diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json" new file mode 100644--- /dev/null +++ "b/model.safetensors.index.json" @@ -0,0 +1,1370 @@ +{ + "metadata": { + "total_size": 209474344960 + }, + "weight_map": { + "lm_head.weight": "model-00043-of-00043.safetensors", + "model.embed_tokens.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00043.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00043.safetensors", + "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00043.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00043.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00043.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00043.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00043.safetensors", + "model.layers.1.block_sparse_moe.gate.weight": "model-00002-of-00043.safetensors", + "model.layers.1.input_layernorm.weight": "model-00003-of-00043.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00043.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00043.safetensors", + "model.layers.10.block_sparse_moe.gate.weight": "model-00011-of-00043.safetensors", + "model.layers.10.input_layernorm.weight": "model-00012-of-00043.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00043.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00011-of-00043.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00011-of-00043.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00011-of-00043.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00043.safetensors", + "model.layers.11.block_sparse_moe.gate.weight": "model-00012-of-00043.safetensors", + "model.layers.11.input_layernorm.weight": "model-00013-of-00043.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00043.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00012-of-00043.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00012-of-00043.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00012-of-00043.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00043.safetensors", + "model.layers.12.block_sparse_moe.gate.weight": "model-00013-of-00043.safetensors", + "model.layers.12.input_layernorm.weight": "model-00014-of-00043.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00043.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00013-of-00043.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00013-of-00043.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00013-of-00043.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00043.safetensors", + "model.layers.13.block_sparse_moe.gate.weight": "model-00014-of-00043.safetensors", + "model.layers.13.input_layernorm.weight": "model-00015-of-00043.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00015-of-00043.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00014-of-00043.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00014-of-00043.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00014-of-00043.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00043.safetensors", + "model.layers.14.block_sparse_moe.gate.weight": "model-00015-of-00043.safetensors", + "model.layers.14.input_layernorm.weight": "model-00016-of-00043.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00016-of-00043.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00015-of-00043.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00015-of-00043.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00015-of-00043.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00043.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00043.safetensors", + "model.layers.15.block_sparse_moe.gate.weight": "model-00016-of-00043.safetensors", + "model.layers.15.input_layernorm.weight": "model-00018-of-00043.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00018-of-00043.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00016-of-00043.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00016-of-00043.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00016-of-00043.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00043.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00043.safetensors", + "model.layers.16.block_sparse_moe.gate.weight": "model-00018-of-00043.safetensors", + "model.layers.16.input_layernorm.weight": "model-00019-of-00043.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00019-of-00043.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00018-of-00043.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00018-of-00043.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00018-of-00043.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00020-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00020-of-00043.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00020-of-00043.safetensors", + "model.layers.17.block_sparse_moe.gate.weight": "model-00019-of-00043.safetensors", + "model.layers.17.input_layernorm.weight": "model-00020-of-00043.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00020-of-00043.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00019-of-00043.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00019-of-00043.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00019-of-00043.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00020-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00021-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00021-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00021-of-00043.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00021-of-00043.safetensors", + "model.layers.18.block_sparse_moe.gate.weight": "model-00020-of-00043.safetensors", + "model.layers.18.input_layernorm.weight": "model-00021-of-00043.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00021-of-00043.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00020-of-00043.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00020-of-00043.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00020-of-00043.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00021-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00022-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00022-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00022-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00022-of-00043.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00022-of-00043.safetensors", + "model.layers.19.block_sparse_moe.gate.weight": "model-00021-of-00043.safetensors", + "model.layers.19.input_layernorm.weight": "model-00022-of-00043.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00022-of-00043.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00043.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00043.safetensors", + "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00043.safetensors", + "model.layers.2.input_layernorm.weight": "model-00004-of-00043.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00043.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00043.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00043.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00043.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00022-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00043.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00023-of-00043.safetensors", + "model.layers.20.block_sparse_moe.gate.weight": "model-00022-of-00043.safetensors", + "model.layers.20.input_layernorm.weight": "model-00023-of-00043.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00023-of-00043.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00024-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00024-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00024-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00024-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00024-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00024-of-00043.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00024-of-00043.safetensors", + "model.layers.21.block_sparse_moe.gate.weight": "model-00023-of-00043.safetensors", + "model.layers.21.input_layernorm.weight": "model-00024-of-00043.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00024-of-00043.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00023-of-00043.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00023-of-00043.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00023-of-00043.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00024-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00025-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00025-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00025-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00025-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00025-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00025-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00025-of-00043.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00025-of-00043.safetensors", + "model.layers.22.block_sparse_moe.gate.weight": "model-00024-of-00043.safetensors", + "model.layers.22.input_layernorm.weight": "model-00025-of-00043.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00025-of-00043.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00025-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00026-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00026-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00026-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00026-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00026-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00026-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00026-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00026-of-00043.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00026-of-00043.safetensors", + "model.layers.23.block_sparse_moe.gate.weight": "model-00025-of-00043.safetensors", + "model.layers.23.input_layernorm.weight": "model-00026-of-00043.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00026-of-00043.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00026-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00027-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00027-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00027-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00027-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00027-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00027-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00027-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00027-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00027-of-00043.safetensors", + "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00027-of-00043.safetensors", + "model.layers.24.block_sparse_moe.gate.weight": "model-00026-of-00043.safetensors", + "model.layers.24.input_layernorm.weight": "model-00027-of-00043.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00027-of-00043.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00026-of-00043.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00026-of-00043.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00026-of-00043.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00027-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00028-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00028-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00028-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00028-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00028-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00028-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00028-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00028-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00028-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00028-of-00043.safetensors", + "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00028-of-00043.safetensors", + "model.layers.25.block_sparse_moe.gate.weight": "model-00027-of-00043.safetensors", + "model.layers.25.input_layernorm.weight": "model-00028-of-00043.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00028-of-00043.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00027-of-00043.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00027-of-00043.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00027-of-00043.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00028-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00028-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00028-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00029-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00029-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00029-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00029-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00029-of-00043.safetensors", + "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00029-of-00043.safetensors", + "model.layers.26.block_sparse_moe.gate.weight": "model-00028-of-00043.safetensors", + "model.layers.26.input_layernorm.weight": "model-00029-of-00043.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00029-of-00043.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00028-of-00043.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00028-of-00043.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00028-of-00043.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00029-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00029-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00029-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00029-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00030-of-00043.safetensors", + "model.layers.27.block_sparse_moe.gate.weight": "model-00029-of-00043.safetensors", + "model.layers.27.input_layernorm.weight": "model-00030-of-00043.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00030-of-00043.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00029-of-00043.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00029-of-00043.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00029-of-00043.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00031-of-00043.safetensors", + "model.layers.28.block_sparse_moe.gate.weight": "model-00030-of-00043.safetensors", + "model.layers.28.input_layernorm.weight": "model-00031-of-00043.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00031-of-00043.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00030-of-00043.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00030-of-00043.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00030-of-00043.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00031-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00031-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00032-of-00043.safetensors", + "model.layers.29.block_sparse_moe.gate.weight": "model-00031-of-00043.safetensors", + "model.layers.29.input_layernorm.weight": "model-00032-of-00043.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00032-of-00043.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00031-of-00043.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00031-of-00043.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00031-of-00043.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00043.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00043.safetensors", + "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00043.safetensors", + "model.layers.3.input_layernorm.weight": "model-00005-of-00043.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00043.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00043.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00043.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00043.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00033-of-00043.safetensors", + "model.layers.30.block_sparse_moe.gate.weight": "model-00032-of-00043.safetensors", + "model.layers.30.input_layernorm.weight": "model-00033-of-00043.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00033-of-00043.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00032-of-00043.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00032-of-00043.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00032-of-00043.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00034-of-00043.safetensors", + "model.layers.31.block_sparse_moe.gate.weight": "model-00033-of-00043.safetensors", + "model.layers.31.input_layernorm.weight": "model-00034-of-00043.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00034-of-00043.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00033-of-00043.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00033-of-00043.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00033-of-00043.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.4.w1.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.4.w2.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.4.w3.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.5.w1.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.5.w2.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.5.w3.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.6.w1.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.6.w2.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.6.w3.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.7.w1.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.7.w2.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.experts.7.w3.weight": "model-00035-of-00043.safetensors", + "model.layers.32.block_sparse_moe.gate.weight": "model-00034-of-00043.safetensors", + "model.layers.32.input_layernorm.weight": "model-00035-of-00043.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00035-of-00043.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00034-of-00043.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00034-of-00043.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00034-of-00043.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.4.w1.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.4.w2.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.4.w3.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.5.w1.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.5.w2.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.5.w3.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.6.w1.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.6.w2.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.6.w3.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.7.w1.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.7.w2.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.experts.7.w3.weight": "model-00036-of-00043.safetensors", + "model.layers.33.block_sparse_moe.gate.weight": "model-00035-of-00043.safetensors", + "model.layers.33.input_layernorm.weight": "model-00036-of-00043.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00036-of-00043.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00035-of-00043.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00035-of-00043.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00035-of-00043.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.4.w1.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.4.w2.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.4.w3.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.5.w1.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.5.w2.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.5.w3.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.6.w1.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.6.w2.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.6.w3.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.7.w1.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.7.w2.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.experts.7.w3.weight": "model-00037-of-00043.safetensors", + "model.layers.34.block_sparse_moe.gate.weight": "model-00036-of-00043.safetensors", + "model.layers.34.input_layernorm.weight": "model-00037-of-00043.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00037-of-00043.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00036-of-00043.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00036-of-00043.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00036-of-00043.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00037-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00037-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00037-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.4.w1.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.4.w2.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.4.w3.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.5.w1.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.5.w2.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.5.w3.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.6.w1.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.6.w2.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.6.w3.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.7.w1.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.7.w2.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.experts.7.w3.weight": "model-00038-of-00043.safetensors", + "model.layers.35.block_sparse_moe.gate.weight": "model-00037-of-00043.safetensors", + "model.layers.35.input_layernorm.weight": "model-00038-of-00043.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00038-of-00043.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.4.w1.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.4.w2.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.4.w3.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.5.w1.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.5.w2.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.5.w3.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.6.w1.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.6.w2.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.6.w3.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.7.w1.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.7.w2.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.experts.7.w3.weight": "model-00039-of-00043.safetensors", + "model.layers.36.block_sparse_moe.gate.weight": "model-00038-of-00043.safetensors", + "model.layers.36.input_layernorm.weight": "model-00039-of-00043.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00039-of-00043.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00038-of-00043.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00038-of-00043.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00038-of-00043.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00039-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.4.w1.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.4.w2.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.4.w3.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.5.w1.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.5.w2.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.5.w3.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.6.w1.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.6.w2.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.6.w3.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.7.w1.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.7.w2.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.experts.7.w3.weight": "model-00040-of-00043.safetensors", + "model.layers.37.block_sparse_moe.gate.weight": "model-00039-of-00043.safetensors", + "model.layers.37.input_layernorm.weight": "model-00040-of-00043.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00040-of-00043.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00039-of-00043.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00039-of-00043.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00039-of-00043.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.4.w1.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.4.w2.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.4.w3.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.5.w1.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.5.w2.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.5.w3.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.6.w1.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.6.w2.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.6.w3.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.7.w1.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.7.w2.weight": "model-00041-of-00043.safetensors", + "model.layers.38.block_sparse_moe.experts.7.w3.weight": "model-00042-of-00043.safetensors", + "model.layers.38.block_sparse_moe.gate.weight": "model-00040-of-00043.safetensors", + "model.layers.38.input_layernorm.weight": "model-00042-of-00043.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00042-of-00043.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.4.w1.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.4.w2.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.4.w3.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.5.w1.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.5.w2.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.5.w3.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.6.w1.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.6.w2.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.6.w3.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.7.w1.weight": "model-00042-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.7.w2.weight": "model-00043-of-00043.safetensors", + "model.layers.39.block_sparse_moe.experts.7.w3.weight": "model-00043-of-00043.safetensors", + "model.layers.39.block_sparse_moe.gate.weight": "model-00042-of-00043.safetensors", + "model.layers.39.input_layernorm.weight": "model-00043-of-00043.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00043-of-00043.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00042-of-00043.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00042-of-00043.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00042-of-00043.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00043.safetensors", + "model.layers.4.block_sparse_moe.gate.weight": "model-00005-of-00043.safetensors", + "model.layers.4.input_layernorm.weight": "model-00006-of-00043.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00043.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00005-of-00043.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00005-of-00043.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00005-of-00043.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00043.safetensors", + "model.layers.5.block_sparse_moe.gate.weight": "model-00006-of-00043.safetensors", + "model.layers.5.input_layernorm.weight": "model-00007-of-00043.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00043.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00043.safetensors", + "model.layers.6.block_sparse_moe.gate.weight": "model-00007-of-00043.safetensors", + "model.layers.6.input_layernorm.weight": "model-00008-of-00043.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00043.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00007-of-00043.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00007-of-00043.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00007-of-00043.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00043.safetensors", + "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00043.safetensors", + "model.layers.7.input_layernorm.weight": "model-00009-of-00043.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00043.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00008-of-00043.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00008-of-00043.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00008-of-00043.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00043.safetensors", + "model.layers.8.block_sparse_moe.gate.weight": "model-00009-of-00043.safetensors", + "model.layers.8.input_layernorm.weight": "model-00010-of-00043.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00043.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00043.safetensors", + "model.layers.9.block_sparse_moe.gate.weight": "model-00010-of-00043.safetensors", + "model.layers.9.input_layernorm.weight": "model-00011-of-00043.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00043.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00043.safetensors", + "model.norm.weight": "model-00043-of-00043.safetensors" + } +}