{ "metadata": { "total_parameters": 3981641728, "total_size": 7963283456 }, "weight_map": { "embed_tokens.weight": "model-00001-of-00002.safetensors", "final_norm.weight": "model-00002-of-00002.safetensors", "layers.0.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.gate.0.weight": "model-00001-of-00002.safetensors", "layers.0.block_sparse_moe.gate.1.weight": "model-00001-of-00002.safetensors", "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.gate.0.weight": "model-00001-of-00002.safetensors", "layers.1.block_sparse_moe.gate.1.weight": "model-00001-of-00002.safetensors", "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "layers.10.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "layers.10.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.10.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "layers.10.block_sparse_moe.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "layers.10.block_sparse_moe.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.10.block_sparse_moe.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "layers.10.block_sparse_moe.experts.2.down_proj.weight": "model-00002-of-00002.safetensors", "layers.10.block_sparse_moe.experts.2.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.10.block_sparse_moe.experts.2.up_proj.weight": "model-00002-of-00002.safetensors", "layers.10.block_sparse_moe.experts.3.down_proj.weight": "model-00002-of-00002.safetensors", "layers.10.block_sparse_moe.experts.3.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.10.block_sparse_moe.experts.3.up_proj.weight": "model-00002-of-00002.safetensors", "layers.10.block_sparse_moe.gate.0.weight": "model-00001-of-00002.safetensors", "layers.10.block_sparse_moe.gate.1.weight": "model-00001-of-00002.safetensors", "layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors", "layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "layers.11.block_sparse_moe.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.experts.2.down_proj.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.experts.2.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.experts.2.up_proj.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.experts.3.down_proj.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.experts.3.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.experts.3.up_proj.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.gate.0.weight": "model-00002-of-00002.safetensors", "layers.11.block_sparse_moe.gate.1.weight": "model-00002-of-00002.safetensors", "layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", "layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.experts.2.down_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.experts.2.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.experts.2.up_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.experts.3.down_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.experts.3.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.experts.3.up_proj.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.gate.0.weight": "model-00002-of-00002.safetensors", "layers.12.block_sparse_moe.gate.1.weight": "model-00002-of-00002.safetensors", "layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", "layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.experts.2.down_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.experts.2.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.experts.2.up_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.experts.3.down_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.experts.3.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.experts.3.up_proj.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.gate.0.weight": "model-00002-of-00002.safetensors", "layers.13.block_sparse_moe.gate.1.weight": "model-00002-of-00002.safetensors", "layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors", "layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.experts.2.down_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.experts.2.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.experts.2.up_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.experts.3.down_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.experts.3.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.experts.3.up_proj.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.gate.0.weight": "model-00002-of-00002.safetensors", "layers.14.block_sparse_moe.gate.1.weight": "model-00002-of-00002.safetensors", "layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", "layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.experts.2.down_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.experts.2.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.experts.2.up_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.experts.3.down_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.experts.3.gate_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.experts.3.up_proj.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.gate.0.weight": "model-00002-of-00002.safetensors", "layers.15.block_sparse_moe.gate.1.weight": "model-00002-of-00002.safetensors", "layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", "layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "layers.2.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.gate.0.weight": "model-00001-of-00002.safetensors", "layers.2.block_sparse_moe.gate.1.weight": "model-00001-of-00002.safetensors", "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.gate.0.weight": "model-00001-of-00002.safetensors", "layers.3.block_sparse_moe.gate.1.weight": "model-00001-of-00002.safetensors", "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.gate.0.weight": "model-00001-of-00002.safetensors", "layers.4.block_sparse_moe.gate.1.weight": "model-00001-of-00002.safetensors", "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.gate.0.weight": "model-00001-of-00002.safetensors", "layers.5.block_sparse_moe.gate.1.weight": "model-00001-of-00002.safetensors", "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.gate.0.weight": "model-00001-of-00002.safetensors", "layers.6.block_sparse_moe.gate.1.weight": "model-00001-of-00002.safetensors", "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.gate.0.weight": "model-00001-of-00002.safetensors", "layers.7.block_sparse_moe.gate.1.weight": "model-00001-of-00002.safetensors", "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.gate.0.weight": "model-00001-of-00002.safetensors", "layers.8.block_sparse_moe.gate.1.weight": "model-00001-of-00002.safetensors", "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.experts.2.down_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.experts.2.up_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.experts.3.down_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.experts.3.up_proj.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.gate.0.weight": "model-00001-of-00002.safetensors", "layers.9.block_sparse_moe.gate.1.weight": "model-00001-of-00002.safetensors", "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "lm_head.weight": "model-00002-of-00002.safetensors" } }