn_hc.hc_fn": "model-00002-of-00027.safetensors",
  "model.layers.12.ffn_hc.hc_scale": "model-00003-of-00027.safetensors",
  "model.layers.12.input_layernorm.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.e_score_correction_bias": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.gate.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.shared_experts.down_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.shared_experts.down_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.shared_experts.gate_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.shared_experts.gate_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.shared_experts.up_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.shared_experts.up_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.A_log": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.b_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.dt_bias": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.f_a_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.f_b_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.g_a_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.g_b_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.k_conv1d": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.k_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.k_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.o_norm": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.o_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.o_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.q_conv1d": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.q_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.q_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.v_conv1d": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.v_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.12.self_attn.v_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.13.attn_hc.hc_base": "model-00003-of-00027.safetensors",
  "model.layers.13.attn_hc.hc_fn": "model-00003-of-00027.safetensors",
  "model.layers.13.attn_hc.hc_scale": "model-00003-of-00027.safetensors",
  "model.layers.13.ffn_hc.hc_base": "model-00003-of-00027.safetensors",
  "model.layers.13.ffn_hc.hc_fn": "model-00003-of-00027.safetensors",
  "model.layers.13.ffn_hc.hc_scale": "model-00003-of-00027.safetensors",
  "model.layers.13.input_layernorm.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.e_score_correction_bias": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.gate.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.shared_experts.down_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.shared_experts.down_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.shared_experts.gate_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.shared_experts.gate_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.shared_experts.up_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.shared_experts.up_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.A_log": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.b_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.dt_bias": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.f_a_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.f_b_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.g_a_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.g_b_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.k_conv1d": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.k_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.k_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.o_norm": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.o_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.o_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.q_conv1d": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.q_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.q_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.v_conv1d": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.v_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.13.self_attn.v_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.14.attn_hc.hc_base": "model-00003-of-00027.safetensors",
  "model.layers.14.attn_hc.hc_fn": "model-00003-of-00027.safetensors",
  "model.layers.14.attn_hc.hc_scale": "model-00003-of-00027.safetensors",
  "model.layers.14.ffn_hc.hc_base": "model-00003-of-00027.safetensors",
  "model.layers.14.ffn_hc.hc_fn": "model-00003-of-00027.safetensors",
  "model.layers.14.ffn_hc.hc_scale": "model-00003-of-00027.safetensors",
  "model.layers.14.input_layernorm.weight": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.e_score_correction_bias": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.gate.weight": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.shared_experts.down_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.shared_experts.down_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.shared_experts.gate_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.shared_experts.up_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.shared_experts.up_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
  "model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.A_log": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.b_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.dt_bias": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.f_a_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.f_b_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.g_a_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.g_b_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.k_conv1d": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.k_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.k_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.o_norm": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.o_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.o_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.q_conv1d": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.q_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.q_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.v_conv1d": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.v_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.14.self_attn.v_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.attn_hc.hc_base": "model-00004-of-00027.safetensors",
  "model.layers.15.attn_hc.hc_fn": "model-00004-of-00027.safetensors",
  "model.layers.15.attn_hc.hc_scale": "model-00004-of-00027.safetensors",
  "model.layers.15.ffn_hc.hc_base": "model-00004-of-00027.safetensors",
  "model.layers.15.ffn_hc.hc_fn": "model-00004-of-00027.safetensors",
  "model.layers.15.ffn_hc.hc_scale": "model-00004-of-00027.safetensors",
  "model.layers.15.input_layernorm.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.e_score_correction_bias": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.gate.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.shared_experts.down_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.shared_experts.down_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.shared_experts.gate_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.shared_experts.up_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.shared_experts.up_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.index_kpool_compress_ape": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.index_kpool_compress_gate": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.k_norm.bias": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.k_norm.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.weights_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.weights_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.weights_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.wk.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.wk.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.wk.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.wq_b.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.wq_b.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.indexer.wq_b.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.kv_a_layernorm.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.kv_b_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.kv_b_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.kv_b_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.o_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.o_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.q_a_layernorm.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.q_a_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.q_a_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.q_a_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.q_b_proj.weight": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.q_b_proj.scales": "model-00004-of-00027.safetensors",
  "model.layers.15.self_attn.q_b_proj.biases": "model-00004-of-00027.safetensors",
  "model.layers.16.attn_hc.hc_base": "model-00004-of-00027.safetensors",
  "model.layers.16.attn_hc.hc_fn": "model-00004-of-00027.safetensors",
  "model.layers.16.attn_hc.hc_scale": "model-00005-of-00027.safetensors",
  "model.layers.16.ffn_hc.hc_base": "model-00005-of-00027.safetensors",
  "model.layers.16.ffn_hc.hc_fn": "model-00005-of-00027.safetensors",
  "model.layers.16.ffn_hc.hc_scale": "model-00005-of-00027.safetensors",
  "model.layers.16.input_layernorm.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.e_score_correction_bias": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.gate.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.shared_experts.down_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.shared_experts.down_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.shared_experts.gate_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.shared_experts.up_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.shared_experts.up_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.A_log": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.b_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.dt_bias": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.f_a_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.f_b_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.g_a_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.g_b_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.k_conv1d": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.k_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.k_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.o_norm": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.o_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.o_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.q_conv1d": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.q_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.q_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.v_conv1d": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.v_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.16.self_attn.v_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.17.attn_hc.hc_base": "model-00005-of-00027.safetensors",
  "model.layers.17.attn_hc.hc_fn": "model-00005-of-00027.safetensors",
  "model.layers.17.attn_hc.hc_scale": "model-00005-of-00027.safetensors",
  "model.layers.17.ffn_hc.hc_base": "model-00005-of-00027.safetensors",
  "model.layers.17.ffn_hc.hc_fn": "model-00005-of-00027.safetensors",
  "model.layers.17.ffn_hc.hc_scale": "model-00005-of-00027.safetensors",
  "model.layers.17.input_layernorm.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.e_score_correction_bias": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.gate.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.shared_experts.down_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.shared_experts.down_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.shared_experts.gate_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.shared_experts.up_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.shared_experts.up_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.A_log": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.b_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.dt_bias": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.f_a_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.f_b_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.g_a_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.g_b_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.k_conv1d": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.k_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.k_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.o_norm": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.o_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.o_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.q_conv1d": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.q_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.q_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.v_conv1d": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.v_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.17.self_attn.v_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.18.attn_hc.hc_base": "model-00005-of-00027.safetensors",
  "model.layers.18.attn_hc.hc_fn": "model-00005-of-00027.safetensors",
  "model.layers.18.attn_hc.hc_scale": "model-00005-of-00027.safetensors",
  "model.layers.18.ffn_hc.hc_base": "model-00005-of-00027.safetensors",
  "model.layers.18.ffn_hc.hc_fn": "model-00005-of-00027.safetensors",
  "model.layers.18.ffn_hc.hc_scale": "model-00005-of-00027.safetensors",
  "model.layers.18.input_layernorm.weight": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.e_score_correction_bias": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.gate.weight": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.shared_experts.down_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.shared_experts.down_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.shared_experts.gate_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.shared_experts.up_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.shared_experts.up_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
  "model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.A_log": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.b_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.dt_bias": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.f_a_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.f_b_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.g_a_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.g_b_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.k_conv1d": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.k_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.k_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.o_norm": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.o_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.o_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.q_conv1d": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.q_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.q_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.v_conv1d": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.v_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.18.self_attn.v_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.attn_hc.hc_base": "model-00006-of-00027.safetensors",
  "model.layers.19.attn_hc.hc_fn": "model-00006-of-00027.safetensors",
  "model.layers.19.attn_hc.hc_scale": "model-00006-of-00027.safetensors",
  "model.layers.19.ffn_hc.hc_base": "model-00006-of-00027.safetensors",
  "model.layers.19.ffn_hc.hc_fn": "model-00006-of-00027.safetensors",
  "model.layers.19.ffn_hc.hc_scale": "model-00006-of-00027.safetensors",
  "model.layers.19.input_layernorm.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.e_score_correction_bias": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.gate.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.shared_experts.down_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.shared_experts.down_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.shared_experts.gate_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.shared_experts.up_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.shared_experts.up_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.index_kpool_compress_ape": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.index_kpool_compress_gate": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.k_norm.bias": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.k_norm.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.weights_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.weights_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.weights_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.wk.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.wk.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.wk.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.wq_b.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.wq_b.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.indexer.wq_b.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.kv_a_proj_with_mqa.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.kv_a_proj_with_mqa.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.kv_b_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.kv_b_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.kv_b_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.o_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.o_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.q_a_layernorm.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.q_a_proj.weight": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.q_a_proj.scales": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.q_a_proj.biases": "model-00006-of-00027.safetensors",
  "model.layers.19.self_attn.q_b_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.19.self_attn.q_b_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.19.self_attn.q_b_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.2.attn_hc.hc_base": "model-00007-of-00027.safetensors",
  "model.layers.2.attn_hc.hc_fn": "model-00007-of-00027.safetensors",
  "model.layers.2.attn_hc.hc_scale": "model-00007-of-00027.safetensors",
  "model.layers.2.ffn_hc.hc_base": "model-00007-of-00027.safetensors",
  "model.layers.2.ffn_hc.hc_fn": "model-00007-of-00027.safetensors",
  "model.layers.2.ffn_hc.hc_scale": "model-00007-of-00027.safetensors",
  "model.layers.2.input_layernorm.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.mlp.down_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.mlp.down_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.2.mlp.down_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.mlp.gate_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.2.mlp.gate_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.2.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.mlp.up_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.2.mlp.up_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.A_log": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.b_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.dt_bias": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.f_a_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.f_b_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.g_a_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.g_b_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.k_conv1d": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.k_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.k_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.o_norm": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.o_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.o_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.q_conv1d": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.q_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.q_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.v_conv1d": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.v_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.2.self_attn.v_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.20.attn_hc.hc_base": "model-00007-of-00027.safetensors",
  "model.layers.20.attn_hc.hc_fn": "model-00007-of-00027.safetensors",
  "model.layers.20.attn_hc.hc_scale": "model-00007-of-00027.safetensors",
  "model.layers.20.ffn_hc.hc_base": "model-00007-of-00027.safetensors",
  "model.layers.20.ffn_hc.hc_fn": "model-00007-of-00027.safetensors",
  "model.layers.20.ffn_hc.hc_scale": "model-00007-of-00027.safetensors",
  "model.layers.20.input_layernorm.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.e_score_correction_bias": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.gate.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.shared_experts.down_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.shared_experts.down_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.shared_experts.gate_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.shared_experts.up_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.shared_experts.up_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.A_log": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.b_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.dt_bias": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.f_a_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.f_b_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.g_a_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.g_b_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.k_conv1d": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.k_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.k_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.o_norm": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.o_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.o_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.q_conv1d": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.q_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.q_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.v_conv1d": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.v_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.20.self_attn.v_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.21.attn_hc.hc_base": "model-00007-of-00027.safetensors",
  "model.layers.21.attn_hc.hc_fn": "model-00007-of-00027.safetensors",
  "model.layers.21.attn_hc.hc_scale": "model-00007-of-00027.safetensors",
  "model.layers.21.ffn_hc.hc_base": "model-00007-of-00027.safetensors",
  "model.layers.21.ffn_hc.hc_fn": "model-00007-of-00027.safetensors",
  "model.layers.21.ffn_hc.hc_scale": "model-00007-of-00027.safetensors",
  "model.layers.21.input_layernorm.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.e_score_correction_bias": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.gate.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.shared_experts.down_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.shared_experts.down_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.shared_experts.gate_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.shared_experts.up_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.shared_experts.up_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.A_log": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.b_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.dt_bias": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.f_a_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.f_b_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.g_a_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.g_b_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.k_conv1d": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.k_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.k_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.o_norm": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.o_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.o_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.q_conv1d": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.q_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.q_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.v_conv1d": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.v_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.21.self_attn.v_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.22.attn_hc.hc_base": "model-00007-of-00027.safetensors",
  "model.layers.22.attn_hc.hc_fn": "model-00007-of-00027.safetensors",
  "model.layers.22.attn_hc.hc_scale": "model-00007-of-00027.safetensors",
  "model.layers.22.ffn_hc.hc_base": "model-00007-of-00027.safetensors",
  "model.layers.22.ffn_hc.hc_fn": "model-00007-of-00027.safetensors",
  "model.layers.22.ffn_hc.hc_scale": "model-00007-of-00027.safetensors",
  "model.layers.22.input_layernorm.weight": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.e_score_correction_bias": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.gate.weight": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.shared_experts.down_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.shared_experts.down_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.shared_experts.gate_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.shared_experts.up_proj.scales": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.shared_experts.up_proj.biases": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00007-of-00027.safetensors",
  "model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00008-of-00027.safetensors",
  "model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00008-of-00027.safetensors",
  "model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00027.safetensors",
  "model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00027.safetensors",
  "model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00027.safetensors",
  "model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00008-of-00027.safetensors",
  "model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00008-of-00027.safetensors",
  "model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00008-of-00027.safetensors",
  "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.A_log": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.b_proj.weight": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.dt_bias": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.f_a_proj.weight": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.f_b_proj.weight": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.g_a_proj.weight": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.g_b_proj.weight": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.k_conv1d": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.k_proj.scales": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.k_proj.biases": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.o_norm": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.o_proj.scales": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.o_proj.biases": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.q_conv1d": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.q_proj.scales": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.q_proj.biases": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.v_conv1d": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.v_proj.scales": "model-00008-of-00027.safetensors",
  "model.layers.22.self_attn.v_proj.biases": "model-00008-of-00027.safetensors",
  "model.layers.23.attn_hc.hc_base": "model-00009-of-00027.safetensors",
  "model.layers.23.attn_hc.hc_fn": "model-00009-of-00027.safetensors",
  "model.layers.23.attn_hc.hc_scale": "model-00009-of-00027.safetensors",
  "model.layers.23.ffn_hc.hc_base": "model-00009-of-00027.safetensors",
  "model.layers.23.ffn_hc.hc_fn": "model-00009-of-00027.safetensors",
  "model.layers.23.ffn_hc.hc_scale": "model-00009-of-00027.safetensors",
  "model.layers.23.input_layernorm.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.e_score_correction_bias": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.gate.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.shared_experts.down_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.shared_experts.down_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.shared_experts.gate_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.shared_experts.up_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.shared_experts.up_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.index_kpool_compress_ape": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.index_kpool_compress_gate": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.k_norm.bias": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.k_norm.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.weights_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.weights_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.weights_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.wk.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.wk.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.wk.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.wq_b.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.wq_b.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.indexer.wq_b.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.kv_a_proj_with_mqa.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.kv_a_proj_with_mqa.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.kv_b_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.kv_b_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.kv_b_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.o_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.o_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.q_a_layernorm.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.q_a_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.q_a_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.q_a_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.q_b_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.q_b_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.23.self_attn.q_b_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.24.attn_hc.hc_base": "model-00009-of-00027.safetensors",
  "model.layers.24.attn_hc.hc_fn": "model-00009-of-00027.safetensors",
  "model.layers.24.attn_hc.hc_scale": "model-00009-of-00027.safetensors",
  "model.layers.24.ffn_hc.hc_base": "model-00009-of-00027.safetensors",
  "model.layers.24.ffn_hc.hc_fn": "model-00009-of-00027.safetensors",
  "model.layers.24.ffn_hc.hc_scale": "model-00009-of-00027.safetensors",
  "model.layers.24.input_layernorm.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.e_score_correction_bias": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.gate.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.shared_experts.down_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.shared_experts.down_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.shared_experts.gate_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.shared_experts.gate_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.shared_experts.up_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.shared_experts.up_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.A_log": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.b_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.dt_bias": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.f_a_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.f_b_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.g_a_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.g_b_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.k_conv1d": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.k_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.k_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.o_norm": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.o_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.o_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.q_conv1d": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.q_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.q_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.v_conv1d": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.v_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.24.self_attn.v_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.25.attn_hc.hc_base": "model-00009-of-00027.safetensors",
  "model.layers.25.attn_hc.hc_fn": "model-00009-of-00027.safetensors",
  "model.layers.25.attn_hc.hc_scale": "model-00009-of-00027.safetensors",
  "model.layers.25.ffn_hc.hc_base": "model-00009-of-00027.safetensors",
  "model.layers.25.ffn_hc.hc_fn": "model-00009-of-00027.safetensors",
  "model.layers.25.ffn_hc.hc_scale": "model-00009-of-00027.safetensors",
  "model.layers.25.input_layernorm.weight": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.e_score_correction_bias": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.gate.weight": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.shared_experts.down_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.shared_experts.down_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.shared_experts.gate_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.shared_experts.gate_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.shared_experts.up_proj.scales": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.shared_experts.up_proj.biases": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00009-of-00027.safetensors",
  "model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.A_log": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.b_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.dt_bias": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.f_a_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.f_b_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.g_a_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.g_b_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.k_conv1d": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.k_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.k_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.o_norm": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.o_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.o_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.q_conv1d": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.q_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.q_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.v_conv1d": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.v_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.25.self_attn.v_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.26.attn_hc.hc_base": "model-00010-of-00027.safetensors",
  "model.layers.26.attn_hc.hc_fn": "model-00010-of-00027.safetensors",
  "model.layers.26.attn_hc.hc_scale": "model-00010-of-00027.safetensors",
  "model.layers.26.ffn_hc.hc_base": "model-00010-of-00027.safetensors",
  "model.layers.26.ffn_hc.hc_fn": "model-00010-of-00027.safetensors",
  "model.layers.26.ffn_hc.hc_scale": "model-00010-of-00027.safetensors",
  "model.layers.26.input_layernorm.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.e_score_correction_bias": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.gate.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.shared_experts.down_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.shared_experts.down_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.shared_experts.gate_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.shared_experts.gate_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.shared_experts.up_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.shared_experts.up_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.A_log": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.b_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.dt_bias": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.f_a_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.f_b_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.g_a_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.g_b_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.k_conv1d": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.k_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.k_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.o_norm": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.o_proj.scales": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.o_proj.biases": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.q_conv1d": "model-00010-of-00027.safetensors",
  "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.26.self_attn.q_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.26.self_attn.q_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.26.self_attn.v_conv1d": "model-00011-of-00027.safetensors",
  "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.26.self_attn.v_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.26.self_attn.v_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.attn_hc.hc_base": "model-00011-of-00027.safetensors",
  "model.layers.27.attn_hc.hc_fn": "model-00011-of-00027.safetensors",
  "model.layers.27.attn_hc.hc_scale": "model-00011-of-00027.safetensors",
  "model.layers.27.ffn_hc.hc_base": "model-00011-of-00027.safetensors",
  "model.layers.27.ffn_hc.hc_fn": "model-00011-of-00027.safetensors",
  "model.layers.27.ffn_hc.hc_scale": "model-00011-of-00027.safetensors",
  "model.layers.27.input_layernorm.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.e_score_correction_bias": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.gate.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.shared_experts.down_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.shared_experts.down_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.shared_experts.gate_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.shared_experts.gate_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.shared_experts.up_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.shared_experts.up_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.index_kpool_compress_ape": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.index_kpool_compress_gate": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.k_norm.bias": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.k_norm.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.weights_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.weights_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.weights_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.wk.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.wk.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.wk.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.wq_b.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.wq_b.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.indexer.wq_b.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.kv_a_layernorm.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.kv_a_proj_with_mqa.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.kv_a_proj_with_mqa.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.kv_a_proj_with_mqa.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.kv_b_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.kv_b_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.kv_b_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.o_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.o_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.q_a_layernorm.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.q_a_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.q_a_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.q_a_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.q_b_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.q_b_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.27.self_attn.q_b_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.28.attn_hc.hc_base": "model-00011-of-00027.safetensors",
  "model.layers.28.attn_hc.hc_fn": "model-00011-of-00027.safetensors",
  "model.layers.28.attn_hc.hc_scale": "model-00011-of-00027.safetensors",
  "model.layers.28.ffn_hc.hc_base": "model-00011-of-00027.safetensors",
  "model.layers.28.ffn_hc.hc_fn": "model-00011-of-00027.safetensors",
  "model.layers.28.ffn_hc.hc_scale": "model-00011-of-00027.safetensors",
  "model.layers.28.input_layernorm.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.e_score_correction_bias": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.gate.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.shared_experts.down_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.shared_experts.down_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.shared_experts.gate_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.shared_experts.gate_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.shared_experts.up_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.shared_experts.up_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.A_log": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.b_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.dt_bias": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.f_a_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.f_b_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.g_a_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.g_b_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.k_conv1d": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.k_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.k_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.o_norm": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.o_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.o_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.q_conv1d": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.q_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.q_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.v_conv1d": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.v_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.28.self_attn.v_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.29.attn_hc.hc_base": "model-00011-of-00027.safetensors",
  "model.layers.29.attn_hc.hc_fn": "model-00011-of-00027.safetensors",
  "model.layers.29.attn_hc.hc_scale": "model-00011-of-00027.safetensors",
  "model.layers.29.ffn_hc.hc_base": "model-00011-of-00027.safetensors",
  "model.layers.29.ffn_hc.hc_fn": "model-00011-of-00027.safetensors",
  "model.layers.29.ffn_hc.hc_scale": "model-00011-of-00027.safetensors",
  "model.layers.29.input_layernorm.weight": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.e_score_correction_bias": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.gate.weight": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.shared_experts.down_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.shared_experts.down_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.shared_experts.gate_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.shared_experts.gate_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.shared_experts.up_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.shared_experts.up_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
  "model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.A_log": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.b_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.dt_bias": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.f_a_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.f_b_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.g_a_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.g_b_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.k_conv1d": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.k_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.k_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.o_norm": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.o_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.o_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.q_conv1d": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.q_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.q_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.v_conv1d": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.v_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.29.self_attn.v_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.3.attn_hc.hc_base": "model-00012-of-00027.safetensors",
  "model.layers.3.attn_hc.hc_fn": "model-00012-of-00027.safetensors",
  "model.layers.3.attn_hc.hc_scale": "model-00012-of-00027.safetensors",
  "model.layers.3.ffn_hc.hc_base": "model-00012-of-00027.safetensors",
  "model.layers.3.ffn_hc.hc_fn": "model-00012-of-00027.safetensors",
  "model.layers.3.ffn_hc.hc_scale": "model-00012-of-00027.safetensors",
  "model.layers.3.input_layernorm.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.e_score_correction_bias": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.gate.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.shared_experts.down_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.shared_experts.down_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.shared_experts.gate_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.shared_experts.gate_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.shared_experts.up_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.shared_experts.up_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.index_kpool_compress_ape": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.index_kpool_compress_gate": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.k_norm.bias": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.k_norm.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.weights_proj.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.weights_proj.scales": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.weights_proj.biases": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.wk.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.wk.scales": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.wk.biases": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.wq_b.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.wq_b.scales": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.indexer.wq_b.biases": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.kv_a_layernorm.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.kv_a_proj_with_mqa.scales": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.kv_a_proj_with_mqa.biases": "model-00012-of-00027.safetensors",
  "model.layers.3.self_attn.kv_b_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.3.self_attn.kv_b_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.3.self_attn.kv_b_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.3.self_attn.o_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.3.self_attn.o_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.3.self_attn.q_a_layernorm.weight": "model-00013-of-00027.safetensors",
  "model.layers.3.self_attn.q_a_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.3.self_attn.q_a_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.3.self_attn.q_a_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.3.self_attn.q_b_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.3.self_attn.q_b_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.3.self_attn.q_b_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.30.attn_hc.hc_base": "model-00013-of-00027.safetensors",
  "model.layers.30.attn_hc.hc_fn": "model-00013-of-00027.safetensors",
  "model.layers.30.attn_hc.hc_scale": "model-00013-of-00027.safetensors",
  "model.layers.30.ffn_hc.hc_base": "model-00013-of-00027.safetensors",
  "model.layers.30.ffn_hc.hc_fn": "model-00013-of-00027.safetensors",
  "model.layers.30.ffn_hc.hc_scale": "model-00013-of-00027.safetensors",
  "model.layers.30.input_layernorm.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.e_score_correction_bias": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.gate.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.shared_experts.down_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.shared_experts.down_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.shared_experts.gate_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.shared_experts.gate_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.shared_experts.up_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.shared_experts.up_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.A_log": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.b_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.dt_bias": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.f_a_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.f_b_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.g_a_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.g_b_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.k_conv1d": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.k_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.k_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.o_norm": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.o_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.o_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.q_conv1d": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.q_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.q_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.v_conv1d": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.v_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.30.self_attn.v_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.attn_hc.hc_base": "model-00013-of-00027.safetensors",
  "model.layers.31.attn_hc.hc_fn": "model-00013-of-00027.safetensors",
  "model.layers.31.attn_hc.hc_scale": "model-00013-of-00027.safetensors",
  "model.layers.31.ffn_hc.hc_base": "model-00013-of-00027.safetensors",
  "model.layers.31.ffn_hc.hc_fn": "model-00013-of-00027.safetensors",
  "model.layers.31.ffn_hc.hc_scale": "model-00013-of-00027.safetensors",
  "model.layers.31.input_layernorm.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.e_score_correction_bias": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.gate.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.shared_experts.down_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.shared_experts.down_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.shared_experts.gate_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.shared_experts.gate_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.shared_experts.up_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.shared_experts.up_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.index_kpool_compress_ape": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.index_kpool_compress_gate": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.k_norm.bias": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.k_norm.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.weights_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.weights_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.weights_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.wk.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.wk.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.wk.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.wq_b.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.wq_b.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.indexer.wq_b.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.kv_a_layernorm.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.kv_a_proj_with_mqa.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.kv_a_proj_with_mqa.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.kv_a_proj_with_mqa.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.kv_b_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.kv_b_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.kv_b_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.o_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.o_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.q_a_layernorm.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.q_a_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.q_a_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.q_a_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.q_b_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.q_b_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.31.self_attn.q_b_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.32.attn_hc.hc_base": "model-00013-of-00027.safetensors",
  "model.layers.32.attn_hc.hc_fn": "model-00013-of-00027.safetensors",
  "model.layers.32.attn_hc.hc_scale": "model-00013-of-00027.safetensors",
  "model.layers.32.ffn_hc.hc_base": "model-00013-of-00027.safetensors",
  "model.layers.32.ffn_hc.hc_fn": "model-00013-of-00027.safetensors",
  "model.layers.32.ffn_hc.hc_scale": "model-00013-of-00027.safetensors",
  "model.layers.32.input_layernorm.weight": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.e_score_correction_bias": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.gate.weight": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.shared_experts.down_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.shared_experts.down_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.shared_experts.gate_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.shared_experts.gate_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.shared_experts.up_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.shared_experts.up_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.switch_mlp.down_proj.biases": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
  "model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00027.safetensors",
  "model.layers.32.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00027.safetensors",
  "model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00014-of-00027.safetensors",
  "model.layers.32.mlp.switch_mlp.up_proj.biases": "model-00014-of-00027.safetensors",
  "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.A_log": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.b_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.dt_bias": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.f_a_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.f_b_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.g_a_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.g_b_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.k_conv1d": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.k_proj.scales": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.k_proj.biases": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.o_norm": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.o_proj.scales": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.o_proj.biases": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.q_conv1d": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.q_proj.scales": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.q_proj.biases": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.v_conv1d": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.v_proj.scales": "model-00014-of-00027.safetensors",
  "model.layers.32.self_attn.v_proj.biases": "model-00014-of-00027.safetensors",
  "model.layers.33.attn_hc.hc_base": "model-00014-of-00027.safetensors",
  "model.layers.33.attn_hc.hc_fn": "model-00014-of-00027.safetensors",
  "model.layers.33.attn_hc.hc_scale": "model-00014-of-00027.safetensors",
  "model.layers.33.ffn_hc.hc_base": "model-00014-of-00027.safetensors",
  "model.layers.33.ffn_hc.hc_fn": "model-00014-of-00027.safetensors",
  "model.layers.33.ffn_hc.hc_scale": "model-00014-of-00027.safetensors",
  "model.layers.33.input_layernorm.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.e_score_correction_bias": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.gate.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.shared_experts.down_proj.scales": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.shared_experts.down_proj.biases": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.shared_experts.gate_proj.scales": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.shared_experts.gate_proj.biases": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.shared_experts.up_proj.scales": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.shared_experts.up_proj.biases": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.switch_mlp.down_proj.biases": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00014-of-00027.safetensors",
  "model.layers.33.mlp.switch_mlp.up_proj.biases": "model-00014-of-00027.safetensors",
  "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.self_attn.A_log": "model-00014-of-00027.safetensors",
  "model.layers.33.self_attn.b_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.self_attn.dt_bias": "model-00014-of-00027.safetensors",
  "model.layers.33.self_attn.f_a_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.self_attn.f_b_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.self_attn.g_a_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.self_attn.g_b_proj.weight": "model-00014-of-00027.safetensors",
  "model.layers.33.self_attn.k_conv1d": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.k_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.k_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.o_norm": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.o_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.o_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.q_conv1d": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.q_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.q_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.v_conv1d": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.v_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.33.self_attn.v_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.34.attn_hc.hc_base": "model-00015-of-00027.safetensors",
  "model.layers.34.attn_hc.hc_fn": "model-00015-of-00027.safetensors",
  "model.layers.34.attn_hc.hc_scale": "model-00015-of-00027.safetensors",
  "model.layers.34.ffn_hc.hc_base": "model-00015-of-00027.safetensors",
  "model.layers.34.ffn_hc.hc_fn": "model-00015-of-00027.safetensors",
  "model.layers.34.ffn_hc.hc_scale": "model-00015-of-00027.safetensors",
  "model.layers.34.input_layernorm.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.e_score_correction_bias": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.gate.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.shared_experts.down_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.shared_experts.down_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.shared_experts.gate_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.shared_experts.gate_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.shared_experts.up_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.shared_experts.up_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.switch_mlp.down_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.switch_mlp.gate_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.34.mlp.switch_mlp.up_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.A_log": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.b_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.dt_bias": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.f_a_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.f_b_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.g_a_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.g_b_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.k_conv1d": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.k_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.k_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.o_norm": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.o_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.o_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.q_conv1d": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.q_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.q_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.v_conv1d": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.v_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.34.self_attn.v_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.attn_hc.hc_base": "model-00015-of-00027.safetensors",
  "model.layers.35.attn_hc.hc_fn": "model-00015-of-00027.safetensors",
  "model.layers.35.attn_hc.hc_scale": "model-00015-of-00027.safetensors",
  "model.layers.35.ffn_hc.hc_base": "model-00015-of-00027.safetensors",
  "model.layers.35.ffn_hc.hc_fn": "model-00015-of-00027.safetensors",
  "model.layers.35.ffn_hc.hc_scale": "model-00015-of-00027.safetensors",
  "model.layers.35.input_layernorm.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.e_score_correction_bias": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.gate.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.shared_experts.down_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.shared_experts.down_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.shared_experts.gate_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.shared_experts.gate_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.shared_experts.up_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.shared_experts.up_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.mlp.switch_mlp.up_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.post_attention_layernorm.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.index_kpool_compress_ape": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.index_kpool_compress_gate": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.k_norm.bias": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.k_norm.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.weights_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.weights_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.weights_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.wk.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.wk.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.wk.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.wq_b.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.wq_b.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.indexer.wq_b.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.kv_a_layernorm.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.kv_a_proj_with_mqa.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.kv_a_proj_with_mqa.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.kv_a_proj_with_mqa.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.kv_b_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.kv_b_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.kv_b_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.o_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.o_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.o_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.q_a_layernorm.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.q_a_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.q_a_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.q_a_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.q_b_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.q_b_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.35.self_attn.q_b_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.36.attn_hc.hc_base": "model-00015-of-00027.safetensors",
  "model.layers.36.attn_hc.hc_fn": "model-00015-of-00027.safetensors",
  "model.layers.36.attn_hc.hc_scale": "model-00015-of-00027.safetensors",
  "model.layers.36.ffn_hc.hc_base": "model-00015-of-00027.safetensors",
  "model.layers.36.ffn_hc.hc_fn": "model-00015-of-00027.safetensors",
  "model.layers.36.ffn_hc.hc_scale": "model-00015-of-00027.safetensors",
  "model.layers.36.input_layernorm.weight": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.e_score_correction_bias": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.gate.weight": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.shared_experts.down_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.shared_experts.down_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.shared_experts.gate_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.shared_experts.gate_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.shared_experts.up_proj.scales": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.shared_experts.up_proj.biases": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00015-of-00027.safetensors",
  "model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.A_log": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.b_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.dt_bias": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.f_a_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.f_b_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.g_a_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.g_b_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.k_conv1d": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.k_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.k_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.o_norm": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.o_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.o_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.q_conv1d": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.q_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.q_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.v_conv1d": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.v_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.36.self_attn.v_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.37.attn_hc.hc_base": "model-00016-of-00027.safetensors",
  "model.layers.37.attn_hc.hc_fn": "model-00016-of-00027.safetensors",
  "model.layers.37.attn_hc.hc_scale": "model-00016-of-00027.safetensors",
  "model.layers.37.ffn_hc.hc_base": "model-00016-of-00027.safetensors",
  "model.layers.37.ffn_hc.hc_fn": "model-00016-of-00027.safetensors",
  "model.layers.37.ffn_hc.hc_scale": "model-00016-of-00027.safetensors",
  "model.layers.37.input_layernorm.weight": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.e_score_correction_bias": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.gate.weight": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.shared_experts.down_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.shared_experts.down_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.shared_experts.gate_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.shared_experts.gate_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.shared_experts.up_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.shared_experts.up_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00016-of-00027.safetensors",
  "model.layers.37.mlp.switch_mlp.up_proj.biases": "model-00016-of-00027.safetensors",
  "model.layers.37.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
  "model.layers.37.self_attn.A_log": "model-00016-of-00027.safetensors",
  "model.layers.37.self_attn.b_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.37.self_attn.dt_bias": "model-00016-of-00027.safetensors",
  "model.layers.37.self_attn.f_a_proj.weight": "model-00016-of-00027.safetensors",
  "model.layers.37.self_attn.f_b_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.g_a_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.g_b_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.k_conv1d": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.k_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.k_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.k_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.o_norm": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.o_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.o_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.o_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.q_conv1d": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.q_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.q_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.v_conv1d": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.v_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.37.self_attn.v_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.38.attn_hc.hc_base": "model-00017-of-00027.safetensors",
  "model.layers.38.attn_hc.hc_fn": "model-00017-of-00027.safetensors",
  "model.layers.38.attn_hc.hc_scale": "model-00017-of-00027.safetensors",
  "model.layers.38.ffn_hc.hc_base": "model-00017-of-00027.safetensors",
  "model.layers.38.ffn_hc.hc_fn": "model-00017-of-00027.safetensors",
  "model.layers.38.ffn_hc.hc_scale": "model-00017-of-00027.safetensors",
  "model.layers.38.input_layernorm.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.e_score_correction_bias": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.gate.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.shared_experts.down_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.shared_experts.down_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.shared_experts.gate_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.shared_experts.gate_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.shared_experts.up_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.shared_experts.up_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.switch_mlp.down_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.switch_mlp.down_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.38.mlp.switch_mlp.up_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.38.post_attention_layernorm.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.A_log": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.b_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.dt_bias": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.f_a_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.f_b_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.g_a_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.g_b_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.k_conv1d": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.k_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.k_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.k_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.o_norm": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.o_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.o_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.o_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.q_conv1d": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.q_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.q_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.v_conv1d": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.v_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.38.self_attn.v_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.attn_hc.hc_base": "model-00017-of-00027.safetensors",
  "model.layers.39.attn_hc.hc_fn": "model-00017-of-00027.safetensors",
  "model.layers.39.attn_hc.hc_scale": "model-00017-of-00027.safetensors",
  "model.layers.39.ffn_hc.hc_base": "model-00017-of-00027.safetensors",
  "model.layers.39.ffn_hc.hc_fn": "model-00017-of-00027.safetensors",
  "model.layers.39.ffn_hc.hc_scale": "model-00017-of-00027.safetensors",
  "model.layers.39.input_layernorm.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.e_score_correction_bias": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.gate.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.shared_experts.down_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.shared_experts.down_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.shared_experts.gate_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.shared_experts.gate_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.shared_experts.up_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.shared_experts.up_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.switch_mlp.down_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.switch_mlp.down_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.mlp.switch_mlp.up_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.post_attention_layernorm.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.index_kpool_compress_ape": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.index_kpool_compress_gate": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.k_norm.bias": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.k_norm.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.weights_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.weights_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.weights_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.wk.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.wk.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.wk.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.wq_b.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.wq_b.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.indexer.wq_b.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.kv_a_layernorm.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.kv_a_proj_with_mqa.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.kv_a_proj_with_mqa.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.kv_a_proj_with_mqa.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.kv_b_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.kv_b_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.kv_b_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.o_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.o_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.o_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.q_a_layernorm.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.q_a_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.q_a_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.q_a_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.q_b_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.q_b_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.39.self_attn.q_b_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.4.attn_hc.hc_base": "model-00017-of-00027.safetensors",
  "model.layers.4.attn_hc.hc_fn": "model-00017-of-00027.safetensors",
  "model.layers.4.attn_hc.hc_scale": "model-00017-of-00027.safetensors",
  "model.layers.4.ffn_hc.hc_base": "model-00017-of-00027.safetensors",
  "model.layers.4.ffn_hc.hc_fn": "model-00017-of-00027.safetensors",
  "model.layers.4.ffn_hc.hc_scale": "model-00017-of-00027.safetensors",
  "model.layers.4.input_layernorm.weight": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.e_score_correction_bias": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.gate.weight": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.shared_experts.down_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.shared_experts.down_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.shared_experts.gate_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.shared_experts.gate_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.shared_experts.up_proj.scales": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.shared_experts.up_proj.biases": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00017-of-00027.safetensors",
  "model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.4.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.A_log": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.b_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.dt_bias": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.f_a_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.f_b_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.g_a_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.g_b_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.k_conv1d": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.k_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.k_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.o_norm": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.o_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.o_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.q_conv1d": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.q_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.q_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.v_conv1d": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.v_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.4.self_attn.v_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.40.attn_hc.hc_base": "model-00018-of-00027.safetensors",
  "model.layers.40.attn_hc.hc_fn": "model-00018-of-00027.safetensors",
  "model.layers.40.attn_hc.hc_scale": "model-00018-of-00027.safetensors",
  "model.layers.40.ffn_hc.hc_base": "model-00018-of-00027.safetensors",
  "model.layers.40.ffn_hc.hc_fn": "model-00018-of-00027.safetensors",
  "model.layers.40.ffn_hc.hc_scale": "model-00018-of-00027.safetensors",
  "model.layers.40.input_layernorm.weight": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.e_score_correction_bias": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.gate.weight": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.shared_experts.down_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.shared_experts.down_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.shared_experts.gate_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.shared_experts.gate_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.shared_experts.up_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.shared_experts.up_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.switch_mlp.down_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.switch_mlp.down_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.switch_mlp.gate_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.switch_mlp.gate_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.switch_mlp.up_proj.scales": "model-00018-of-00027.safetensors",
  "model.layers.40.mlp.switch_mlp.up_proj.biases": "model-00018-of-00027.safetensors",
  "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
  "model.layers.40.self_attn.A_log": "model-00018-of-00027.safetensors",
  "model.layers.40.self_attn.b_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.dt_bias": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.f_a_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.f_b_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.g_a_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.g_b_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.k_conv1d": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.k_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.k_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.o_norm": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.o_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.o_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.o_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.q_conv1d": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.q_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.q_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.v_conv1d": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.v_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.40.self_attn.v_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.41.attn_hc.hc_base": "model-00019-of-00027.safetensors",
  "model.layers.41.attn_hc.hc_fn": "model-00019-of-00027.safetensors",
  "model.layers.41.attn_hc.hc_scale": "model-00019-of-00027.safetensors",
  "model.layers.41.ffn_hc.hc_base": "model-00019-of-00027.safetensors",
  "model.layers.41.ffn_hc.hc_fn": "model-00019-of-00027.safetensors",
  "model.layers.41.ffn_hc.hc_scale": "model-00019-of-00027.safetensors",
  "model.layers.41.input_layernorm.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.e_score_correction_bias": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.gate.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.shared_experts.down_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.shared_experts.down_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.shared_experts.gate_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.shared_experts.gate_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.shared_experts.up_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.shared_experts.up_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.switch_mlp.down_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.switch_mlp.down_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.switch_mlp.gate_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.switch_mlp.gate_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.switch_mlp.up_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.41.mlp.switch_mlp.up_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.41.post_attention_layernorm.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.A_log": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.b_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.dt_bias": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.f_a_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.f_b_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.g_a_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.g_b_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.k_conv1d": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.k_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.k_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.o_norm": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.o_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.o_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.q_conv1d": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.q_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.q_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.v_conv1d": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.v_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.41.self_attn.v_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.42.attn_hc.hc_base": "model-00019-of-00027.safetensors",
  "model.layers.42.attn_hc.hc_fn": "model-00019-of-00027.safetensors",
  "model.layers.42.attn_hc.hc_scale": "model-00019-of-00027.safetensors",
  "model.layers.42.ffn_hc.hc_base": "model-00019-of-00027.safetensors",
  "model.layers.42.ffn_hc.hc_fn": "model-00019-of-00027.safetensors",
  "model.layers.42.ffn_hc.hc_scale": "model-00019-of-00027.safetensors",
  "model.layers.42.input_layernorm.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.e_score_correction_bias": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.gate.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.shared_experts.down_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.shared_experts.down_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.shared_experts.gate_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.shared_experts.gate_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.shared_experts.up_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.shared_experts.up_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.switch_mlp.down_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.switch_mlp.down_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.switch_mlp.gate_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.switch_mlp.gate_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.switch_mlp.up_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.42.mlp.switch_mlp.up_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.42.post_attention_layernorm.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.A_log": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.b_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.dt_bias": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.f_a_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.f_b_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.g_a_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.g_b_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.k_conv1d": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.k_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.k_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.o_norm": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.o_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.o_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.o_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.q_conv1d": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.q_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.q_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.v_conv1d": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.v_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.42.self_attn.v_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.43.attn_hc.hc_base": "model-00019-of-00027.safetensors",
  "model.layers.43.attn_hc.hc_fn": "model-00019-of-00027.safetensors",
  "model.layers.43.attn_hc.hc_scale": "model-00019-of-00027.safetensors",
  "model.layers.43.ffn_hc.hc_base": "model-00019-of-00027.safetensors",
  "model.layers.43.ffn_hc.hc_fn": "model-00019-of-00027.safetensors",
  "model.layers.43.ffn_hc.hc_scale": "model-00019-of-00027.safetensors",
  "model.layers.43.input_layernorm.weight": "model-00019-of-00027.safetensors",
  "model.layers.43.mlp.e_score_correction_bias": "model-00019-of-00027.safetensors",
  "model.layers.43.mlp.gate.weight": "model-00019-of-00027.safetensors",
  "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.43.mlp.shared_experts.down_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.43.mlp.shared_experts.down_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.43.mlp.shared_experts.gate_proj.scales": "model-00019-of-00027.safetensors",
  "model.layers.43.mlp.shared_experts.gate_proj.biases": "model-00019-of-00027.safetensors",
  "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00019-of-00027.safetensors",
  "model.layers.43.mlp.shared_experts.up_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.43.mlp.shared_experts.up_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.mlp.switch_mlp.down_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.43.mlp.switch_mlp.down_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.43.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.mlp.switch_mlp.up_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.43.mlp.switch_mlp.up_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.43.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.index_kpool_compress_ape": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.index_kpool_compress_gate": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.k_norm.bias": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.k_norm.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.weights_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.weights_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.weights_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.wk.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.wk.scales": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.wk.biases": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.wq_b.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.wq_b.scales": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.indexer.wq_b.biases": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.kv_a_layernorm.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.kv_a_proj_with_mqa.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.kv_a_proj_with_mqa.scales": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.kv_a_proj_with_mqa.biases": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.kv_b_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.kv_b_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.kv_b_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.o_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.o_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.q_a_layernorm.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.q_a_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.q_a_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.q_a_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.q_b_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.q_b_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.43.self_attn.q_b_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.44.attn_hc.hc_base": "model-00020-of-00027.safetensors",
  "model.layers.44.attn_hc.hc_fn": "model-00020-of-00027.safetensors",
  "model.layers.44.attn_hc.hc_scale": "model-00020-of-00027.safetensors",
  "model.layers.44.ffn_hc.hc_base": "model-00020-of-00027.safetensors",
  "model.layers.44.ffn_hc.hc_fn": "model-00020-of-00027.safetensors",
  "model.layers.44.ffn_hc.hc_scale": "model-00020-of-00027.safetensors",
  "model.layers.44.input_layernorm.weight": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.e_score_correction_bias": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.gate.weight": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.shared_experts.down_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.shared_experts.down_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.shared_experts.gate_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.shared_experts.gate_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.shared_experts.up_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.shared_experts.up_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.switch_mlp.down_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00027.safetensors",
  "model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.44.mlp.switch_mlp.up_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.44.post_attention_layernorm.weight": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.A_log": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.b_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.dt_bias": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.f_a_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.f_b_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.g_a_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.g_b_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.k_conv1d": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.k_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.k_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.k_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.o_norm": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.o_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.o_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.o_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.q_conv1d": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.q_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.q_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.q_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.v_conv1d": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.v_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.v_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.44.self_attn.v_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.eh_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.eh_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.eh_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.enorm.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.hnorm.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.input_layernorm.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.e_score_correction_bias": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.gate.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.shared_experts.down_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.shared_experts.down_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.shared_experts.gate_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.shared_experts.gate_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.shared_experts.up_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.shared_experts.up_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.switch_mlp.down_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.switch_mlp.gate_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.mlp.switch_mlp.up_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.post_attention_layernorm.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.index_kpool_compress_ape": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.index_kpool_compress_gate": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.k_norm.bias": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.k_norm.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.weights_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.weights_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.weights_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.wk.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.wk.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.wk.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.wq_b.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.wq_b.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.indexer.wq_b.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.kv_a_layernorm.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.kv_a_proj_with_mqa.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.kv_a_proj_with_mqa.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.kv_a_proj_with_mqa.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.kv_b_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.kv_b_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.kv_b_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.o_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.o_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.o_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.q_a_layernorm.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.q_a_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.q_a_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.q_a_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.q_b_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.q_b_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.45.self_attn.q_b_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.45.shared_head.norm.weight": "model-00021-of-00027.safetensors",
  "model.layers.5.attn_hc.hc_base": "model-00021-of-00027.safetensors",
  "model.layers.5.attn_hc.hc_fn": "model-00021-of-00027.safetensors",
  "model.layers.5.attn_hc.hc_scale": "model-00021-of-00027.safetensors",
  "model.layers.5.ffn_hc.hc_base": "model-00021-of-00027.safetensors",
  "model.layers.5.ffn_hc.hc_fn": "model-00021-of-00027.safetensors",
  "model.layers.5.ffn_hc.hc_scale": "model-00021-of-00027.safetensors",
  "model.layers.5.input_layernorm.weight": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.e_score_correction_bias": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.gate.weight": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.shared_experts.down_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.shared_experts.down_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.shared_experts.gate_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.shared_experts.gate_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.shared_experts.up_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.shared_experts.up_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00021-of-00027.safetensors",
  "model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.5.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.A_log": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.b_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.dt_bias": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.f_a_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.f_b_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.g_a_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.g_b_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.k_conv1d": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.k_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.k_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.o_norm": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.o_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.o_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.q_conv1d": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.q_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.q_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.v_conv1d": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.v_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.5.self_attn.v_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.6.attn_hc.hc_base": "model-00022-of-00027.safetensors",
  "model.layers.6.attn_hc.hc_fn": "model-00022-of-00027.safetensors",
  "model.layers.6.attn_hc.hc_scale": "model-00022-of-00027.safetensors",
  "model.layers.6.ffn_hc.hc_base": "model-00022-of-00027.safetensors",
  "model.layers.6.ffn_hc.hc_fn": "model-00022-of-00027.safetensors",
  "model.layers.6.ffn_hc.hc_scale": "model-00022-of-00027.safetensors",
  "model.layers.6.input_layernorm.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.e_score_correction_bias": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.gate.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.shared_experts.down_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.shared_experts.down_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.shared_experts.gate_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.shared_experts.gate_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.shared_experts.up_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.shared_experts.up_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.A_log": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.b_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.dt_bias": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.f_a_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.f_b_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.g_a_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.g_b_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.k_conv1d": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.k_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.k_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.o_norm": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.o_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.o_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.q_conv1d": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.q_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.q_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.v_conv1d": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.v_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.6.self_attn.v_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.7.attn_hc.hc_base": "model-00022-of-00027.safetensors",
  "model.layers.7.attn_hc.hc_fn": "model-00022-of-00027.safetensors",
  "model.layers.7.attn_hc.hc_scale": "model-00022-of-00027.safetensors",
  "model.layers.7.ffn_hc.hc_base": "model-00022-of-00027.safetensors",
  "model.layers.7.ffn_hc.hc_fn": "model-00022-of-00027.safetensors",
  "model.layers.7.ffn_hc.hc_scale": "model-00022-of-00027.safetensors",
  "model.layers.7.input_layernorm.weight": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.e_score_correction_bias": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.gate.weight": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.shared_experts.down_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.shared_experts.down_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.shared_experts.gate_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.shared_experts.gate_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.shared_experts.up_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.shared_experts.up_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00022-of-00027.safetensors",
  "model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.7.post_attention_layernorm.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.index_kpool_compress_ape": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.index_kpool_compress_gate": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.k_norm.bias": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.k_norm.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.weights_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.weights_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.weights_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.wk.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.wk.scales": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.wk.biases": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.wq_b.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.wq_b.scales": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.indexer.wq_b.biases": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.kv_a_layernorm.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.kv_a_proj_with_mqa.scales": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.kv_a_proj_with_mqa.biases": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.kv_b_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.kv_b_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.kv_b_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.o_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.o_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.o_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.q_a_layernorm.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.q_a_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.q_a_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.q_a_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.q_b_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.q_b_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.7.self_attn.q_b_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.8.attn_hc.hc_base": "model-00023-of-00027.safetensors",
  "model.layers.8.attn_hc.hc_fn": "model-00023-of-00027.safetensors",
  "model.layers.8.attn_hc.hc_scale": "model-00023-of-00027.safetensors",
  "model.layers.8.ffn_hc.hc_base": "model-00023-of-00027.safetensors",
  "model.layers.8.ffn_hc.hc_fn": "model-00023-of-00027.safetensors",
  "model.layers.8.ffn_hc.hc_scale": "model-00023-of-00027.safetensors",
  "model.layers.8.input_layernorm.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.e_score_correction_bias": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.gate.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.shared_experts.down_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.shared_experts.down_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.shared_experts.gate_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.shared_experts.gate_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.shared_experts.up_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.shared_experts.up_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.8.post_attention_layernorm.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.A_log": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.b_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.dt_bias": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.f_a_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.f_b_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.g_a_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.g_b_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.k_conv1d": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.k_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.k_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.k_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.o_norm": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.o_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.o_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.o_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.q_conv1d": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.q_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.q_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.q_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.v_conv1d": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.v_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.v_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.8.self_attn.v_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.9.attn_hc.hc_base": "model-00023-of-00027.safetensors",
  "model.layers.9.attn_hc.hc_fn": "model-00023-of-00027.safetensors",
  "model.layers.9.attn_hc.hc_scale": "model-00023-of-00027.safetensors",
  "model.layers.9.ffn_hc.hc_base": "model-00023-of-00027.safetensors",
  "model.layers.9.ffn_hc.hc_fn": "model-00023-of-00027.safetensors",
  "model.layers.9.ffn_hc.hc_scale": "model-00023-of-00027.safetensors",
  "model.layers.9.input_layernorm.weight": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.e_score_correction_bias": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.gate.weight": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.shared_experts.down_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.shared_experts.down_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.shared_experts.gate_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.shared_experts.gate_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.shared_experts.up_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.shared_experts.up_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00023-of-00027.safetensors",
  "model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00024-of-00027.safetensors",
  "model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00024-of-00027.safetensors",
  "model.layers.9.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.A_log": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.b_proj.weight": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.dt_bias": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.f_a_proj.weight": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.f_b_proj.weight": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.g_a_proj.weight": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.g_b_proj.weight": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.k_conv1d": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.k_proj.scales": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.k_proj.biases": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.o_norm": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.o_proj.scales": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.o_proj.biases": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.q_conv1d": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.q_proj.scales": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.q_proj.biases": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.v_conv1d": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.v_proj.scales": "model-00024-of-00027.safetensors",
  "model.layers.9.self_attn.v_proj.biases": "model-00024-of-00027.safetensors",
  "model.norm.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.0.attn.k_norm.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.0.attn.proj.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.0.attn.proj.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.0.attn.proj.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.0.attn.proj.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.0.attn.q_norm.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.0.attn.qkv.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.0.attn.qkv.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.0.attn.qkv.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.0.attn.qkv.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.0.mlp.down_proj.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.0.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.0.mlp.down_proj.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.0.mlp.down_proj.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.0.mlp.gate_proj.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.0.mlp.gate_proj.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.0.mlp.gate_proj.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.0.mlp.gate_proj.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.0.mlp.up_proj.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.0.mlp.up_proj.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.0.mlp.up_proj.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.0.mlp.up_proj.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.0.norm1.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.0.norm2.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.1.attn.k_norm.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.1.attn.proj.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.1.attn.proj.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.1.attn.proj.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.1.attn.proj.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.1.attn.q_norm.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.1.attn.qkv.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.1.attn.qkv.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.1.attn.qkv.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.1.attn.qkv.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.1.mlp.down_proj.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.1.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.1.mlp.down_proj.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.1.mlp.down_proj.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.1.mlp.gate_proj.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.1.mlp.gate_proj.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.1.mlp.gate_proj.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.1.mlp.gate_proj.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.1.mlp.up_proj.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.1.mlp.up_proj.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.1.mlp.up_proj.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.1.mlp.up_proj.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.1.norm1.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.1.norm2.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.10.attn.k_norm.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.10.attn.proj.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.10.attn.proj.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.10.attn.proj.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.10.attn.proj.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.10.attn.q_norm.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.10.attn.qkv.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.10.attn.qkv.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.10.attn.qkv.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.10.attn.qkv.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.10.mlp.down_proj.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.10.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.10.mlp.down_proj.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.10.mlp.down_proj.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.10.mlp.gate_proj.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.10.mlp.gate_proj.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.10.mlp.gate_proj.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.10.mlp.gate_proj.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.10.mlp.up_proj.bias": "model-00024-of-00027.safetensors",
  "visual.blocks.10.mlp.up_proj.weight": "model-00024-of-00027.safetensors",
  "visual.blocks.10.mlp.up_proj.scales": "model-00024-of-00027.safetensors",
  "visual.blocks.10.mlp.up_proj.biases": "model-00024-of-00027.safetensors",
  "visual.blocks.10.norm1.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.10.norm2.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.11.attn.k_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.11.attn.proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.11.attn.proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.11.attn.proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.11.attn.proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.11.attn.q_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.11.attn.qkv.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.11.attn.qkv.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.11.attn.qkv.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.11.attn.qkv.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.11.mlp.down_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.11.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.11.mlp.down_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.11.mlp.down_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.11.mlp.gate_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.11.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.11.mlp.gate_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.11.mlp.gate_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.11.mlp.up_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.11.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.11.mlp.up_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.11.mlp.up_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.11.norm1.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.11.norm2.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.12.attn.k_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.12.attn.proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.12.attn.proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.12.attn.proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.12.attn.proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.12.attn.q_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.12.attn.qkv.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.12.attn.qkv.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.12.attn.qkv.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.12.attn.qkv.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.12.mlp.down_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.12.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.12.mlp.down_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.12.mlp.down_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.12.mlp.gate_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.12.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.12.mlp.gate_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.12.mlp.gate_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.12.mlp.up_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.12.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.12.mlp.up_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.12.mlp.up_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.12.norm1.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.12.norm2.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.13.attn.k_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.13.attn.proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.13.attn.proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.13.attn.proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.13.attn.proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.13.attn.q_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.13.attn.qkv.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.13.attn.qkv.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.13.attn.qkv.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.13.attn.qkv.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.13.mlp.down_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.13.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.13.mlp.down_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.13.mlp.down_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.13.mlp.gate_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.13.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.13.mlp.gate_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.13.mlp.gate_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.13.mlp.up_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.13.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.13.mlp.up_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.13.mlp.up_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.13.norm1.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.13.norm2.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.14.attn.k_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.14.attn.proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.14.attn.proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.14.attn.proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.14.attn.proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.14.attn.q_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.14.attn.qkv.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.14.attn.qkv.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.14.attn.qkv.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.14.attn.qkv.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.14.mlp.down_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.14.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.14.mlp.down_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.14.mlp.down_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.14.mlp.gate_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.14.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.14.mlp.gate_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.14.mlp.gate_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.14.mlp.up_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.14.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.14.mlp.up_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.14.mlp.up_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.14.norm1.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.14.norm2.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.15.attn.k_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.15.attn.proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.15.attn.proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.15.attn.proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.15.attn.proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.15.attn.q_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.15.attn.qkv.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.15.attn.qkv.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.15.attn.qkv.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.15.attn.qkv.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.15.mlp.down_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.15.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.15.mlp.down_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.15.mlp.down_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.15.mlp.gate_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.15.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.15.mlp.gate_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.15.mlp.gate_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.15.mlp.up_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.15.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.15.mlp.up_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.15.mlp.up_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.15.norm1.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.15.norm2.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.16.attn.k_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.16.attn.proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.16.attn.proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.16.attn.proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.16.attn.proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.16.attn.q_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.16.attn.qkv.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.16.attn.qkv.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.16.attn.qkv.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.16.attn.qkv.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.16.mlp.down_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.16.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.16.mlp.down_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.16.mlp.down_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.16.mlp.gate_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.16.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.16.mlp.gate_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.16.mlp.gate_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.16.mlp.up_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.16.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.16.mlp.up_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.16.mlp.up_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.16.norm1.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.16.norm2.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.17.attn.k_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.17.attn.proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.17.attn.proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.17.attn.proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.17.attn.proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.17.attn.q_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.17.attn.qkv.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.17.attn.qkv.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.17.attn.qkv.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.17.attn.qkv.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.17.mlp.down_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.17.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.17.mlp.down_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.17.mlp.down_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.17.mlp.gate_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.17.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.17.mlp.gate_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.17.mlp.gate_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.17.mlp.up_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.17.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.17.mlp.up_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.17.mlp.up_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.17.norm1.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.17.norm2.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.18.attn.k_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.18.attn.proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.18.attn.proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.18.attn.proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.18.attn.proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.18.attn.q_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.18.attn.qkv.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.18.attn.qkv.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.18.attn.qkv.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.18.attn.qkv.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.18.mlp.down_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.18.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.18.mlp.down_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.18.mlp.down_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.18.mlp.gate_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.18.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.18.mlp.gate_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.18.mlp.gate_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.18.mlp.up_proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.18.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.18.mlp.up_proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.18.mlp.up_proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.18.norm1.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.18.norm2.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.19.attn.k_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.19.attn.proj.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.19.attn.proj.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.19.attn.proj.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.19.attn.proj.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.19.attn.q_norm.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.19.attn.qkv.bias": "model-00025-of-00027.safetensors",
  "visual.blocks.19.attn.qkv.weight": "model-00025-of-00027.safetensors",
  "visual.blocks.19.attn.qkv.scales": "model-00025-of-00027.safetensors",
  "visual.blocks.19.attn.qkv.biases": "model-00025-of-00027.safetensors",
  "visual.blocks.19.mlp.down_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.19.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.19.mlp.down_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.19.mlp.down_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.19.mlp.gate_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.19.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.19.mlp.gate_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.19.mlp.gate_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.19.mlp.up_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.19.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.19.mlp.up_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.19.mlp.up_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.19.norm1.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.19.norm2.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.2.attn.k_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.2.attn.proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.2.attn.proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.2.attn.proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.2.attn.proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.2.attn.q_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.2.attn.qkv.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.2.attn.qkv.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.2.attn.qkv.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.2.attn.qkv.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.2.mlp.down_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.2.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.2.mlp.down_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.2.mlp.down_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.2.mlp.gate_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.2.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.2.mlp.gate_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.2.mlp.gate_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.2.mlp.up_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.2.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.2.mlp.up_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.2.mlp.up_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.2.norm1.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.2.norm2.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.20.attn.k_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.20.attn.proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.20.attn.proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.20.attn.proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.20.attn.proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.20.attn.q_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.20.attn.qkv.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.20.attn.qkv.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.20.attn.qkv.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.20.attn.qkv.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.20.mlp.down_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.20.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.20.mlp.down_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.20.mlp.down_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.20.mlp.gate_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.20.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.20.mlp.gate_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.20.mlp.gate_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.20.mlp.up_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.20.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.20.mlp.up_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.20.mlp.up_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.20.norm1.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.20.norm2.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.21.attn.k_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.21.attn.proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.21.attn.proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.21.attn.proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.21.attn.proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.21.attn.q_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.21.attn.qkv.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.21.attn.qkv.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.21.attn.qkv.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.21.attn.qkv.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.21.mlp.down_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.21.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.21.mlp.down_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.21.mlp.down_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.21.mlp.gate_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.21.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.21.mlp.gate_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.21.mlp.gate_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.21.mlp.up_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.21.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.21.mlp.up_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.21.mlp.up_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.21.norm1.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.21.norm2.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.22.attn.k_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.22.attn.proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.22.attn.proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.22.attn.proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.22.attn.proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.22.attn.q_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.22.attn.qkv.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.22.attn.qkv.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.22.attn.qkv.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.22.attn.qkv.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.22.mlp.down_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.22.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.22.mlp.down_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.22.mlp.down_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.22.mlp.gate_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.22.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.22.mlp.gate_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.22.mlp.gate_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.22.mlp.up_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.22.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.22.mlp.up_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.22.mlp.up_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.22.norm1.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.22.norm2.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.23.attn.k_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.23.attn.proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.23.attn.proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.23.attn.proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.23.attn.proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.23.attn.q_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.23.attn.qkv.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.23.attn.qkv.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.23.attn.qkv.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.23.attn.qkv.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.23.mlp.down_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.23.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.23.mlp.down_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.23.mlp.down_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.23.mlp.gate_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.23.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.23.mlp.gate_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.23.mlp.gate_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.23.mlp.up_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.23.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.23.mlp.up_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.23.mlp.up_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.23.norm1.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.23.norm2.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.3.attn.k_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.3.attn.proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.3.attn.proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.3.attn.proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.3.attn.proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.3.attn.q_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.3.attn.qkv.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.3.attn.qkv.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.3.attn.qkv.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.3.attn.qkv.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.3.mlp.down_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.3.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.3.mlp.down_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.3.mlp.down_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.3.mlp.gate_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.3.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.3.mlp.gate_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.3.mlp.gate_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.3.mlp.up_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.3.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.3.mlp.up_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.3.mlp.up_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.3.norm1.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.3.norm2.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.4.attn.k_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.4.attn.proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.4.attn.proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.4.attn.proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.4.attn.proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.4.attn.q_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.4.attn.qkv.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.4.attn.qkv.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.4.attn.qkv.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.4.attn.qkv.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.4.mlp.down_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.4.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.4.mlp.down_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.4.mlp.down_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.4.mlp.gate_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.4.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.4.mlp.gate_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.4.mlp.gate_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.4.mlp.up_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.4.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.4.mlp.up_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.4.mlp.up_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.4.norm1.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.4.norm2.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.5.attn.k_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.5.attn.proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.5.attn.proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.5.attn.proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.5.attn.proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.5.attn.q_norm.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.5.attn.qkv.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.5.attn.qkv.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.5.attn.qkv.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.5.attn.qkv.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.5.mlp.down_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.5.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.5.mlp.down_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.5.mlp.down_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.5.mlp.gate_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.5.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.5.mlp.gate_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.5.mlp.gate_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.5.mlp.up_proj.bias": "model-00026-of-00027.safetensors",
  "visual.blocks.5.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.5.mlp.up_proj.scales": "model-00026-of-00027.safetensors",
  "visual.blocks.5.mlp.up_proj.biases": "model-00026-of-00027.safetensors",
  "visual.blocks.5.norm1.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.5.norm2.weight": "model-00026-of-00027.safetensors",
  "visual.blocks.6.attn.k_norm.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.6.attn.proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.6.attn.proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.6.attn.proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.6.attn.proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.6.attn.q_norm.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.6.attn.qkv.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.6.attn.qkv.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.6.attn.qkv.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.6.attn.qkv.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.6.mlp.down_proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.6.mlp.down_proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.6.mlp.down_proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.6.mlp.down_proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.6.mlp.gate_proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.6.mlp.gate_proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.6.mlp.gate_proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.6.mlp.gate_proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.6.mlp.up_proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.6.mlp.up_proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.6.mlp.up_proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.6.mlp.up_proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.6.norm1.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.6.norm2.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.7.attn.k_norm.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.7.attn.proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.7.attn.proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.7.attn.proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.7.attn.proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.7.attn.q_norm.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.7.attn.qkv.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.7.attn.qkv.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.7.attn.qkv.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.7.attn.qkv.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.7.mlp.down_proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.7.mlp.down_proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.7.mlp.down_proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.7.mlp.down_proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.7.mlp.gate_proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.7.mlp.gate_proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.7.mlp.gate_proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.7.mlp.gate_proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.7.mlp.up_proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.7.mlp.up_proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.7.mlp.up_proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.7.mlp.up_proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.7.norm1.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.7.norm2.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.8.attn.k_norm.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.8.attn.proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.8.attn.proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.8.attn.proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.8.attn.proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.8.attn.q_norm.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.8.attn.qkv.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.8.attn.qkv.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.8.attn.qkv.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.8.attn.qkv.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.8.mlp.down_proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.8.mlp.down_proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.8.mlp.down_proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.8.mlp.down_proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.8.mlp.gate_proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.8.mlp.gate_proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.8.mlp.gate_proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.8.mlp.gate_proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.8.mlp.up_proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.8.mlp.up_proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.8.mlp.up_proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.8.mlp.up_proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.8.norm1.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.8.norm2.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.9.attn.k_norm.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.9.attn.proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.9.attn.proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.9.attn.proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.9.attn.proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.9.attn.q_norm.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.9.attn.qkv.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.9.attn.qkv.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.9.attn.qkv.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.9.attn.qkv.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.9.mlp.down_proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.9.mlp.down_proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.9.mlp.down_proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.9.mlp.down_proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.9.mlp.gate_proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.9.mlp.gate_proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.9.mlp.gate_proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.9.mlp.gate_proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.9.mlp.up_proj.bias": "model-00027-of-00027.safetensors",
  "visual.blocks.9.mlp.up_proj.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.9.mlp.up_proj.scales": "model-00027-of-00027.safetensors",
  "visual.blocks.9.mlp.up_proj.biases": "model-00027-of-00027.safetensors",
  "visual.blocks.9.norm1.weight": "model-00027-of-00027.safetensors",
  "visual.blocks.9.norm2.weight": "model-00027-of-00027.safetensors",
  "visual.downsample.bias": "model-00027-of-00027.safetensors",
  "visual.downsample.weight": "model-00027-of-00027.safetensors",
  "visual.merger.down_proj.weight": "model-00027-of-00027.safetensors",
  "visual.merger.down_proj.scales": "model-00027-of-00027.safetensors",
  "visual.merger.down_proj.biases": "model-00027-of-00027.safetensors",
  "visual.merger.gate_proj.weight": "model-00027-of-00027.safetensors",
  "visual.merger.gate_proj.scales": "model-00027-of-00027.safetensors",
  "visual.merger.gate_proj.biases": "model-00027-of-00027.safetensors",
  "visual.merger.post_projection_norm.bias": "model-00027-of-00027.safetensors",
  "visual.merger.post_projection_norm.weight": "model-00027-of-00027.safetensors",
  "visual.merger.proj.weight": "model-00027-of-00027.safetensors",
  "visual.merger.proj.scales": "model-00027-of-00027.safetensors",
  "visual.merger.proj.biases": "model-00027-of-00027.safetensors",
  "visual.merger.up_proj.weight": "model-00027-of-00027.safetensors",
  "visual.merger.up_proj.scales": "model-00027-of-00027.safetensors",
  "visual.merger.up_proj.biases": "model-00027-of-00027.safetensors",
  "visual.patch_embed.proj.bias": "model-00027-of-00027.safetensors",
  "visual.patch_embed.proj.weight": "model-00027-of-00027.safetensors",
  "visual.post_layernorm.weight": "model-00027-of-00027.safetensors"
 }
}