{ "weight_map": { "lm_head.biases": "model-00014-00027.safetensors", "lm_head.scales": "model-00014-00027.safetensors", "lm_head.weight": "model-00014-00027.safetensors", "model.layers.14.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.14.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.14.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.14.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.14.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.14.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.14.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.14.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.14.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.14.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.14.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.14.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.14.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.14.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.14.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.14.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.14.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.layers.15.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.15.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.15.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.15.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.15.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.15.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.15.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.15.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.15.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.15.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.15.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.15.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.15.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.15.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.15.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.15.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.15.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.layers.16.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.16.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.16.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.16.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.16.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.16.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.16.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.16.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.16.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.16.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.16.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.16.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.16.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.16.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.16.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.16.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.16.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.layers.17.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.17.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.17.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.17.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.17.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.17.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.17.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.17.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.17.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.17.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.17.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.17.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.17.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.17.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.17.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.17.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.17.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.layers.18.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.18.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.18.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.18.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.18.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.18.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.18.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.18.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.18.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.18.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.18.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.18.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.18.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.18.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.18.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.18.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.18.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.layers.19.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.19.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.19.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.19.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.19.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.19.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.19.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.19.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.19.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.19.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.19.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.19.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.19.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.19.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.19.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.19.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.layers.20.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.20.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.20.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.20.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.20.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.20.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.20.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.20.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.20.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.20.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.20.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.20.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.20.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.20.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.20.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.20.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.20.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.layers.21.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.21.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.21.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.21.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.21.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.21.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.21.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.21.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.21.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.21.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.21.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.21.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.21.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.21.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.21.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.21.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.21.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.22.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.22.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.22.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.22.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.22.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.22.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.22.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.22.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.22.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.22.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.22.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.22.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.22.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.22.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.22.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.22.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.23.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.23.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.23.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.23.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.23.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.23.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.23.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.23.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.23.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.23.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.23.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.23.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.23.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.23.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.23.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.layers.24.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.24.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.24.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.24.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.24.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.24.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.24.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.24.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.24.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.24.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.24.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.24.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.24.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.24.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.24.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.24.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.24.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.24.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.layers.25.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.25.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.25.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.25.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.25.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.25.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.25.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.25.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.25.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.25.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.25.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.25.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.25.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.25.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.25.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.25.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.25.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.25.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.layers.26.input_layernorm.weight": "model-00014-00027.safetensors", "model.layers.26.mlp.gate.weight": "model-00014-00027.safetensors", "model.layers.26.mlp.shared_experts.down_proj.biases": "model-00014-00027.safetensors", "model.layers.26.mlp.shared_experts.down_proj.scales": "model-00014-00027.safetensors", "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00014-00027.safetensors", "model.layers.26.mlp.shared_experts.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.26.mlp.shared_experts.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.26.mlp.shared_experts.up_proj.biases": "model-00014-00027.safetensors", "model.layers.26.mlp.shared_experts.up_proj.scales": "model-00014-00027.safetensors", "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00014-00027.safetensors", "model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00014-00027.safetensors", "model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00014-00027.safetensors", "model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00014-00027.safetensors", "model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00014-00027.safetensors", "model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00014-00027.safetensors", "model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00014-00027.safetensors", "model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00014-00027.safetensors", "model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00014-00027.safetensors", "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00014-00027.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-00027.safetensors", "model.layers.26.self_attn.kv_a_layernorm.weight": "model-00014-00027.safetensors", "model.layers.26.self_attn.kv_a_proj_with_mqa.biases": "model-00014-00027.safetensors", "model.layers.26.self_attn.kv_a_proj_with_mqa.scales": "model-00014-00027.safetensors", "model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00014-00027.safetensors", "model.layers.26.self_attn.kv_b_proj.biases": "model-00014-00027.safetensors", "model.layers.26.self_attn.kv_b_proj.scales": "model-00014-00027.safetensors", "model.layers.26.self_attn.kv_b_proj.weight": "model-00014-00027.safetensors", "model.layers.26.self_attn.o_proj.biases": "model-00014-00027.safetensors", "model.layers.26.self_attn.o_proj.scales": "model-00014-00027.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00014-00027.safetensors", "model.layers.26.self_attn.q_proj.biases": "model-00014-00027.safetensors", "model.layers.26.self_attn.q_proj.scales": "model-00014-00027.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-00027.safetensors", "model.norm.weight": "model-00014-00027.safetensors" } }