{ "metadata": { "total_size": 46719029248 }, "weight_map": { "model.embed_tokens.weight": "model_00.safetensors", "model.layers.0.self_attn.q_proj.weight": "model_01.safetensors", "model.layers.0.self_attn.k_proj.weight": "model_01.safetensors", "model.layers.0.self_attn.v_proj.weight": "model_01.safetensors", "model.layers.0.self_attn.o_proj.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model_01.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model_01.safetensors", "model.layers.0.input_layernorm.weight": "model_01.safetensors", "model.layers.0.post_attention_layernorm.weight": "model_01.safetensors", "model.layers.1.self_attn.q_proj.weight": "model_02.safetensors", "model.layers.1.self_attn.k_proj.weight": "model_02.safetensors", "model.layers.1.self_attn.v_proj.weight": "model_02.safetensors", "model.layers.1.self_attn.o_proj.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model_02.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model_02.safetensors", "model.layers.1.input_layernorm.weight": "model_02.safetensors", "model.layers.1.post_attention_layernorm.weight": "model_02.safetensors", "model.layers.2.self_attn.q_proj.weight": "model_03.safetensors", "model.layers.2.self_attn.k_proj.weight": "model_03.safetensors", "model.layers.2.self_attn.v_proj.weight": "model_03.safetensors", "model.layers.2.self_attn.o_proj.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model_03.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model_03.safetensors", "model.layers.2.input_layernorm.weight": "model_03.safetensors", "model.layers.2.post_attention_layernorm.weight": "model_03.safetensors", "model.layers.3.self_attn.q_proj.weight": "model_04.safetensors", "model.layers.3.self_attn.k_proj.weight": "model_04.safetensors", "model.layers.3.self_attn.v_proj.weight": "model_04.safetensors", "model.layers.3.self_attn.o_proj.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model_04.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model_04.safetensors", "model.layers.3.input_layernorm.weight": "model_04.safetensors", "model.layers.3.post_attention_layernorm.weight": "model_04.safetensors", "model.layers.4.self_attn.q_proj.weight": "model_05.safetensors", "model.layers.4.self_attn.k_proj.weight": "model_05.safetensors", "model.layers.4.self_attn.v_proj.weight": "model_05.safetensors", "model.layers.4.self_attn.o_proj.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model_05.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model_05.safetensors", "model.layers.4.input_layernorm.weight": "model_05.safetensors", "model.layers.4.post_attention_layernorm.weight": "model_05.safetensors", "model.layers.5.self_attn.q_proj.weight": "model_06.safetensors", "model.layers.5.self_attn.k_proj.weight": "model_06.safetensors", "model.layers.5.self_attn.v_proj.weight": "model_06.safetensors", "model.layers.5.self_attn.o_proj.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model_06.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model_06.safetensors", "model.layers.5.input_layernorm.weight": "model_06.safetensors", "model.layers.5.post_attention_layernorm.weight": "model_06.safetensors", "model.layers.6.self_attn.q_proj.weight": "model_07.safetensors", "model.layers.6.self_attn.k_proj.weight": "model_07.safetensors", "model.layers.6.self_attn.v_proj.weight": "model_07.safetensors", "model.layers.6.self_attn.o_proj.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model_07.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model_07.safetensors", "model.layers.6.input_layernorm.weight": "model_07.safetensors", "model.layers.6.post_attention_layernorm.weight": "model_07.safetensors", "model.layers.7.self_attn.q_proj.weight": "model_08.safetensors", "model.layers.7.self_attn.k_proj.weight": "model_08.safetensors", "model.layers.7.self_attn.v_proj.weight": "model_08.safetensors", "model.layers.7.self_attn.o_proj.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model_08.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model_08.safetensors", "model.layers.7.input_layernorm.weight": "model_08.safetensors", "model.layers.7.post_attention_layernorm.weight": "model_08.safetensors", "model.layers.8.self_attn.q_proj.weight": "model_09.safetensors", "model.layers.8.self_attn.k_proj.weight": "model_09.safetensors", "model.layers.8.self_attn.v_proj.weight": "model_09.safetensors", "model.layers.8.self_attn.o_proj.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model_09.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model_09.safetensors", "model.layers.8.input_layernorm.weight": "model_09.safetensors", "model.layers.8.post_attention_layernorm.weight": "model_09.safetensors", "model.layers.9.self_attn.q_proj.weight": "model_10.safetensors", "model.layers.9.self_attn.k_proj.weight": "model_10.safetensors", "model.layers.9.self_attn.v_proj.weight": "model_10.safetensors", "model.layers.9.self_attn.o_proj.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model_10.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model_10.safetensors", "model.layers.9.input_layernorm.weight": "model_10.safetensors", "model.layers.9.post_attention_layernorm.weight": "model_10.safetensors", "model.layers.10.self_attn.q_proj.weight": "model_11.safetensors", "model.layers.10.self_attn.k_proj.weight": "model_11.safetensors", "model.layers.10.self_attn.v_proj.weight": "model_11.safetensors", "model.layers.10.self_attn.o_proj.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model_11.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model_11.safetensors", "model.layers.10.input_layernorm.weight": "model_11.safetensors", "model.layers.10.post_attention_layernorm.weight": "model_11.safetensors", "model.layers.11.self_attn.q_proj.weight": "model_12.safetensors", "model.layers.11.self_attn.k_proj.weight": "model_12.safetensors", "model.layers.11.self_attn.v_proj.weight": "model_12.safetensors", "model.layers.11.self_attn.o_proj.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model_12.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model_12.safetensors", "model.layers.11.input_layernorm.weight": "model_12.safetensors", "model.layers.11.post_attention_layernorm.weight": "model_12.safetensors", "model.layers.12.self_attn.q_proj.weight": "model_13.safetensors", "model.layers.12.self_attn.k_proj.weight": "model_13.safetensors", "model.layers.12.self_attn.v_proj.weight": "model_13.safetensors", "model.layers.12.self_attn.o_proj.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model_13.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model_13.safetensors", "model.layers.12.input_layernorm.weight": "model_13.safetensors", "model.layers.12.post_attention_layernorm.weight": "model_13.safetensors", "model.layers.13.self_attn.q_proj.weight": "model_14.safetensors", "model.layers.13.self_attn.k_proj.weight": "model_14.safetensors", "model.layers.13.self_attn.v_proj.weight": "model_14.safetensors", "model.layers.13.self_attn.o_proj.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model_14.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model_14.safetensors", "model.layers.13.input_layernorm.weight": "model_14.safetensors", "model.layers.13.post_attention_layernorm.weight": "model_14.safetensors", "model.layers.14.self_attn.q_proj.weight": "model_15.safetensors", "model.layers.14.self_attn.k_proj.weight": "model_15.safetensors", "model.layers.14.self_attn.v_proj.weight": "model_15.safetensors", "model.layers.14.self_attn.o_proj.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model_15.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model_15.safetensors", "model.layers.14.input_layernorm.weight": "model_15.safetensors", "model.layers.14.post_attention_layernorm.weight": "model_15.safetensors", "model.layers.15.self_attn.q_proj.weight": "model_16.safetensors", "model.layers.15.self_attn.k_proj.weight": "model_16.safetensors", "model.layers.15.self_attn.v_proj.weight": "model_16.safetensors", "model.layers.15.self_attn.o_proj.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model_16.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model_16.safetensors", "model.layers.15.input_layernorm.weight": "model_16.safetensors", "model.layers.15.post_attention_layernorm.weight": "model_16.safetensors", "model.layers.16.self_attn.q_proj.weight": "model_17.safetensors", "model.layers.16.self_attn.k_proj.weight": "model_17.safetensors", "model.layers.16.self_attn.v_proj.weight": "model_17.safetensors", "model.layers.16.self_attn.o_proj.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model_17.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model_17.safetensors", "model.layers.16.input_layernorm.weight": "model_17.safetensors", "model.layers.16.post_attention_layernorm.weight": "model_17.safetensors", "model.layers.17.self_attn.q_proj.weight": "model_18.safetensors", "model.layers.17.self_attn.k_proj.weight": "model_18.safetensors", "model.layers.17.self_attn.v_proj.weight": "model_18.safetensors", "model.layers.17.self_attn.o_proj.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model_18.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model_18.safetensors", "model.layers.17.input_layernorm.weight": "model_18.safetensors", "model.layers.17.post_attention_layernorm.weight": "model_18.safetensors", "model.layers.18.self_attn.q_proj.weight": "model_19.safetensors", "model.layers.18.self_attn.k_proj.weight": "model_19.safetensors", "model.layers.18.self_attn.v_proj.weight": "model_19.safetensors", "model.layers.18.self_attn.o_proj.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model_19.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model_19.safetensors", "model.layers.18.input_layernorm.weight": "model_19.safetensors", "model.layers.18.post_attention_layernorm.weight": "model_19.safetensors", "model.layers.19.self_attn.q_proj.weight": "model_20.safetensors", "model.layers.19.self_attn.k_proj.weight": "model_20.safetensors", "model.layers.19.self_attn.v_proj.weight": "model_20.safetensors", "model.layers.19.self_attn.o_proj.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model_20.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model_20.safetensors", "model.layers.19.input_layernorm.weight": "model_20.safetensors", "model.layers.19.post_attention_layernorm.weight": "model_20.safetensors", "model.layers.20.self_attn.q_proj.weight": "model_21.safetensors", "model.layers.20.self_attn.k_proj.weight": "model_21.safetensors", "model.layers.20.self_attn.v_proj.weight": "model_21.safetensors", "model.layers.20.self_attn.o_proj.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model_21.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model_21.safetensors", "model.layers.20.input_layernorm.weight": "model_21.safetensors", "model.layers.20.post_attention_layernorm.weight": "model_21.safetensors", "model.layers.21.self_attn.q_proj.weight": "model_22.safetensors", "model.layers.21.self_attn.k_proj.weight": "model_22.safetensors", "model.layers.21.self_attn.v_proj.weight": "model_22.safetensors", "model.layers.21.self_attn.o_proj.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model_22.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model_22.safetensors", "model.layers.21.input_layernorm.weight": "model_22.safetensors", "model.layers.21.post_attention_layernorm.weight": "model_22.safetensors", "model.layers.22.self_attn.q_proj.weight": "model_23.safetensors", "model.layers.22.self_attn.k_proj.weight": "model_23.safetensors", "model.layers.22.self_attn.v_proj.weight": "model_23.safetensors", "model.layers.22.self_attn.o_proj.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model_23.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model_23.safetensors", "model.layers.22.input_layernorm.weight": "model_23.safetensors", "model.layers.22.post_attention_layernorm.weight": "model_23.safetensors", "model.layers.23.self_attn.q_proj.weight": "model_24.safetensors", "model.layers.23.self_attn.k_proj.weight": "model_24.safetensors", "model.layers.23.self_attn.v_proj.weight": "model_24.safetensors", "model.layers.23.self_attn.o_proj.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model_24.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model_24.safetensors", "model.layers.23.input_layernorm.weight": "model_24.safetensors", "model.layers.23.post_attention_layernorm.weight": "model_24.safetensors", "model.layers.24.self_attn.q_proj.weight": "model_25.safetensors", "model.layers.24.self_attn.k_proj.weight": "model_25.safetensors", "model.layers.24.self_attn.v_proj.weight": "model_25.safetensors", "model.layers.24.self_attn.o_proj.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model_25.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model_25.safetensors", "model.layers.24.input_layernorm.weight": "model_25.safetensors", "model.layers.24.post_attention_layernorm.weight": "model_25.safetensors", "model.layers.25.self_attn.q_proj.weight": "model_26.safetensors", "model.layers.25.self_attn.k_proj.weight": "model_26.safetensors", "model.layers.25.self_attn.v_proj.weight": "model_26.safetensors", "model.layers.25.self_attn.o_proj.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model_26.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model_26.safetensors", "model.layers.25.input_layernorm.weight": "model_26.safetensors", "model.layers.25.post_attention_layernorm.weight": "model_26.safetensors", "model.layers.26.self_attn.q_proj.weight": "model_27.safetensors", "model.layers.26.self_attn.k_proj.weight": "model_27.safetensors", "model.layers.26.self_attn.v_proj.weight": "model_27.safetensors", "model.layers.26.self_attn.o_proj.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model_27.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model_27.safetensors", "model.layers.26.input_layernorm.weight": "model_27.safetensors", "model.layers.26.post_attention_layernorm.weight": "model_27.safetensors", "model.layers.27.self_attn.q_proj.weight": "model_28.safetensors", "model.layers.27.self_attn.k_proj.weight": "model_28.safetensors", "model.layers.27.self_attn.v_proj.weight": "model_28.safetensors", "model.layers.27.self_attn.o_proj.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model_28.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model_28.safetensors", "model.layers.27.input_layernorm.weight": "model_28.safetensors", "model.layers.27.post_attention_layernorm.weight": "model_28.safetensors", "model.layers.28.self_attn.q_proj.weight": "model_29.safetensors", "model.layers.28.self_attn.k_proj.weight": "model_29.safetensors", "model.layers.28.self_attn.v_proj.weight": "model_29.safetensors", "model.layers.28.self_attn.o_proj.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model_29.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model_29.safetensors", "model.layers.28.input_layernorm.weight": "model_29.safetensors", "model.layers.28.post_attention_layernorm.weight": "model_29.safetensors", "model.layers.29.self_attn.q_proj.weight": "model_30.safetensors", "model.layers.29.self_attn.k_proj.weight": "model_30.safetensors", "model.layers.29.self_attn.v_proj.weight": "model_30.safetensors", "model.layers.29.self_attn.o_proj.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model_30.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model_30.safetensors", "model.layers.29.input_layernorm.weight": "model_30.safetensors", "model.layers.29.post_attention_layernorm.weight": "model_30.safetensors", "model.layers.30.self_attn.q_proj.weight": "model_31.safetensors", "model.layers.30.self_attn.k_proj.weight": "model_31.safetensors", "model.layers.30.self_attn.v_proj.weight": "model_31.safetensors", "model.layers.30.self_attn.o_proj.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model_31.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model_31.safetensors", "model.layers.30.input_layernorm.weight": "model_31.safetensors", "model.layers.30.post_attention_layernorm.weight": "model_31.safetensors", "model.layers.31.self_attn.q_proj.weight": "model_32.safetensors", "model.layers.31.self_attn.k_proj.weight": "model_32.safetensors", "model.layers.31.self_attn.v_proj.weight": "model_32.safetensors", "model.layers.31.self_attn.o_proj.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model_32.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model_32.safetensors", "model.layers.31.input_layernorm.weight": "model_32.safetensors", "model.layers.31.post_attention_layernorm.weight": "model_32.safetensors", "model.norm.weight": "model_33.safetensors", "lm_head.weight": "model_34.safetensors" } }