terryyz's picture
Upload LlamaMoEUpscalingForCausalLM
bdea83b verified
{
"metadata": {
"total_size": 148168005760
},
"weight_map": {
"lm_head.weight": "model-00030-of-00030.safetensors",
"model.embed_tokens.weight": "model-00001-of-00030.safetensors",
"model.layers.0.input_layernorm.weight": "model-00002-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_down.0.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_down.1.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_down.2.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_down.3.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_down.4.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_down.5.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_down.6.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_down.7.weight": "model-00002-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_gate.0.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_gate.1.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_gate.2.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_gate.3.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_gate.4.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_gate.5.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_gate.6.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_gate.7.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_up.0.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_up.1.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_up.2.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_up.3.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_up.4.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_up.5.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_up.6.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.calculator.experts.weight_up.7.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.gate.gate_network.0.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.gate.gate_network.2.weight": "model-00001-of-00030.safetensors",
"model.layers.0.mlp.gate.weight_noise.weight": "model-00001-of-00030.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
"model.layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_down.0.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_down.1.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_down.2.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_down.3.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_down.4.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_down.5.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_down.6.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_down.7.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_gate.0.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_gate.1.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_gate.2.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_gate.3.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_gate.4.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_gate.5.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_gate.6.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_gate.7.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_up.0.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_up.1.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_up.2.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_up.3.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_up.4.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_up.5.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_up.6.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.calculator.experts.weight_up.7.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.gate.gate_network.0.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.gate.gate_network.2.weight": "model-00002-of-00030.safetensors",
"model.layers.1.mlp.gate.weight_noise.weight": "model-00002-of-00030.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
"model.layers.10.input_layernorm.weight": "model-00011-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_down.0.weight": "model-00011-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_down.1.weight": "model-00011-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_down.2.weight": "model-00011-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_down.3.weight": "model-00011-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_down.4.weight": "model-00011-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_down.5.weight": "model-00011-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_down.6.weight": "model-00011-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_down.7.weight": "model-00011-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_gate.0.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_gate.1.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_gate.2.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_gate.3.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_gate.4.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_gate.5.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_gate.6.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_gate.7.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_up.0.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_up.1.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_up.2.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_up.3.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_up.4.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_up.5.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_up.6.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.calculator.experts.weight_up.7.weight": "model-00011-of-00030.safetensors",
"model.layers.10.mlp.gate.gate_network.0.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.gate.gate_network.2.weight": "model-00010-of-00030.safetensors",
"model.layers.10.mlp.gate.weight_noise.weight": "model-00010-of-00030.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
"model.layers.11.input_layernorm.weight": "model-00012-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_down.0.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_down.1.weight": "model-00012-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_down.2.weight": "model-00012-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_down.3.weight": "model-00012-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_down.4.weight": "model-00012-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_down.5.weight": "model-00012-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_down.6.weight": "model-00012-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_down.7.weight": "model-00012-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_gate.0.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_gate.1.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_gate.2.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_gate.3.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_gate.4.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_gate.5.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_gate.6.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_gate.7.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_up.0.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_up.1.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_up.2.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_up.3.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_up.4.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_up.5.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_up.6.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.calculator.experts.weight_up.7.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.gate.gate_network.0.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.gate.gate_network.2.weight": "model-00011-of-00030.safetensors",
"model.layers.11.mlp.gate.weight_noise.weight": "model-00011-of-00030.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
"model.layers.12.input_layernorm.weight": "model-00013-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_down.0.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_down.1.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_down.2.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_down.3.weight": "model-00013-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_down.4.weight": "model-00013-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_down.5.weight": "model-00013-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_down.6.weight": "model-00013-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_down.7.weight": "model-00013-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_gate.0.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_gate.1.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_gate.2.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_gate.3.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_gate.4.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_gate.5.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_gate.6.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_gate.7.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_up.0.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_up.1.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_up.2.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_up.3.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_up.4.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_up.5.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_up.6.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.calculator.experts.weight_up.7.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.gate.gate_network.0.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.gate.gate_network.2.weight": "model-00012-of-00030.safetensors",
"model.layers.12.mlp.gate.weight_noise.weight": "model-00012-of-00030.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
"model.layers.13.input_layernorm.weight": "model-00014-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_down.0.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_down.1.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_down.2.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_down.3.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_down.4.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_down.5.weight": "model-00014-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_down.6.weight": "model-00014-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_down.7.weight": "model-00014-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_gate.0.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_gate.1.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_gate.2.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_gate.3.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_gate.4.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_gate.5.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_gate.6.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_gate.7.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_up.0.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_up.1.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_up.2.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_up.3.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_up.4.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_up.5.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_up.6.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.calculator.experts.weight_up.7.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.gate.gate_network.0.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.gate.gate_network.2.weight": "model-00013-of-00030.safetensors",
"model.layers.13.mlp.gate.weight_noise.weight": "model-00013-of-00030.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
"model.layers.14.input_layernorm.weight": "model-00015-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_down.0.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_down.1.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_down.2.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_down.3.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_down.4.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_down.5.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_down.6.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_down.7.weight": "model-00015-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_gate.0.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_gate.1.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_gate.2.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_gate.3.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_gate.4.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_gate.5.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_gate.6.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_gate.7.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_up.0.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_up.1.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_up.2.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_up.3.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_up.4.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_up.5.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_up.6.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.calculator.experts.weight_up.7.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.gate.gate_network.0.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.gate.gate_network.2.weight": "model-00014-of-00030.safetensors",
"model.layers.14.mlp.gate.weight_noise.weight": "model-00014-of-00030.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
"model.layers.15.input_layernorm.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_down.0.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_down.1.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_down.2.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_down.3.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_down.4.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_down.5.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_down.6.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_down.7.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_gate.0.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_gate.1.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_gate.2.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_gate.3.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_gate.4.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_gate.5.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_gate.6.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_gate.7.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_up.0.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_up.1.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_up.2.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_up.3.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_up.4.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_up.5.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_up.6.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.calculator.experts.weight_up.7.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.gate.gate_network.0.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.gate.gate_network.2.weight": "model-00015-of-00030.safetensors",
"model.layers.15.mlp.gate.weight_noise.weight": "model-00015-of-00030.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
"model.layers.16.input_layernorm.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_down.0.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_down.1.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_down.2.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_down.3.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_down.4.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_down.5.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_down.6.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_down.7.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_gate.0.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_gate.1.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_gate.2.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_gate.3.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_gate.4.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_gate.5.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_gate.6.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_gate.7.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_up.0.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_up.1.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_up.2.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_up.3.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_up.4.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_up.5.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_up.6.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.calculator.experts.weight_up.7.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.gate.gate_network.0.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.gate.gate_network.2.weight": "model-00016-of-00030.safetensors",
"model.layers.16.mlp.gate.weight_noise.weight": "model-00016-of-00030.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
"model.layers.17.input_layernorm.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_down.0.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_down.1.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_down.2.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_down.3.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_down.4.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_down.5.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_down.6.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_down.7.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_gate.0.weight": "model-00016-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_gate.1.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_gate.2.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_gate.3.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_gate.4.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_gate.5.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_gate.6.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_gate.7.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_up.0.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_up.1.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_up.2.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_up.3.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_up.4.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_up.5.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_up.6.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.calculator.experts.weight_up.7.weight": "model-00017-of-00030.safetensors",
"model.layers.17.mlp.gate.gate_network.0.weight": "model-00016-of-00030.safetensors",
"model.layers.17.mlp.gate.gate_network.2.weight": "model-00016-of-00030.safetensors",
"model.layers.17.mlp.gate.weight_noise.weight": "model-00016-of-00030.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
"model.layers.18.input_layernorm.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_down.0.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_down.1.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_down.2.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_down.3.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_down.4.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_down.5.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_down.6.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_down.7.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_gate.0.weight": "model-00017-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_gate.1.weight": "model-00017-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_gate.2.weight": "model-00017-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_gate.3.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_gate.4.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_gate.5.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_gate.6.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_gate.7.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_up.0.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_up.1.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_up.2.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_up.3.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_up.4.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_up.5.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_up.6.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.calculator.experts.weight_up.7.weight": "model-00018-of-00030.safetensors",
"model.layers.18.mlp.gate.gate_network.0.weight": "model-00017-of-00030.safetensors",
"model.layers.18.mlp.gate.gate_network.2.weight": "model-00017-of-00030.safetensors",
"model.layers.18.mlp.gate.weight_noise.weight": "model-00017-of-00030.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
"model.layers.19.input_layernorm.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_down.0.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_down.1.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_down.2.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_down.3.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_down.4.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_down.5.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_down.6.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_down.7.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_gate.0.weight": "model-00018-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_gate.1.weight": "model-00018-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_gate.2.weight": "model-00018-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_gate.3.weight": "model-00018-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_gate.4.weight": "model-00018-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_gate.5.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_gate.6.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_gate.7.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_up.0.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_up.1.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_up.2.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_up.3.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_up.4.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_up.5.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_up.6.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.calculator.experts.weight_up.7.weight": "model-00019-of-00030.safetensors",
"model.layers.19.mlp.gate.gate_network.0.weight": "model-00018-of-00030.safetensors",
"model.layers.19.mlp.gate.gate_network.2.weight": "model-00018-of-00030.safetensors",
"model.layers.19.mlp.gate.weight_noise.weight": "model-00018-of-00030.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
"model.layers.2.input_layernorm.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_down.0.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_down.1.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_down.2.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_down.3.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_down.4.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_down.5.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_down.6.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_down.7.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_gate.0.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_gate.1.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_gate.2.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_gate.3.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_gate.4.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_gate.5.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_gate.6.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_gate.7.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_up.0.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_up.1.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_up.2.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_up.3.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_up.4.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_up.5.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_up.6.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.calculator.experts.weight_up.7.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.gate.gate_network.0.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.gate.gate_network.2.weight": "model-00003-of-00030.safetensors",
"model.layers.2.mlp.gate.weight_noise.weight": "model-00003-of-00030.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
"model.layers.20.input_layernorm.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_down.0.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_down.1.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_down.2.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_down.3.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_down.4.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_down.5.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_down.6.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_down.7.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_gate.0.weight": "model-00019-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_gate.1.weight": "model-00019-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_gate.2.weight": "model-00019-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_gate.3.weight": "model-00019-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_gate.4.weight": "model-00019-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_gate.5.weight": "model-00019-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_gate.6.weight": "model-00019-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_gate.7.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_up.0.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_up.1.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_up.2.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_up.3.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_up.4.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_up.5.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_up.6.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.calculator.experts.weight_up.7.weight": "model-00020-of-00030.safetensors",
"model.layers.20.mlp.gate.gate_network.0.weight": "model-00019-of-00030.safetensors",
"model.layers.20.mlp.gate.gate_network.2.weight": "model-00019-of-00030.safetensors",
"model.layers.20.mlp.gate.weight_noise.weight": "model-00019-of-00030.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
"model.layers.21.input_layernorm.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_down.0.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_down.1.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_down.2.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_down.3.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_down.4.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_down.5.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_down.6.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_down.7.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_gate.0.weight": "model-00020-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_gate.1.weight": "model-00020-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_gate.2.weight": "model-00020-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_gate.3.weight": "model-00020-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_gate.4.weight": "model-00020-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_gate.5.weight": "model-00020-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_gate.6.weight": "model-00020-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_gate.7.weight": "model-00020-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_up.0.weight": "model-00020-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_up.1.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_up.2.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_up.3.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_up.4.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_up.5.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_up.6.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.calculator.experts.weight_up.7.weight": "model-00021-of-00030.safetensors",
"model.layers.21.mlp.gate.gate_network.0.weight": "model-00020-of-00030.safetensors",
"model.layers.21.mlp.gate.gate_network.2.weight": "model-00020-of-00030.safetensors",
"model.layers.21.mlp.gate.weight_noise.weight": "model-00020-of-00030.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
"model.layers.22.input_layernorm.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_down.0.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_down.1.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_down.2.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_down.3.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_down.4.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_down.5.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_down.6.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_down.7.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_gate.0.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_gate.1.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_gate.2.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_gate.3.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_gate.4.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_gate.5.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_gate.6.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_gate.7.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_up.0.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_up.1.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_up.2.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_up.3.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_up.4.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_up.5.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_up.6.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.calculator.experts.weight_up.7.weight": "model-00022-of-00030.safetensors",
"model.layers.22.mlp.gate.gate_network.0.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.gate.gate_network.2.weight": "model-00021-of-00030.safetensors",
"model.layers.22.mlp.gate.weight_noise.weight": "model-00021-of-00030.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
"model.layers.23.input_layernorm.weight": "model-00023-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_down.0.weight": "model-00023-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_down.1.weight": "model-00023-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_down.2.weight": "model-00023-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_down.3.weight": "model-00023-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_down.4.weight": "model-00023-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_down.5.weight": "model-00023-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_down.6.weight": "model-00023-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_down.7.weight": "model-00023-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_gate.0.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_gate.1.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_gate.2.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_gate.3.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_gate.4.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_gate.5.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_gate.6.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_gate.7.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_up.0.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_up.1.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_up.2.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_up.3.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_up.4.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_up.5.weight": "model-00023-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_up.6.weight": "model-00023-of-00030.safetensors",
"model.layers.23.mlp.calculator.experts.weight_up.7.weight": "model-00023-of-00030.safetensors",
"model.layers.23.mlp.gate.gate_network.0.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.gate.gate_network.2.weight": "model-00022-of-00030.safetensors",
"model.layers.23.mlp.gate.weight_noise.weight": "model-00022-of-00030.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
"model.layers.24.input_layernorm.weight": "model-00024-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_down.0.weight": "model-00024-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_down.1.weight": "model-00024-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_down.2.weight": "model-00024-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_down.3.weight": "model-00024-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_down.4.weight": "model-00024-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_down.5.weight": "model-00024-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_down.6.weight": "model-00024-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_down.7.weight": "model-00024-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_gate.0.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_gate.1.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_gate.2.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_gate.3.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_gate.4.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_gate.5.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_gate.6.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_gate.7.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_up.0.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_up.1.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_up.2.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_up.3.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_up.4.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_up.5.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_up.6.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.calculator.experts.weight_up.7.weight": "model-00024-of-00030.safetensors",
"model.layers.24.mlp.gate.gate_network.0.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.gate.gate_network.2.weight": "model-00023-of-00030.safetensors",
"model.layers.24.mlp.gate.weight_noise.weight": "model-00023-of-00030.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
"model.layers.25.input_layernorm.weight": "model-00025-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_down.0.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_down.1.weight": "model-00025-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_down.2.weight": "model-00025-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_down.3.weight": "model-00025-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_down.4.weight": "model-00025-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_down.5.weight": "model-00025-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_down.6.weight": "model-00025-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_down.7.weight": "model-00025-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_gate.0.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_gate.1.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_gate.2.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_gate.3.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_gate.4.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_gate.5.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_gate.6.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_gate.7.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_up.0.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_up.1.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_up.2.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_up.3.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_up.4.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_up.5.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_up.6.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.calculator.experts.weight_up.7.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.gate.gate_network.0.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.gate.gate_network.2.weight": "model-00024-of-00030.safetensors",
"model.layers.25.mlp.gate.weight_noise.weight": "model-00024-of-00030.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
"model.layers.26.input_layernorm.weight": "model-00026-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_down.0.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_down.1.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_down.2.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_down.3.weight": "model-00026-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_down.4.weight": "model-00026-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_down.5.weight": "model-00026-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_down.6.weight": "model-00026-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_down.7.weight": "model-00026-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_gate.0.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_gate.1.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_gate.2.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_gate.3.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_gate.4.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_gate.5.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_gate.6.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_gate.7.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_up.0.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_up.1.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_up.2.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_up.3.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_up.4.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_up.5.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_up.6.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.calculator.experts.weight_up.7.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.gate.gate_network.0.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.gate.gate_network.2.weight": "model-00025-of-00030.safetensors",
"model.layers.26.mlp.gate.weight_noise.weight": "model-00025-of-00030.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
"model.layers.27.input_layernorm.weight": "model-00027-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_down.0.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_down.1.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_down.2.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_down.3.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_down.4.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_down.5.weight": "model-00027-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_down.6.weight": "model-00027-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_down.7.weight": "model-00027-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_gate.0.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_gate.1.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_gate.2.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_gate.3.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_gate.4.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_gate.5.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_gate.6.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_gate.7.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_up.0.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_up.1.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_up.2.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_up.3.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_up.4.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_up.5.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_up.6.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.calculator.experts.weight_up.7.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.gate.gate_network.0.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.gate.gate_network.2.weight": "model-00026-of-00030.safetensors",
"model.layers.27.mlp.gate.weight_noise.weight": "model-00026-of-00030.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
"model.layers.28.input_layernorm.weight": "model-00028-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_down.0.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_down.1.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_down.2.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_down.3.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_down.4.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_down.5.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_down.6.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_down.7.weight": "model-00028-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_gate.0.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_gate.1.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_gate.2.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_gate.3.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_gate.4.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_gate.5.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_gate.6.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_gate.7.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_up.0.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_up.1.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_up.2.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_up.3.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_up.4.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_up.5.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_up.6.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.calculator.experts.weight_up.7.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.gate.gate_network.0.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.gate.gate_network.2.weight": "model-00027-of-00030.safetensors",
"model.layers.28.mlp.gate.weight_noise.weight": "model-00027-of-00030.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
"model.layers.29.input_layernorm.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_down.0.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_down.1.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_down.2.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_down.3.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_down.4.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_down.5.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_down.6.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_down.7.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_gate.0.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_gate.1.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_gate.2.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_gate.3.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_gate.4.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_gate.5.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_gate.6.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_gate.7.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_up.0.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_up.1.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_up.2.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_up.3.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_up.4.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_up.5.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_up.6.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.calculator.experts.weight_up.7.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.gate.gate_network.0.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.gate.gate_network.2.weight": "model-00028-of-00030.safetensors",
"model.layers.29.mlp.gate.weight_noise.weight": "model-00028-of-00030.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
"model.layers.3.input_layernorm.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_down.0.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_down.1.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_down.2.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_down.3.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_down.4.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_down.5.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_down.6.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_down.7.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_gate.0.weight": "model-00003-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_gate.1.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_gate.2.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_gate.3.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_gate.4.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_gate.5.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_gate.6.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_gate.7.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_up.0.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_up.1.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_up.2.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_up.3.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_up.4.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_up.5.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_up.6.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.calculator.experts.weight_up.7.weight": "model-00004-of-00030.safetensors",
"model.layers.3.mlp.gate.gate_network.0.weight": "model-00003-of-00030.safetensors",
"model.layers.3.mlp.gate.gate_network.2.weight": "model-00003-of-00030.safetensors",
"model.layers.3.mlp.gate.weight_noise.weight": "model-00003-of-00030.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
"model.layers.30.input_layernorm.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_down.0.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_down.1.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_down.2.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_down.3.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_down.4.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_down.5.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_down.6.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_down.7.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_gate.0.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_gate.1.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_gate.2.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_gate.3.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_gate.4.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_gate.5.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_gate.6.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_gate.7.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_up.0.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_up.1.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_up.2.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_up.3.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_up.4.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_up.5.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_up.6.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.calculator.experts.weight_up.7.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.gate.gate_network.0.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.gate.gate_network.2.weight": "model-00029-of-00030.safetensors",
"model.layers.30.mlp.gate.weight_noise.weight": "model-00029-of-00030.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
"model.layers.31.input_layernorm.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_down.0.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_down.1.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_down.2.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_down.3.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_down.4.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_down.5.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_down.6.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_down.7.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_gate.0.weight": "model-00029-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_gate.1.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_gate.2.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_gate.3.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_gate.4.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_gate.5.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_gate.6.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_gate.7.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_up.0.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_up.1.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_up.2.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_up.3.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_up.4.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_up.5.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_up.6.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.calculator.experts.weight_up.7.weight": "model-00030-of-00030.safetensors",
"model.layers.31.mlp.gate.gate_network.0.weight": "model-00029-of-00030.safetensors",
"model.layers.31.mlp.gate.gate_network.2.weight": "model-00029-of-00030.safetensors",
"model.layers.31.mlp.gate.weight_noise.weight": "model-00029-of-00030.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00030-of-00030.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
"model.layers.4.input_layernorm.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_down.0.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_down.1.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_down.2.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_down.3.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_down.4.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_down.5.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_down.6.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_down.7.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_gate.0.weight": "model-00004-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_gate.1.weight": "model-00004-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_gate.2.weight": "model-00004-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_gate.3.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_gate.4.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_gate.5.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_gate.6.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_gate.7.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_up.0.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_up.1.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_up.2.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_up.3.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_up.4.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_up.5.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_up.6.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.calculator.experts.weight_up.7.weight": "model-00005-of-00030.safetensors",
"model.layers.4.mlp.gate.gate_network.0.weight": "model-00004-of-00030.safetensors",
"model.layers.4.mlp.gate.gate_network.2.weight": "model-00004-of-00030.safetensors",
"model.layers.4.mlp.gate.weight_noise.weight": "model-00004-of-00030.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
"model.layers.5.input_layernorm.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_down.0.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_down.1.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_down.2.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_down.3.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_down.4.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_down.5.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_down.6.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_down.7.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_gate.0.weight": "model-00005-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_gate.1.weight": "model-00005-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_gate.2.weight": "model-00005-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_gate.3.weight": "model-00005-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_gate.4.weight": "model-00005-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_gate.5.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_gate.6.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_gate.7.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_up.0.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_up.1.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_up.2.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_up.3.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_up.4.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_up.5.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_up.6.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.calculator.experts.weight_up.7.weight": "model-00006-of-00030.safetensors",
"model.layers.5.mlp.gate.gate_network.0.weight": "model-00005-of-00030.safetensors",
"model.layers.5.mlp.gate.gate_network.2.weight": "model-00005-of-00030.safetensors",
"model.layers.5.mlp.gate.weight_noise.weight": "model-00005-of-00030.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
"model.layers.6.input_layernorm.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_down.0.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_down.1.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_down.2.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_down.3.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_down.4.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_down.5.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_down.6.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_down.7.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_gate.0.weight": "model-00006-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_gate.1.weight": "model-00006-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_gate.2.weight": "model-00006-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_gate.3.weight": "model-00006-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_gate.4.weight": "model-00006-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_gate.5.weight": "model-00006-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_gate.6.weight": "model-00006-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_gate.7.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_up.0.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_up.1.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_up.2.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_up.3.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_up.4.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_up.5.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_up.6.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.calculator.experts.weight_up.7.weight": "model-00007-of-00030.safetensors",
"model.layers.6.mlp.gate.gate_network.0.weight": "model-00006-of-00030.safetensors",
"model.layers.6.mlp.gate.gate_network.2.weight": "model-00006-of-00030.safetensors",
"model.layers.6.mlp.gate.weight_noise.weight": "model-00006-of-00030.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
"model.layers.7.input_layernorm.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_down.0.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_down.1.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_down.2.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_down.3.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_down.4.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_down.5.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_down.6.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_down.7.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_gate.0.weight": "model-00007-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_gate.1.weight": "model-00007-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_gate.2.weight": "model-00007-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_gate.3.weight": "model-00007-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_gate.4.weight": "model-00007-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_gate.5.weight": "model-00007-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_gate.6.weight": "model-00007-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_gate.7.weight": "model-00007-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_up.0.weight": "model-00007-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_up.1.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_up.2.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_up.3.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_up.4.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_up.5.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_up.6.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.calculator.experts.weight_up.7.weight": "model-00008-of-00030.safetensors",
"model.layers.7.mlp.gate.gate_network.0.weight": "model-00007-of-00030.safetensors",
"model.layers.7.mlp.gate.gate_network.2.weight": "model-00007-of-00030.safetensors",
"model.layers.7.mlp.gate.weight_noise.weight": "model-00007-of-00030.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
"model.layers.8.input_layernorm.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_down.0.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_down.1.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_down.2.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_down.3.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_down.4.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_down.5.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_down.6.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_down.7.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_gate.0.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_gate.1.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_gate.2.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_gate.3.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_gate.4.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_gate.5.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_gate.6.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_gate.7.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_up.0.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_up.1.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_up.2.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_up.3.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_up.4.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_up.5.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_up.6.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.calculator.experts.weight_up.7.weight": "model-00009-of-00030.safetensors",
"model.layers.8.mlp.gate.gate_network.0.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.gate.gate_network.2.weight": "model-00008-of-00030.safetensors",
"model.layers.8.mlp.gate.weight_noise.weight": "model-00008-of-00030.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
"model.layers.9.input_layernorm.weight": "model-00010-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_down.0.weight": "model-00010-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_down.1.weight": "model-00010-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_down.2.weight": "model-00010-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_down.3.weight": "model-00010-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_down.4.weight": "model-00010-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_down.5.weight": "model-00010-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_down.6.weight": "model-00010-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_down.7.weight": "model-00010-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_gate.0.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_gate.1.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_gate.2.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_gate.3.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_gate.4.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_gate.5.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_gate.6.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_gate.7.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_up.0.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_up.1.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_up.2.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_up.3.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_up.4.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_up.5.weight": "model-00010-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_up.6.weight": "model-00010-of-00030.safetensors",
"model.layers.9.mlp.calculator.experts.weight_up.7.weight": "model-00010-of-00030.safetensors",
"model.layers.9.mlp.gate.gate_network.0.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.gate.gate_network.2.weight": "model-00009-of-00030.safetensors",
"model.layers.9.mlp.gate.weight_noise.weight": "model-00009-of-00030.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
"model.norm.weight": "model-00030-of-00030.safetensors"
}
}