{ "metadata": { "total_size": 963334844416 }, "weight_map": { "lm_head.weight": "model-00195-of-00195.safetensors", "model.embed_tokens.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.100.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.100.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.100.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.101.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.101.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.101.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.102.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.102.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.102.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.103.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.103.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.103.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.104.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.104.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.104.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.105.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.105.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.105.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.106.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.106.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.106.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.107.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.107.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.107.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.108.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.108.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.108.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.109.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.109.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.109.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.110.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.110.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.110.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.111.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.111.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.111.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.112.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.112.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.112.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.113.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.113.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.113.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.114.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.114.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.114.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.115.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.115.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.115.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.116.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.116.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.116.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.117.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.117.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.117.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.118.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.118.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.118.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.119.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.119.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.119.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.120.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.120.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.120.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.121.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.121.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.121.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.122.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.122.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.122.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.123.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.123.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.123.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.124.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.124.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.124.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.125.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.125.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.125.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.126.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.126.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.126.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.127.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.127.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.127.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.32.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.32.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.33.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.33.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.34.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.35.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.35.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.37.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.37.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.38.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.38.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.39.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.39.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.40.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.40.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.41.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.41.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.41.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.42.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.42.w3.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.43.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.43.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.44.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.45.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.45.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.46.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.46.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.47.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.47.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.47.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.48.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.48.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.48.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.49.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.49.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.49.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.50.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.50.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.51.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.51.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.52.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.52.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.52.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.53.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.53.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.53.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.54.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.54.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.55.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.55.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.56.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.57.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.57.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.58.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.58.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.58.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.59.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.59.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.59.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.60.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.60.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.61.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.61.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.61.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.62.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.63.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.64.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.64.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.64.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.65.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.65.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.65.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.66.w1.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.66.w2.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.66.w3.weight": "model-00003-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.67.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.67.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.67.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.68.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.68.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.68.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.69.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.69.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.69.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.70.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.70.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.70.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.71.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.71.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.71.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.72.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.72.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.72.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.73.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.73.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.73.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.74.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.74.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.74.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.75.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.75.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.75.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.76.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.76.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.76.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.77.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.77.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.77.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.78.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.78.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.78.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.79.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.79.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.79.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.80.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.80.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.80.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.81.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.81.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.81.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.82.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.82.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.82.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.83.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.83.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.83.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.84.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.84.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.84.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.85.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.85.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.85.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.86.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.86.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.86.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.87.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.87.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.87.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.88.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.88.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.88.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.89.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.89.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.89.w3.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.90.w1.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.90.w2.weight": "model-00004-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.90.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.91.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.91.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.91.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.92.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.92.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.92.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.93.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.93.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.93.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.94.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.94.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.94.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.95.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.95.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.95.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.96.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.96.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.96.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.97.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.97.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.97.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.98.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.98.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.98.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.99.w1.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.99.w2.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.experts.99.w3.weight": "model-00005-of-00195.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00195.safetensors", "model.layers.0.input_layernorm.weight": "model-00006-of-00195.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00006-of-00195.safetensors", "model.layers.0.residual_layernorm.weight": "model-00006-of-00195.safetensors", "model.layers.0.residual_mlp.w1.weight": "model-00006-of-00195.safetensors", "model.layers.0.residual_mlp.w2.weight": "model-00006-of-00195.safetensors", "model.layers.0.residual_mlp.w3.weight": "model-00006-of-00195.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00195.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00195.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00195.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.10.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.10.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.100.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.100.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.100.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.101.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.101.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.101.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.102.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.102.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.102.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.103.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.103.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.103.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.104.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.104.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.104.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.105.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.105.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.105.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.106.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.106.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.106.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.107.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.107.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.107.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.108.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.108.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.108.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.109.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.109.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.109.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.11.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.11.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.11.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.110.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.110.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.110.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.111.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.111.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.111.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.112.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.112.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.112.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.113.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.113.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.113.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.114.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.114.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.114.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.115.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.115.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.115.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.116.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.116.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.116.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.117.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.117.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.117.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.118.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.118.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.118.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.119.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.119.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.119.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.12.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.12.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.12.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.120.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.120.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.120.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.121.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.121.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.121.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.122.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.122.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.122.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.123.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.123.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.123.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.124.w1.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.124.w2.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.124.w3.weight": "model-00011-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.125.w1.weight": "model-00012-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.125.w2.weight": "model-00012-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.125.w3.weight": "model-00012-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.126.w1.weight": "model-00012-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.126.w2.weight": "model-00012-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.126.w3.weight": "model-00012-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.127.w1.weight": "model-00012-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.127.w2.weight": "model-00012-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.127.w3.weight": "model-00012-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.13.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.13.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.13.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.14.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.14.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.14.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.15.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.15.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.15.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.16.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.16.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.16.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.17.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.17.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.17.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.18.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.18.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.18.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.19.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.19.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.19.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.20.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.20.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.20.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.21.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.21.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.21.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.22.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.22.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.22.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.23.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.23.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.23.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.24.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.24.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.24.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.25.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.25.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.25.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.26.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.26.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.26.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.27.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.27.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.27.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.28.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.28.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.28.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.29.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.29.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.29.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.30.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.30.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.30.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.31.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.31.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.31.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.32.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.32.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.32.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.33.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.33.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.33.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.34.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.34.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.34.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.35.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.35.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.35.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.36.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.36.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.36.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.37.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.37.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.37.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.38.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.38.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.38.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.39.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.39.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.39.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.40.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.40.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.40.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.41.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.41.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.41.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.42.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.42.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.42.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.43.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.43.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.43.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.44.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.44.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.44.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.45.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.45.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.45.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.46.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.46.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.46.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.47.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.47.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.47.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.48.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.48.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.48.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.49.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.49.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.49.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.50.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.50.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.50.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.51.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.51.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.51.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.52.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.52.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.52.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.53.w1.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.53.w2.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.53.w3.weight": "model-00008-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.54.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.54.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.54.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.55.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.55.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.55.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.56.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.56.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.56.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.57.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.57.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.57.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.58.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.58.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.58.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.59.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.59.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.59.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.60.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.60.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.60.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.61.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.61.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.61.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.62.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.62.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.62.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.63.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.63.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.63.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.64.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.64.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.64.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.65.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.65.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.65.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.66.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.66.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.66.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.67.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.67.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.67.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.68.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.68.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.68.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.69.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.69.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.69.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.70.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.70.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.70.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.71.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.71.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.71.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.72.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.72.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.72.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.73.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.73.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.73.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.74.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.74.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.74.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.75.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.75.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.75.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.76.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.76.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.76.w3.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.77.w1.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.77.w2.weight": "model-00009-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.77.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.78.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.78.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.78.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.79.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.79.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.79.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.8.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.8.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.8.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.80.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.80.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.80.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.81.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.81.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.81.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.82.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.82.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.82.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.83.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.83.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.83.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.84.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.84.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.84.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.85.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.85.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.85.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.86.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.86.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.86.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.87.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.87.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.87.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.88.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.88.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.88.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.89.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.89.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.89.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.9.w1.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.9.w2.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.9.w3.weight": "model-00007-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.90.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.90.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.90.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.91.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.91.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.91.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.92.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.92.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.92.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.93.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.93.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.93.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.94.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.94.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.94.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.95.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.95.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.95.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.96.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.96.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.96.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.97.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.97.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.97.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.98.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.98.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.98.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.99.w1.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.99.w2.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.experts.99.w3.weight": "model-00010-of-00195.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00006-of-00195.safetensors", "model.layers.1.input_layernorm.weight": "model-00012-of-00195.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00012-of-00195.safetensors", "model.layers.1.residual_layernorm.weight": "model-00012-of-00195.safetensors", "model.layers.1.residual_mlp.w1.weight": "model-00012-of-00195.safetensors", "model.layers.1.residual_mlp.w2.weight": "model-00012-of-00195.safetensors", "model.layers.1.residual_mlp.w3.weight": "model-00012-of-00195.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00006-of-00195.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00006-of-00195.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00006-of-00195.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00006-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.10.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.10.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.10.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.100.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.100.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.100.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.101.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.101.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.101.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.102.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.102.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.102.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.103.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.103.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.103.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.104.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.104.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.104.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.105.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.105.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.105.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.106.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.106.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.106.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.107.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.107.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.107.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.108.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.108.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.108.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.109.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.109.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.109.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.11.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.11.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.11.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.110.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.110.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.110.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.111.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.111.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.111.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.112.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.112.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.112.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.113.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.113.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.113.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.114.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.114.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.114.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.115.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.115.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.115.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.116.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.116.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.116.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.117.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.117.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.117.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.118.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.118.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.118.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.119.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.119.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.119.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.12.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.12.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.12.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.120.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.120.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.120.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.121.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.121.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.121.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.122.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.122.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.122.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.123.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.123.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.123.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.124.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.124.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.124.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.125.w1.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.125.w2.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.125.w3.weight": "model-00061-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.126.w1.weight": "model-00062-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.126.w2.weight": "model-00062-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.126.w3.weight": "model-00062-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.127.w1.weight": "model-00062-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.127.w2.weight": "model-00062-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.127.w3.weight": "model-00062-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.13.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.13.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.13.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.14.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.14.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.14.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.15.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.15.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.15.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.16.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.16.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.16.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.17.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.17.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.17.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.18.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.18.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.18.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.19.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.19.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.19.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.20.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.20.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.20.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.21.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.21.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.21.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.22.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.22.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.22.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.23.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.23.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.23.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.24.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.24.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.24.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.25.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.25.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.25.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.26.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.26.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.26.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.27.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.27.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.27.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.28.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.28.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.28.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.29.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.29.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.29.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.30.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.30.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.30.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.31.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.31.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.31.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.32.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.32.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.32.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.33.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.33.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.33.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.34.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.34.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.34.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.35.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.35.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.35.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.36.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.36.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.36.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.37.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.37.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.37.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.38.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.38.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.38.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.39.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.39.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.39.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.40.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.40.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.40.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.41.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.41.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.41.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.42.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.42.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.42.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.43.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.43.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.43.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.44.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.44.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.44.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.45.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.45.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.45.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.46.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.46.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.46.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.47.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.47.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.47.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.48.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.48.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.48.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.49.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.49.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.49.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.50.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.50.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.50.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.51.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.51.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.51.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.52.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.52.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.52.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.53.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.53.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.53.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.54.w1.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.54.w2.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.54.w3.weight": "model-00058-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.55.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.55.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.55.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.56.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.56.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.56.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.57.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.57.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.57.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.58.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.58.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.58.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.59.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.59.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.59.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.60.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.60.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.60.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.61.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.61.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.61.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.62.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.62.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.62.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.63.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.63.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.63.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.64.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.64.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.64.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.65.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.65.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.65.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.66.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.66.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.66.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.67.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.67.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.67.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.68.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.68.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.68.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.69.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.69.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.69.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00056-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.70.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.70.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.70.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.71.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.71.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.71.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.72.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.72.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.72.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.73.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.73.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.73.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.74.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.74.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.74.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.75.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.75.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.75.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.76.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.76.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.76.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.77.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.77.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.77.w3.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.78.w1.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.78.w2.weight": "model-00059-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.78.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.79.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.79.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.79.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.8.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.8.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.8.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.80.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.80.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.80.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.81.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.81.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.81.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.82.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.82.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.82.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.83.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.83.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.83.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.84.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.84.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.84.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.85.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.85.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.85.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.86.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.86.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.86.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.87.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.87.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.87.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.88.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.88.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.88.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.89.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.89.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.89.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.9.w1.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.9.w2.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.9.w3.weight": "model-00057-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.90.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.90.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.90.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.91.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.91.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.91.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.92.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.92.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.92.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.93.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.93.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.93.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.94.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.94.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.94.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.95.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.95.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.95.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.96.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.96.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.96.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.97.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.97.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.97.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.98.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.98.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.98.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.99.w1.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.99.w2.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.experts.99.w3.weight": "model-00060-of-00195.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00056-of-00195.safetensors", "model.layers.10.input_layernorm.weight": "model-00062-of-00195.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00062-of-00195.safetensors", "model.layers.10.residual_layernorm.weight": "model-00062-of-00195.safetensors", "model.layers.10.residual_mlp.w1.weight": "model-00062-of-00195.safetensors", "model.layers.10.residual_mlp.w2.weight": "model-00062-of-00195.safetensors", "model.layers.10.residual_mlp.w3.weight": "model-00062-of-00195.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00056-of-00195.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00056-of-00195.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00056-of-00195.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00056-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.10.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.10.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.10.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.100.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.100.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.100.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.101.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.101.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.101.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.102.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.102.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.102.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.103.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.103.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.103.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.104.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.104.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.104.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.105.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.105.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.105.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.106.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.106.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.106.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.107.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.107.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.107.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.108.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.108.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.108.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.109.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.109.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.109.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.11.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.11.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.11.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.110.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.110.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.110.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.111.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.111.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.111.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.112.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.112.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.112.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.113.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.113.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.113.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.114.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.114.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.114.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.115.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.115.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.115.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.116.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.116.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.116.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.117.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.117.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.117.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.118.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.118.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.118.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.119.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.119.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.119.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.12.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.12.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.12.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.120.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.120.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.120.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.121.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.121.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.121.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.122.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.122.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.122.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.123.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.123.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.123.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.124.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.124.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.124.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.125.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.125.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.125.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.126.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.126.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.126.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.127.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.127.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.127.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.13.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.13.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.13.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.14.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.14.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.14.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.15.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.15.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.15.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.16.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.16.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.16.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.17.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.17.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.17.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.18.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.18.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.18.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.19.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.19.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.19.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.20.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.20.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.20.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.21.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.21.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.21.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.22.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.22.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.22.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.23.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.23.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.23.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.24.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.24.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.24.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.25.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.25.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.25.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.26.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.26.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.26.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.27.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.27.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.27.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.28.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.28.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.28.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.29.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.29.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.29.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.30.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.30.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.30.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.31.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.31.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.31.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.32.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.32.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.32.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.33.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.33.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.33.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.34.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.34.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.34.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.35.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.35.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.35.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.36.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.36.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.36.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.37.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.37.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.37.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.38.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.38.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.38.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.39.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.39.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.39.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.40.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.40.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.40.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.41.w1.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.41.w2.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.41.w3.weight": "model-00063-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.42.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.42.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.42.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.43.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.43.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.43.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.44.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.44.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.44.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.45.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.45.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.45.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.46.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.46.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.46.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.47.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.47.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.47.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.48.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.48.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.48.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.49.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.49.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.49.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.50.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.50.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.50.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.51.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.51.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.51.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.52.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.52.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.52.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.53.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.53.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.53.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.54.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.54.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.54.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.55.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.55.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.55.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.56.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.56.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.56.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.57.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.57.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.57.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.58.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.58.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.58.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.59.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.59.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.59.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.60.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.60.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.60.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.61.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.61.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.61.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.62.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.62.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.62.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.63.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.63.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.63.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.64.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.64.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.64.w3.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.65.w1.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.65.w2.weight": "model-00064-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.65.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.66.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.66.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.66.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.67.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.67.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.67.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.68.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.68.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.68.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.69.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.69.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.69.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.70.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.70.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.70.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.71.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.71.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.71.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.72.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.72.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.72.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.73.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.73.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.73.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.74.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.74.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.74.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.75.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.75.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.75.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.76.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.76.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.76.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.77.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.77.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.77.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.78.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.78.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.78.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.79.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.79.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.79.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.8.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.8.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.8.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.80.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.80.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.80.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.81.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.81.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.81.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.82.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.82.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.82.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.83.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.83.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.83.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.84.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.84.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.84.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.85.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.85.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.85.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.86.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.86.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.86.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.87.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.87.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.87.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.88.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.88.w2.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.88.w3.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.89.w1.weight": "model-00065-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.89.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.89.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.9.w1.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.9.w2.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.9.w3.weight": "model-00062-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.90.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.90.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.90.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.91.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.91.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.91.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.92.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.92.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.92.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.93.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.93.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.93.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.94.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.94.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.94.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.95.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.95.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.95.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.96.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.96.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.96.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.97.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.97.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.97.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.98.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.98.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.98.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.99.w1.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.99.w2.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.experts.99.w3.weight": "model-00066-of-00195.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00062-of-00195.safetensors", "model.layers.11.input_layernorm.weight": "model-00067-of-00195.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00067-of-00195.safetensors", "model.layers.11.residual_layernorm.weight": "model-00067-of-00195.safetensors", "model.layers.11.residual_mlp.w1.weight": "model-00067-of-00195.safetensors", "model.layers.11.residual_mlp.w2.weight": "model-00067-of-00195.safetensors", "model.layers.11.residual_mlp.w3.weight": "model-00067-of-00195.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00062-of-00195.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00062-of-00195.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00062-of-00195.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00062-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.10.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.10.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.10.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.100.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.100.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.100.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.101.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.101.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.101.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.102.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.102.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.102.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.103.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.103.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.103.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.104.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.104.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.104.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.105.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.105.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.105.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.106.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.106.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.106.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.107.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.107.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.107.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.108.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.108.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.108.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.109.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.109.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.109.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.11.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.11.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.11.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.110.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.110.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.110.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.111.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.111.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.111.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.112.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.112.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.112.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.113.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.113.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.113.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.114.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.114.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.114.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.115.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.115.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.115.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.116.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.116.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.116.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.117.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.117.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.117.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.118.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.118.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.118.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.119.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.119.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.119.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.12.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.12.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.12.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.120.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.120.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.120.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.121.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.121.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.121.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.122.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.122.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.122.w3.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.123.w1.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.123.w2.weight": "model-00072-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.123.w3.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.124.w1.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.124.w2.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.124.w3.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.125.w1.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.125.w2.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.125.w3.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.126.w1.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.126.w2.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.126.w3.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.127.w1.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.127.w2.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.127.w3.weight": "model-00073-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.13.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.13.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.13.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.14.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.14.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.14.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.15.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.15.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.15.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.16.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.16.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.16.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.17.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.17.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.17.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.18.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.18.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.18.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.19.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.19.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.19.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.20.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.20.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.20.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.21.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.21.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.21.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.22.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.22.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.22.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.23.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.23.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.23.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.24.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.24.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.24.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.25.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.25.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.25.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.26.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.26.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.26.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.27.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.27.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.27.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.28.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.28.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.28.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.29.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.29.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.29.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.30.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.30.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.30.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.31.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.31.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.31.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.32.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.32.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.32.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.33.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.33.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.33.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.34.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.34.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.34.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.35.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.35.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.35.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.36.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.36.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.36.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.37.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.37.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.37.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.38.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.38.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.38.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.39.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.39.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.39.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.40.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.40.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.40.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.41.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.41.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.41.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.42.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.42.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.42.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.43.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.43.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.43.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.44.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.44.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.44.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.45.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.45.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.45.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.46.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.46.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.46.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.47.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.47.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.47.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.48.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.48.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.48.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.49.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.49.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.49.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00067-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.50.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.50.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.50.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.51.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.51.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.51.w3.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.52.w1.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.52.w2.weight": "model-00069-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.52.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.53.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.53.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.53.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.54.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.54.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.54.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.55.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.55.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.55.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.56.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.56.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.56.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.57.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.57.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.57.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.58.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.58.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.58.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.59.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.59.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.59.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.60.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.60.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.60.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.61.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.61.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.61.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.62.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.62.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.62.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.63.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.63.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.63.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.64.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.64.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.64.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.65.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.65.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.65.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.66.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.66.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.66.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.67.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.67.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.67.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.68.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.68.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.68.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.69.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.69.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.69.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.70.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.70.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.70.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.71.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.71.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.71.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.72.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.72.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.72.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.73.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.73.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.73.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.74.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.74.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.74.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.75.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.75.w2.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.75.w3.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.76.w1.weight": "model-00070-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.76.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.76.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.77.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.77.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.77.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.78.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.78.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.78.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.79.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.79.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.79.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.8.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.8.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.8.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.80.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.80.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.80.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.81.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.81.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.81.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.82.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.82.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.82.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.83.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.83.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.83.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.84.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.84.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.84.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.85.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.85.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.85.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.86.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.86.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.86.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.87.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.87.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.87.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.88.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.88.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.88.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.89.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.89.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.89.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.9.w1.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.9.w2.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.9.w3.weight": "model-00068-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.90.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.90.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.90.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.91.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.91.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.91.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.92.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.92.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.92.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.93.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.93.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.93.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.94.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.94.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.94.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.95.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.95.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.95.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.96.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.96.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.96.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.97.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.97.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.97.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.98.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.98.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.98.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.99.w1.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.99.w2.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.experts.99.w3.weight": "model-00071-of-00195.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00067-of-00195.safetensors", "model.layers.12.input_layernorm.weight": "model-00073-of-00195.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00073-of-00195.safetensors", "model.layers.12.residual_layernorm.weight": "model-00073-of-00195.safetensors", "model.layers.12.residual_mlp.w1.weight": "model-00073-of-00195.safetensors", "model.layers.12.residual_mlp.w2.weight": "model-00073-of-00195.safetensors", "model.layers.12.residual_mlp.w3.weight": "model-00073-of-00195.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00067-of-00195.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00067-of-00195.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00067-of-00195.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00067-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.10.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.10.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.10.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.100.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.100.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.100.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.101.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.101.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.101.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.102.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.102.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.102.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.103.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.103.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.103.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.104.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.104.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.104.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.105.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.105.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.105.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.106.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.106.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.106.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.107.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.107.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.107.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.108.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.108.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.108.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.109.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.109.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.109.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.11.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.11.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.11.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.110.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.110.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.110.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.111.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.111.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.111.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.112.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.112.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.112.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.113.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.113.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.113.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.114.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.114.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.114.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.115.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.115.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.115.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.116.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.116.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.116.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.117.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.117.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.117.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.118.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.118.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.118.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.119.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.119.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.119.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.12.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.12.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.12.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.120.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.120.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.120.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.121.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.121.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.121.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.122.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.122.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.122.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.123.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.123.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.123.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.124.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.124.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.124.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.125.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.125.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.125.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.126.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.126.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.126.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.127.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.127.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.127.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.13.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.13.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.13.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.14.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.14.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.14.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.15.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.15.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.15.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.16.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.16.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.16.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.17.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.17.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.17.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.18.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.18.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.18.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.19.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.19.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.19.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.20.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.20.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.20.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.21.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.21.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.21.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.22.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.22.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.22.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.23.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.23.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.23.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.24.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.24.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.24.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.25.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.25.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.25.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.26.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.26.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.26.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.27.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.27.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.27.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.28.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.28.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.28.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.29.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.29.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.29.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.30.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.30.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.30.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.31.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.31.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.31.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.32.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.32.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.32.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.33.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.33.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.33.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.34.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.34.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.34.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.35.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.35.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.35.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.36.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.36.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.36.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.37.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.37.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.37.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.38.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.38.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.38.w3.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.39.w1.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.39.w2.weight": "model-00074-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.39.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.40.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.40.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.40.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.41.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.41.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.41.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.42.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.42.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.42.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.43.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.43.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.43.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.44.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.44.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.44.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.45.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.45.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.45.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.46.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.46.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.46.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.47.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.47.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.47.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.48.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.48.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.48.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.49.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.49.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.49.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.50.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.50.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.50.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.51.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.51.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.51.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.52.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.52.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.52.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.53.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.53.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.53.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.54.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.54.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.54.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.55.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.55.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.55.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.56.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.56.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.56.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.57.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.57.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.57.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.58.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.58.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.58.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.59.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.59.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.59.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.60.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.60.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.60.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.61.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.61.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.61.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.62.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.62.w2.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.62.w3.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.63.w1.weight": "model-00075-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.63.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.63.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.64.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.64.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.64.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.65.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.65.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.65.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.66.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.66.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.66.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.67.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.67.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.67.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.68.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.68.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.68.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.69.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.69.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.69.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.70.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.70.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.70.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.71.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.71.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.71.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.72.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.72.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.72.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.73.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.73.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.73.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.74.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.74.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.74.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.75.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.75.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.75.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.76.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.76.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.76.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.77.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.77.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.77.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.78.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.78.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.78.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.79.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.79.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.79.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.8.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.8.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.8.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.80.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.80.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.80.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.81.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.81.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.81.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.82.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.82.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.82.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.83.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.83.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.83.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.84.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.84.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.84.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.85.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.85.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.85.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.86.w1.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.86.w2.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.86.w3.weight": "model-00076-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.87.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.87.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.87.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.88.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.88.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.88.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.89.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.89.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.89.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.9.w1.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.9.w2.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.9.w3.weight": "model-00073-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.90.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.90.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.90.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.91.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.91.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.91.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.92.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.92.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.92.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.93.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.93.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.93.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.94.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.94.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.94.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.95.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.95.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.95.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.96.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.96.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.96.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.97.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.97.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.97.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.98.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.98.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.98.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.99.w1.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.99.w2.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.experts.99.w3.weight": "model-00077-of-00195.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00073-of-00195.safetensors", "model.layers.13.input_layernorm.weight": "model-00078-of-00195.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00078-of-00195.safetensors", "model.layers.13.residual_layernorm.weight": "model-00078-of-00195.safetensors", "model.layers.13.residual_mlp.w1.weight": "model-00078-of-00195.safetensors", "model.layers.13.residual_mlp.w2.weight": "model-00078-of-00195.safetensors", "model.layers.13.residual_mlp.w3.weight": "model-00078-of-00195.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00073-of-00195.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00073-of-00195.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00073-of-00195.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00073-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00078-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00078-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00078-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00078-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00078-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00078-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.10.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.10.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.10.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.100.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.100.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.100.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.101.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.101.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.101.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.102.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.102.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.102.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.103.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.103.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.103.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.104.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.104.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.104.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.105.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.105.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.105.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.106.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.106.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.106.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.107.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.107.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.107.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.108.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.108.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.108.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.109.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.109.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.109.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.11.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.11.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.11.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.110.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.110.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.110.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.111.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.111.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.111.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.112.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.112.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.112.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.113.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.113.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.113.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.114.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.114.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.114.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.115.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.115.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.115.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.116.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.116.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.116.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.117.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.117.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.117.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.118.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.118.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.118.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.119.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.119.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.119.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.12.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.12.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.12.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.120.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.120.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.120.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.121.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.121.w2.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.121.w3.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.122.w1.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.122.w2.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.122.w3.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.123.w1.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.123.w2.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.123.w3.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.124.w1.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.124.w2.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.124.w3.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.125.w1.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.125.w2.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.125.w3.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.126.w1.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.126.w2.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.126.w3.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.127.w1.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.127.w2.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.127.w3.weight": "model-00084-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.13.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.13.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.13.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.14.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.14.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.14.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.15.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.15.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.15.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.16.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.16.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.16.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.17.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.17.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.17.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.18.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.18.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.18.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.19.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.19.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.19.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00078-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00078-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00078-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.20.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.20.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.20.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.21.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.21.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.21.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.22.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.22.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.22.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.23.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.23.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.23.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.24.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.24.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.24.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.25.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.25.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.25.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.26.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.26.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.26.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.27.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.27.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.27.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.28.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.28.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.28.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.29.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.29.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.29.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.30.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.30.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.30.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.31.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.31.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.31.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.32.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.32.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.32.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.33.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.33.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.33.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.34.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.34.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.34.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.35.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.35.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.35.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.36.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.36.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.36.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.37.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.37.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.37.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.38.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.38.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.38.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.39.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.39.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.39.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.40.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.40.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.40.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.41.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.41.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.41.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.42.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.42.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.42.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.43.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.43.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.43.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.44.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.44.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.44.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.45.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.45.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.45.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.46.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.46.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.46.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.47.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.47.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.47.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.48.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.48.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.48.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.49.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.49.w2.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.49.w3.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.50.w1.weight": "model-00080-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.50.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.50.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.51.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.51.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.51.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.52.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.52.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.52.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.53.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.53.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.53.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.54.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.54.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.54.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.55.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.55.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.55.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.56.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.56.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.56.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.57.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.57.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.57.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.58.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.58.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.58.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.59.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.59.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.59.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.60.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.60.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.60.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.61.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.61.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.61.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.62.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.62.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.62.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.63.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.63.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.63.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.64.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.64.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.64.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.65.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.65.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.65.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.66.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.66.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.66.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.67.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.67.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.67.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.68.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.68.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.68.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.69.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.69.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.69.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.70.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.70.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.70.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.71.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.71.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.71.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.72.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.72.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.72.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.73.w1.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.73.w2.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.73.w3.weight": "model-00081-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.74.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.74.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.74.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.75.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.75.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.75.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.76.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.76.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.76.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.77.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.77.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.77.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.78.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.78.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.78.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.79.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.79.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.79.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.8.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.8.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.8.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.80.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.80.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.80.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.81.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.81.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.81.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.82.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.82.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.82.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.83.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.83.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.83.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.84.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.84.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.84.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.85.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.85.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.85.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.86.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.86.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.86.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.87.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.87.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.87.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.88.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.88.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.88.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.89.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.89.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.89.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.9.w1.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.9.w2.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.9.w3.weight": "model-00079-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.90.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.90.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.90.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.91.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.91.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.91.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.92.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.92.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.92.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.93.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.93.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.93.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.94.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.94.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.94.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.95.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.95.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.95.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.96.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.96.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.96.w3.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.97.w1.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.97.w2.weight": "model-00082-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.97.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.98.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.98.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.98.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.99.w1.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.99.w2.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.experts.99.w3.weight": "model-00083-of-00195.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00078-of-00195.safetensors", "model.layers.14.input_layernorm.weight": "model-00084-of-00195.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00084-of-00195.safetensors", "model.layers.14.residual_layernorm.weight": "model-00084-of-00195.safetensors", "model.layers.14.residual_mlp.w1.weight": "model-00084-of-00195.safetensors", "model.layers.14.residual_mlp.w2.weight": "model-00084-of-00195.safetensors", "model.layers.14.residual_mlp.w3.weight": "model-00084-of-00195.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00078-of-00195.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00078-of-00195.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00078-of-00195.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00078-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.10.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.10.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.10.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.100.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.100.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.100.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.101.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.101.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.101.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.102.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.102.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.102.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.103.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.103.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.103.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.104.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.104.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.104.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.105.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.105.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.105.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.106.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.106.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.106.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.107.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.107.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.107.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.108.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.108.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.108.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.109.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.109.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.109.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.11.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.11.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.11.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.110.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.110.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.110.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.111.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.111.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.111.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.112.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.112.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.112.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.113.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.113.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.113.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.114.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.114.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.114.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.115.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.115.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.115.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.116.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.116.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.116.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.117.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.117.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.117.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.118.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.118.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.118.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.119.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.119.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.119.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.12.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.12.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.12.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.120.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.120.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.120.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.121.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.121.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.121.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.122.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.122.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.122.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.123.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.123.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.123.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.124.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.124.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.124.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.125.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.125.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.125.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.126.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.126.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.126.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.127.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.127.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.127.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.13.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.13.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.13.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.14.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.14.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.14.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.15.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.15.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.15.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.16.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.16.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.16.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.17.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.17.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.17.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.18.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.18.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.18.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.19.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.19.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.19.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.20.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.20.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.20.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.21.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.21.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.21.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.22.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.22.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.22.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.23.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.23.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.23.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.24.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.24.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.24.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.25.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.25.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.25.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.26.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.26.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.26.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.27.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.27.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.27.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.28.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.28.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.28.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.29.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.29.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.29.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.30.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.30.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.30.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.31.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.31.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.31.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.32.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.32.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.32.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.33.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.33.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.33.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.34.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.34.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.34.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.35.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.35.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.35.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.36.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.36.w2.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.36.w3.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.37.w1.weight": "model-00085-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.37.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.37.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.38.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.38.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.38.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.39.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.39.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.39.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.40.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.40.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.40.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.41.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.41.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.41.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.42.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.42.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.42.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.43.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.43.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.43.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.44.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.44.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.44.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.45.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.45.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.45.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.46.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.46.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.46.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.47.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.47.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.47.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.48.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.48.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.48.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.49.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.49.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.49.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.50.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.50.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.50.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.51.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.51.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.51.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.52.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.52.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.52.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.53.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.53.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.53.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.54.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.54.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.54.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.55.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.55.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.55.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.56.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.56.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.56.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.57.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.57.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.57.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.58.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.58.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.58.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.59.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.59.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.59.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.60.w1.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.60.w2.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.60.w3.weight": "model-00086-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.61.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.61.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.61.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.62.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.62.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.62.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.63.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.63.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.63.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.64.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.64.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.64.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.65.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.65.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.65.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.66.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.66.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.66.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.67.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.67.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.67.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.68.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.68.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.68.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.69.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.69.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.69.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.70.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.70.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.70.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.71.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.71.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.71.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.72.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.72.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.72.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.73.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.73.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.73.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.74.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.74.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.74.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.75.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.75.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.75.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.76.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.76.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.76.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.77.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.77.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.77.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.78.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.78.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.78.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.79.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.79.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.79.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.8.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.8.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.8.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.80.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.80.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.80.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.81.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.81.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.81.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.82.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.82.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.82.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.83.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.83.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.83.w3.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.84.w1.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.84.w2.weight": "model-00087-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.84.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.85.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.85.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.85.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.86.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.86.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.86.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.87.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.87.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.87.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.88.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.88.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.88.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.89.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.89.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.89.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.9.w1.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.9.w2.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.9.w3.weight": "model-00084-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.90.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.90.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.90.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.91.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.91.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.91.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.92.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.92.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.92.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.93.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.93.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.93.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.94.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.94.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.94.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.95.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.95.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.95.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.96.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.96.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.96.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.97.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.97.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.97.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.98.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.98.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.98.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.99.w1.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.99.w2.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.experts.99.w3.weight": "model-00088-of-00195.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00084-of-00195.safetensors", "model.layers.15.input_layernorm.weight": "model-00089-of-00195.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00089-of-00195.safetensors", "model.layers.15.residual_layernorm.weight": "model-00089-of-00195.safetensors", "model.layers.15.residual_mlp.w1.weight": "model-00089-of-00195.safetensors", "model.layers.15.residual_mlp.w2.weight": "model-00089-of-00195.safetensors", "model.layers.15.residual_mlp.w3.weight": "model-00089-of-00195.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00084-of-00195.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00084-of-00195.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00084-of-00195.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00084-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00089-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00089-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.10.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.10.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.10.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.100.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.100.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.100.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.101.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.101.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.101.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.102.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.102.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.102.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.103.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.103.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.103.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.104.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.104.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.104.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.105.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.105.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.105.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.106.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.106.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.106.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.107.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.107.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.107.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.108.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.108.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.108.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.109.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.109.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.109.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.11.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.11.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.11.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.110.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.110.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.110.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.111.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.111.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.111.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.112.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.112.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.112.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.113.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.113.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.113.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.114.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.114.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.114.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.115.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.115.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.115.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.116.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.116.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.116.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.117.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.117.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.117.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.118.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.118.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.118.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.119.w1.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.119.w2.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.119.w3.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.12.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.12.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.12.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.120.w1.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.120.w2.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.120.w3.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.121.w1.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.121.w2.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.121.w3.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.122.w1.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.122.w2.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.122.w3.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.123.w1.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.123.w2.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.123.w3.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.124.w1.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.124.w2.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.124.w3.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.125.w1.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.125.w2.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.125.w3.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.126.w1.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.126.w2.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.126.w3.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.127.w1.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.127.w2.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.127.w3.weight": "model-00095-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.13.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.13.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.13.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.14.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.14.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.14.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.15.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.15.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.15.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.16.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.16.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.16.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.17.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.17.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.17.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.18.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.18.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.18.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.19.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.19.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.19.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.20.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.20.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.20.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.21.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.21.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.21.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.22.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.22.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.22.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.23.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.23.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.23.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.24.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.24.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.24.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.25.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.25.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.25.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.26.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.26.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.26.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.27.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.27.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.27.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.28.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.28.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.28.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.29.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.29.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.29.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.30.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.30.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.30.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.31.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.31.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.31.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.32.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.32.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.32.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.33.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.33.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.33.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.34.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.34.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.34.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.35.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.35.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.35.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.36.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.36.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.36.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.37.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.37.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.37.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.38.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.38.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.38.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.39.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.39.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.39.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.40.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.40.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.40.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.41.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.41.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.41.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.42.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.42.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.42.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.43.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.43.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.43.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.44.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.44.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.44.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.45.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.45.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.45.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.46.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.46.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.46.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.47.w1.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.47.w2.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.47.w3.weight": "model-00091-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.48.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.48.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.48.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.49.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.49.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.49.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.50.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.50.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.50.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.51.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.51.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.51.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.52.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.52.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.52.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.53.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.53.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.53.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.54.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.54.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.54.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.55.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.55.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.55.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.56.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.56.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.56.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.57.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.57.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.57.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.58.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.58.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.58.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.59.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.59.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.59.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.60.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.60.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.60.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.61.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.61.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.61.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.62.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.62.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.62.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.63.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.63.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.63.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.64.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.64.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.64.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.65.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.65.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.65.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.66.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.66.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.66.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.67.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.67.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.67.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.68.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.68.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.68.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.69.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.69.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.69.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.70.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.70.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.70.w3.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.71.w1.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.71.w2.weight": "model-00092-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.71.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.72.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.72.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.72.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.73.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.73.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.73.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.74.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.74.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.74.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.75.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.75.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.75.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.76.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.76.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.76.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.77.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.77.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.77.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.78.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.78.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.78.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.79.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.79.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.79.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.8.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.8.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.8.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.80.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.80.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.80.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.81.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.81.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.81.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.82.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.82.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.82.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.83.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.83.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.83.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.84.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.84.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.84.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.85.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.85.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.85.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.86.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.86.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.86.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.87.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.87.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.87.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.88.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.88.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.88.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.89.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.89.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.89.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.9.w1.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.9.w2.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.9.w3.weight": "model-00090-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.90.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.90.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.90.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.91.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.91.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.91.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.92.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.92.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.92.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.93.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.93.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.93.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.94.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.94.w2.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.94.w3.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.95.w1.weight": "model-00093-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.95.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.95.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.96.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.96.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.96.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.97.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.97.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.97.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.98.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.98.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.98.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.99.w1.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.99.w2.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.experts.99.w3.weight": "model-00094-of-00195.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00089-of-00195.safetensors", "model.layers.16.input_layernorm.weight": "model-00095-of-00195.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00095-of-00195.safetensors", "model.layers.16.residual_layernorm.weight": "model-00095-of-00195.safetensors", "model.layers.16.residual_mlp.w1.weight": "model-00095-of-00195.safetensors", "model.layers.16.residual_mlp.w2.weight": "model-00095-of-00195.safetensors", "model.layers.16.residual_mlp.w3.weight": "model-00095-of-00195.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00089-of-00195.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00089-of-00195.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00089-of-00195.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00089-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.10.w1.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.10.w2.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.10.w3.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.100.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.100.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.100.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.101.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.101.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.101.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.102.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.102.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.102.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.103.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.103.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.103.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.104.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.104.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.104.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.105.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.105.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.105.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.106.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.106.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.106.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.107.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.107.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.107.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.108.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.108.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.108.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.109.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.109.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.109.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.11.w1.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.11.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.11.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.110.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.110.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.110.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.111.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.111.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.111.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.112.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.112.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.112.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.113.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.113.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.113.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.114.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.114.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.114.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.115.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.115.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.115.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.116.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.116.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.116.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.117.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.117.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.117.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.118.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.118.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.118.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.119.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.119.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.119.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.12.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.12.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.12.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.120.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.120.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.120.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.121.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.121.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.121.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.122.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.122.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.122.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.123.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.123.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.123.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.124.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.124.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.124.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.125.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.125.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.125.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.126.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.126.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.126.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.127.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.127.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.127.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.13.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.13.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.13.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.14.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.14.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.14.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.15.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.15.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.15.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.16.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.16.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.16.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.17.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.17.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.17.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.18.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.18.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.18.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.19.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.19.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.19.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.20.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.20.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.20.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.21.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.21.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.21.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.22.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.22.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.22.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.23.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.23.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.23.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.24.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.24.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.24.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.25.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.25.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.25.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.26.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.26.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.26.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.27.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.27.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.27.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.28.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.28.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.28.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.29.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.29.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.29.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.30.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.30.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.30.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.31.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.31.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.31.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.32.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.32.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.32.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.33.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.33.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.33.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.34.w1.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.34.w2.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.34.w3.weight": "model-00096-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.35.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.35.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.35.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.36.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.36.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.36.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.37.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.37.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.37.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.38.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.38.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.38.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.39.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.39.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.39.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.40.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.40.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.40.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.41.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.41.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.41.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.42.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.42.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.42.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.43.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.43.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.43.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.44.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.44.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.44.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.45.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.45.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.45.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.46.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.46.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.46.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.47.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.47.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.47.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.48.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.48.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.48.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.49.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.49.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.49.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.50.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.50.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.50.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.51.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.51.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.51.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.52.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.52.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.52.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.53.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.53.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.53.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.54.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.54.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.54.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.55.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.55.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.55.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.56.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.56.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.56.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.57.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.57.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.57.w3.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.58.w1.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.58.w2.weight": "model-00097-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.58.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.59.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.59.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.59.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.60.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.60.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.60.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.61.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.61.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.61.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.62.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.62.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.62.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.63.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.63.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.63.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.64.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.64.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.64.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.65.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.65.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.65.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.66.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.66.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.66.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.67.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.67.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.67.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.68.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.68.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.68.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.69.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.69.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.69.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.70.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.70.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.70.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.71.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.71.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.71.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.72.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.72.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.72.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.73.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.73.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.73.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.74.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.74.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.74.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.75.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.75.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.75.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.76.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.76.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.76.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.77.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.77.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.77.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.78.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.78.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.78.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.79.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.79.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.79.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.8.w1.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.8.w2.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.8.w3.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.80.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.80.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.80.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.81.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.81.w2.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.81.w3.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.82.w1.weight": "model-00098-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.82.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.82.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.83.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.83.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.83.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.84.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.84.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.84.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.85.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.85.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.85.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.86.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.86.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.86.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.87.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.87.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.87.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.88.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.88.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.88.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.89.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.89.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.89.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.9.w1.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.9.w2.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.9.w3.weight": "model-00095-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.90.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.90.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.90.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.91.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.91.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.91.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.92.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.92.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.92.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.93.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.93.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.93.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.94.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.94.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.94.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.95.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.95.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.95.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.96.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.96.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.96.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.97.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.97.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.97.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.98.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.98.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.98.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.99.w1.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.99.w2.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.experts.99.w3.weight": "model-00099-of-00195.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00095-of-00195.safetensors", "model.layers.17.input_layernorm.weight": "model-00100-of-00195.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00100-of-00195.safetensors", "model.layers.17.residual_layernorm.weight": "model-00100-of-00195.safetensors", "model.layers.17.residual_mlp.w1.weight": "model-00100-of-00195.safetensors", "model.layers.17.residual_mlp.w2.weight": "model-00100-of-00195.safetensors", "model.layers.17.residual_mlp.w3.weight": "model-00100-of-00195.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00095-of-00195.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00095-of-00195.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00095-of-00195.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00095-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.10.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.10.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.10.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.100.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.100.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.100.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.101.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.101.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.101.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.102.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.102.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.102.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.103.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.103.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.103.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.104.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.104.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.104.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.105.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.105.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.105.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.106.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.106.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.106.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.107.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.107.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.107.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.108.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.108.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.108.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.109.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.109.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.109.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.11.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.11.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.11.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.110.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.110.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.110.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.111.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.111.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.111.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.112.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.112.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.112.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.113.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.113.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.113.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.114.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.114.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.114.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.115.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.115.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.115.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.116.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.116.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.116.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.117.w1.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.117.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.117.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.118.w1.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.118.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.118.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.119.w1.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.119.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.119.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.12.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.12.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.12.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.120.w1.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.120.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.120.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.121.w1.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.121.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.121.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.122.w1.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.122.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.122.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.123.w1.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.123.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.123.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.124.w1.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.124.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.124.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.125.w1.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.125.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.125.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.126.w1.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.126.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.126.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.127.w1.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.127.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.127.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.13.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.13.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.13.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.14.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.14.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.14.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.15.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.15.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.15.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.16.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.16.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.16.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.17.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.17.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.17.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.18.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.18.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.18.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.19.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.19.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.19.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.20.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.20.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.20.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.21.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.21.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.21.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.22.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.22.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.22.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.23.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.23.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.23.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.24.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.24.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.24.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.25.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.25.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.25.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.26.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.26.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.26.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.27.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.27.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.27.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.28.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.28.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.28.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.29.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.29.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.29.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.30.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.30.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.30.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.31.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.31.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.31.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.32.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.32.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.32.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.33.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.33.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.33.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.34.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.34.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.34.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.35.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.35.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.35.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.36.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.36.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.36.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.37.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.37.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.37.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.38.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.38.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.38.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.39.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.39.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.39.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.40.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.40.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.40.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.41.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.41.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.41.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.42.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.42.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.42.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.43.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.43.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.43.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.44.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.44.w2.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.44.w3.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.45.w1.weight": "model-00102-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.45.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.45.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.46.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.46.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.46.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.47.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.47.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.47.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.48.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.48.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.48.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.49.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.49.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.49.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.50.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.50.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.50.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.51.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.51.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.51.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.52.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.52.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.52.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.53.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.53.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.53.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.54.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.54.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.54.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.55.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.55.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.55.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.56.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.56.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.56.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.57.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.57.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.57.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.58.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.58.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.58.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.59.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.59.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.59.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.60.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.60.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.60.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.61.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.61.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.61.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.62.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.62.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.62.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.63.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.63.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.63.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.64.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.64.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.64.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.65.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.65.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.65.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.66.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.66.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.66.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.67.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.67.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.67.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.68.w1.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.68.w2.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.68.w3.weight": "model-00103-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.69.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.69.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.69.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.70.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.70.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.70.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.71.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.71.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.71.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.72.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.72.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.72.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.73.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.73.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.73.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.74.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.74.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.74.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.75.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.75.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.75.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.76.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.76.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.76.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.77.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.77.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.77.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.78.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.78.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.78.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.79.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.79.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.79.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.8.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.8.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.8.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.80.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.80.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.80.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.81.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.81.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.81.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.82.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.82.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.82.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.83.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.83.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.83.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.84.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.84.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.84.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.85.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.85.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.85.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.86.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.86.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.86.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.87.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.87.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.87.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.88.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.88.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.88.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.89.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.89.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.89.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.9.w1.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.9.w2.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.9.w3.weight": "model-00101-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.90.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.90.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.90.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.91.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.91.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.91.w3.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.92.w1.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.92.w2.weight": "model-00104-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.92.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.93.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.93.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.93.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.94.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.94.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.94.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.95.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.95.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.95.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.96.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.96.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.96.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.97.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.97.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.97.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.98.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.98.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.98.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.99.w1.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.99.w2.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.experts.99.w3.weight": "model-00105-of-00195.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00101-of-00195.safetensors", "model.layers.18.input_layernorm.weight": "model-00106-of-00195.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00106-of-00195.safetensors", "model.layers.18.residual_layernorm.weight": "model-00106-of-00195.safetensors", "model.layers.18.residual_mlp.w1.weight": "model-00106-of-00195.safetensors", "model.layers.18.residual_mlp.w2.weight": "model-00106-of-00195.safetensors", "model.layers.18.residual_mlp.w3.weight": "model-00106-of-00195.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00101-of-00195.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00101-of-00195.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00101-of-00195.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00101-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.10.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.10.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.10.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.100.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.100.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.100.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.101.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.101.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.101.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.102.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.102.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.102.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.103.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.103.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.103.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.104.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.104.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.104.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.105.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.105.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.105.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.106.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.106.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.106.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.107.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.107.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.107.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.108.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.108.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.108.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.109.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.109.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.109.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.11.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.11.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.11.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.110.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.110.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.110.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.111.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.111.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.111.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.112.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.112.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.112.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.113.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.113.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.113.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.114.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.114.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.114.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.115.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.115.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.115.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.116.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.116.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.116.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.117.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.117.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.117.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.118.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.118.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.118.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.119.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.119.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.119.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.12.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.12.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.12.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.120.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.120.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.120.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.121.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.121.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.121.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.122.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.122.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.122.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.123.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.123.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.123.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.124.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.124.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.124.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.125.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.125.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.125.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.126.w1.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.126.w2.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.126.w3.weight": "model-00111-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.127.w1.weight": "model-00112-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.127.w2.weight": "model-00112-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.127.w3.weight": "model-00112-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.13.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.13.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.13.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.14.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.14.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.14.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.15.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.15.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.15.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.16.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.16.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.16.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.17.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.17.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.17.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.18.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.18.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.18.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.19.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.19.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.19.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.20.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.20.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.20.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.21.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.21.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.21.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.22.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.22.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.22.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.23.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.23.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.23.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.24.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.24.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.24.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.25.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.25.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.25.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.26.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.26.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.26.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.27.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.27.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.27.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.28.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.28.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.28.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.29.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.29.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.29.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.30.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.30.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.30.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.31.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.31.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.31.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.32.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.32.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.32.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.33.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.33.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.33.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.34.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.34.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.34.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.35.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.35.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.35.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.36.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.36.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.36.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.37.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.37.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.37.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.38.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.38.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.38.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.39.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.39.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.39.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.40.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.40.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.40.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.41.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.41.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.41.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.42.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.42.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.42.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.43.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.43.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.43.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.44.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.44.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.44.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.45.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.45.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.45.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.46.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.46.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.46.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.47.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.47.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.47.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.48.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.48.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.48.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.49.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.49.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.49.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.50.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.50.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.50.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.51.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.51.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.51.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.52.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.52.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.52.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.53.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.53.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.53.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.54.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.54.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.54.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.55.w1.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.55.w2.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.55.w3.weight": "model-00108-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.56.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.56.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.56.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.57.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.57.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.57.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.58.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.58.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.58.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.59.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.59.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.59.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.60.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.60.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.60.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.61.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.61.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.61.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.62.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.62.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.62.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.63.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.63.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.63.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.64.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.64.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.64.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.65.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.65.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.65.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.66.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.66.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.66.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.67.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.67.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.67.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.68.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.68.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.68.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.69.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.69.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.69.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.70.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.70.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.70.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.71.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.71.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.71.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.72.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.72.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.72.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.73.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.73.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.73.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.74.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.74.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.74.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.75.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.75.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.75.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.76.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.76.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.76.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.77.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.77.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.77.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.78.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.78.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.78.w3.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.79.w1.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.79.w2.weight": "model-00109-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.79.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.8.w1.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.8.w2.weight": "model-00106-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.8.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.80.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.80.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.80.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.81.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.81.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.81.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.82.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.82.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.82.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.83.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.83.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.83.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.84.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.84.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.84.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.85.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.85.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.85.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.86.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.86.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.86.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.87.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.87.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.87.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.88.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.88.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.88.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.89.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.89.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.89.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.9.w1.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.9.w2.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.9.w3.weight": "model-00107-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.90.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.90.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.90.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.91.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.91.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.91.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.92.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.92.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.92.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.93.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.93.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.93.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.94.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.94.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.94.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.95.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.95.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.95.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.96.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.96.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.96.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.97.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.97.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.97.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.98.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.98.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.98.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.99.w1.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.99.w2.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.experts.99.w3.weight": "model-00110-of-00195.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00106-of-00195.safetensors", "model.layers.19.input_layernorm.weight": "model-00112-of-00195.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00112-of-00195.safetensors", "model.layers.19.residual_layernorm.weight": "model-00112-of-00195.safetensors", "model.layers.19.residual_mlp.w1.weight": "model-00112-of-00195.safetensors", "model.layers.19.residual_mlp.w2.weight": "model-00112-of-00195.safetensors", "model.layers.19.residual_mlp.w3.weight": "model-00112-of-00195.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00106-of-00195.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00106-of-00195.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00106-of-00195.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00106-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.10.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.10.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.10.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.100.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.100.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.100.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.101.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.101.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.101.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.102.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.102.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.102.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.103.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.103.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.103.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.104.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.104.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.104.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.105.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.105.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.105.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.106.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.106.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.106.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.107.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.107.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.107.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.108.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.108.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.108.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.109.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.109.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.109.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.11.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.11.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.11.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.110.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.110.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.110.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.111.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.111.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.111.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.112.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.112.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.112.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.113.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.113.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.113.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.114.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.114.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.114.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.115.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.115.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.115.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.116.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.116.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.116.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.117.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.117.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.117.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.118.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.118.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.118.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.119.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.119.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.119.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.12.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.12.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.12.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.120.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.120.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.120.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.121.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.121.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.121.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.122.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.122.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.122.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.123.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.123.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.123.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.124.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.124.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.124.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.125.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.125.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.125.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.126.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.126.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.126.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.127.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.127.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.127.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.13.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.13.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.13.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.14.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.14.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.14.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.15.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.15.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.15.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.16.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.16.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.16.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.17.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.17.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.17.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.18.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.18.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.18.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.19.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.19.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.19.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.20.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.20.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.20.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.21.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.21.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.21.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.22.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.22.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.22.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.23.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.23.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.23.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.24.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.24.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.24.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.25.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.25.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.25.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.26.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.26.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.26.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.27.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.27.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.27.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.28.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.28.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.28.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.29.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.29.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.29.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.30.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.30.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.30.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.31.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.31.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.31.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.32.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.32.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.32.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.33.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.33.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.33.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.34.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.34.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.34.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.35.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.35.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.35.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.36.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.36.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.36.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.37.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.37.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.37.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.38.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.38.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.38.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.39.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.39.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.39.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.40.w1.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.40.w2.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.40.w3.weight": "model-00013-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.41.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.41.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.41.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.42.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.42.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.42.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.43.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.43.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.43.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.44.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.44.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.44.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.45.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.45.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.45.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.46.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.46.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.46.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.47.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.47.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.47.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.48.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.48.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.48.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.49.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.49.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.49.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.50.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.50.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.50.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.51.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.51.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.51.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.52.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.52.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.52.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.53.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.53.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.53.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.54.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.54.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.54.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.55.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.55.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.55.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.56.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.56.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.56.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.57.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.57.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.57.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.58.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.58.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.58.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.59.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.59.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.59.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.60.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.60.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.60.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.61.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.61.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.61.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.62.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.62.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.62.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.63.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.63.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.63.w3.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.64.w1.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.64.w2.weight": "model-00014-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.64.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.65.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.65.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.65.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.66.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.66.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.66.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.67.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.67.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.67.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.68.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.68.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.68.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.69.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.69.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.69.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.70.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.70.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.70.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.71.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.71.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.71.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.72.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.72.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.72.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.73.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.73.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.73.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.74.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.74.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.74.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.75.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.75.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.75.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.76.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.76.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.76.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.77.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.77.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.77.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.78.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.78.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.78.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.79.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.79.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.79.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.8.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.8.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.8.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.80.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.80.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.80.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.81.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.81.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.81.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.82.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.82.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.82.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.83.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.83.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.83.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.84.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.84.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.84.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.85.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.85.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.85.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.86.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.86.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.86.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.87.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.87.w2.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.87.w3.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.88.w1.weight": "model-00015-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.88.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.88.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.89.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.89.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.89.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.9.w1.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.9.w2.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.9.w3.weight": "model-00012-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.90.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.90.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.90.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.91.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.91.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.91.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.92.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.92.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.92.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.93.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.93.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.93.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.94.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.94.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.94.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.95.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.95.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.95.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.96.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.96.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.96.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.97.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.97.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.97.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.98.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.98.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.98.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.99.w1.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.99.w2.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.experts.99.w3.weight": "model-00016-of-00195.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00012-of-00195.safetensors", "model.layers.2.input_layernorm.weight": "model-00017-of-00195.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00017-of-00195.safetensors", "model.layers.2.residual_layernorm.weight": "model-00017-of-00195.safetensors", "model.layers.2.residual_mlp.w1.weight": "model-00017-of-00195.safetensors", "model.layers.2.residual_mlp.w2.weight": "model-00017-of-00195.safetensors", "model.layers.2.residual_mlp.w3.weight": "model-00017-of-00195.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00195.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00195.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00195.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.10.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.10.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.10.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.100.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.100.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.100.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.101.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.101.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.101.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.102.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.102.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.102.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.103.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.103.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.103.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.104.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.104.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.104.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.105.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.105.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.105.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.106.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.106.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.106.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.107.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.107.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.107.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.108.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.108.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.108.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.109.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.109.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.109.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.11.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.11.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.11.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.110.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.110.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.110.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.111.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.111.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.111.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.112.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.112.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.112.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.113.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.113.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.113.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.114.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.114.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.114.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.115.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.115.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.115.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.116.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.116.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.116.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.117.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.117.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.117.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.118.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.118.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.118.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.119.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.119.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.119.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.12.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.12.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.12.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.120.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.120.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.120.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.121.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.121.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.121.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.122.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.122.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.122.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.123.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.123.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.123.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.124.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.124.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.124.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.125.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.125.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.125.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.126.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.126.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.126.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.127.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.127.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.127.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.13.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.13.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.13.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.14.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.14.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.14.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.15.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.15.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.15.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.16.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.16.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.16.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.17.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.17.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.17.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.18.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.18.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.18.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.19.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.19.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.19.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.20.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.20.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.20.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.21.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.21.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.21.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.22.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.22.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.22.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.23.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.23.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.23.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.24.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.24.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.24.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.25.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.25.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.25.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.26.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.26.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.26.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.27.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.27.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.27.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.28.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.28.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.28.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.29.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.29.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.29.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.30.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.30.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.30.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.31.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.31.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.31.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.32.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.32.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.32.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.33.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.33.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.33.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.34.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.34.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.34.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.35.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.35.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.35.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.36.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.36.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.36.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.37.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.37.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.37.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.38.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.38.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.38.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.39.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.39.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.39.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.40.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.40.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.40.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.41.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.41.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.41.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.42.w1.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.42.w2.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.42.w3.weight": "model-00113-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.43.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.43.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.43.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.44.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.44.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.44.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.45.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.45.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.45.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.46.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.46.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.46.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.47.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.47.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.47.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.48.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.48.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.48.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.49.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.49.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.49.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.50.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.50.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.50.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.51.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.51.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.51.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.52.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.52.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.52.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.53.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.53.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.53.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.54.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.54.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.54.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.55.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.55.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.55.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.56.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.56.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.56.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.57.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.57.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.57.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.58.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.58.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.58.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.59.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.59.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.59.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.60.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.60.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.60.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.61.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.61.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.61.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.62.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.62.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.62.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.63.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.63.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.63.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.64.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.64.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.64.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.65.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.65.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.65.w3.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.66.w1.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.66.w2.weight": "model-00114-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.66.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.67.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.67.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.67.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.68.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.68.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.68.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.69.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.69.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.69.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.70.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.70.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.70.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.71.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.71.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.71.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.72.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.72.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.72.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.73.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.73.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.73.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.74.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.74.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.74.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.75.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.75.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.75.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.76.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.76.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.76.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.77.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.77.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.77.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.78.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.78.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.78.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.79.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.79.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.79.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.8.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.8.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.8.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.80.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.80.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.80.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.81.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.81.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.81.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.82.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.82.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.82.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.83.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.83.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.83.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.84.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.84.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.84.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.85.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.85.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.85.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.86.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.86.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.86.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.87.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.87.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.87.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.88.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.88.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.88.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.89.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.89.w2.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.89.w3.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.9.w1.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.9.w2.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.9.w3.weight": "model-00112-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.90.w1.weight": "model-00115-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.90.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.90.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.91.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.91.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.91.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.92.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.92.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.92.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.93.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.93.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.93.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.94.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.94.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.94.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.95.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.95.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.95.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.96.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.96.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.96.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.97.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.97.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.97.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.98.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.98.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.98.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.99.w1.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.99.w2.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.experts.99.w3.weight": "model-00116-of-00195.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00112-of-00195.safetensors", "model.layers.20.input_layernorm.weight": "model-00117-of-00195.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00117-of-00195.safetensors", "model.layers.20.residual_layernorm.weight": "model-00117-of-00195.safetensors", "model.layers.20.residual_mlp.w1.weight": "model-00117-of-00195.safetensors", "model.layers.20.residual_mlp.w2.weight": "model-00117-of-00195.safetensors", "model.layers.20.residual_mlp.w3.weight": "model-00117-of-00195.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00112-of-00195.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00112-of-00195.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00112-of-00195.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00112-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.10.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.10.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.10.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.100.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.100.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.100.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.101.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.101.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.101.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.102.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.102.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.102.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.103.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.103.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.103.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.104.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.104.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.104.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.105.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.105.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.105.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.106.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.106.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.106.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.107.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.107.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.107.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.108.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.108.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.108.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.109.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.109.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.109.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.11.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.11.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.11.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.110.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.110.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.110.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.111.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.111.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.111.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.112.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.112.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.112.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.113.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.113.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.113.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.114.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.114.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.114.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.115.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.115.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.115.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.116.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.116.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.116.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.117.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.117.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.117.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.118.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.118.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.118.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.119.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.119.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.119.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.12.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.12.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.12.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.120.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.120.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.120.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.121.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.121.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.121.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.122.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.122.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.122.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.123.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.123.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.123.w3.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.124.w1.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.124.w2.weight": "model-00122-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.124.w3.weight": "model-00123-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.125.w1.weight": "model-00123-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.125.w2.weight": "model-00123-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.125.w3.weight": "model-00123-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.126.w1.weight": "model-00123-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.126.w2.weight": "model-00123-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.126.w3.weight": "model-00123-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.127.w1.weight": "model-00123-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.127.w2.weight": "model-00123-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.127.w3.weight": "model-00123-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.13.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.13.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.13.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.14.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.14.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.14.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.15.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.15.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.15.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.16.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.16.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.16.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.17.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.17.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.17.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.18.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.18.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.18.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.19.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.19.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.19.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.20.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.20.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.20.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.21.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.21.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.21.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.22.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.22.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.22.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.23.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.23.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.23.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.24.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.24.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.24.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.25.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.25.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.25.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.26.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.26.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.26.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.27.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.27.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.27.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.28.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.28.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.28.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.29.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.29.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.29.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.30.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.30.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.30.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.31.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.31.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.31.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.32.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.32.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.32.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.33.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.33.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.33.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.34.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.34.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.34.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.35.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.35.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.35.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.36.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.36.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.36.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.37.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.37.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.37.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.38.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.38.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.38.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.39.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.39.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.39.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.40.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.40.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.40.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.41.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.41.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.41.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.42.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.42.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.42.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.43.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.43.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.43.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.44.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.44.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.44.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.45.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.45.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.45.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.46.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.46.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.46.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.47.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.47.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.47.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.48.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.48.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.48.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.49.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.49.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.49.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.50.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.50.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.50.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.51.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.51.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.51.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.52.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.52.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.52.w3.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.53.w1.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.53.w2.weight": "model-00119-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.53.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.54.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.54.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.54.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.55.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.55.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.55.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.56.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.56.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.56.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.57.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.57.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.57.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.58.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.58.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.58.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.59.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.59.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.59.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00117-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.60.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.60.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.60.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.61.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.61.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.61.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.62.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.62.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.62.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.63.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.63.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.63.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.64.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.64.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.64.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.65.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.65.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.65.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.66.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.66.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.66.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.67.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.67.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.67.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.68.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.68.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.68.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.69.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.69.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.69.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.70.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.70.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.70.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.71.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.71.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.71.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.72.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.72.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.72.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.73.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.73.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.73.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.74.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.74.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.74.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.75.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.75.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.75.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.76.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.76.w2.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.76.w3.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.77.w1.weight": "model-00120-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.77.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.77.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.78.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.78.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.78.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.79.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.79.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.79.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.8.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.8.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.8.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.80.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.80.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.80.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.81.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.81.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.81.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.82.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.82.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.82.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.83.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.83.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.83.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.84.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.84.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.84.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.85.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.85.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.85.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.86.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.86.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.86.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.87.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.87.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.87.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.88.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.88.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.88.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.89.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.89.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.89.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.9.w1.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.9.w2.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.9.w3.weight": "model-00118-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.90.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.90.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.90.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.91.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.91.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.91.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.92.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.92.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.92.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.93.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.93.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.93.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.94.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.94.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.94.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.95.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.95.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.95.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.96.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.96.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.96.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.97.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.97.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.97.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.98.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.98.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.98.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.99.w1.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.99.w2.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.experts.99.w3.weight": "model-00121-of-00195.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00117-of-00195.safetensors", "model.layers.21.input_layernorm.weight": "model-00123-of-00195.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00123-of-00195.safetensors", "model.layers.21.residual_layernorm.weight": "model-00123-of-00195.safetensors", "model.layers.21.residual_mlp.w1.weight": "model-00123-of-00195.safetensors", "model.layers.21.residual_mlp.w2.weight": "model-00123-of-00195.safetensors", "model.layers.21.residual_mlp.w3.weight": "model-00123-of-00195.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00117-of-00195.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00117-of-00195.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00117-of-00195.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00117-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.10.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.10.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.10.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.100.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.100.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.100.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.101.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.101.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.101.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.102.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.102.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.102.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.103.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.103.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.103.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.104.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.104.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.104.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.105.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.105.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.105.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.106.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.106.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.106.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.107.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.107.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.107.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.108.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.108.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.108.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.109.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.109.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.109.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.11.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.11.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.11.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.110.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.110.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.110.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.111.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.111.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.111.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.112.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.112.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.112.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.113.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.113.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.113.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.114.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.114.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.114.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.115.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.115.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.115.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.116.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.116.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.116.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.117.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.117.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.117.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.118.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.118.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.118.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.119.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.119.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.119.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.12.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.12.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.12.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.120.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.120.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.120.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.121.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.121.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.121.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.122.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.122.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.122.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.123.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.123.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.123.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.124.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.124.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.124.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.125.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.125.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.125.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.126.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.126.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.126.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.127.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.127.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.127.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.13.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.13.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.13.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.14.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.14.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.14.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.15.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.15.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.15.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.16.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.16.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.16.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.17.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.17.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.17.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.18.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.18.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.18.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.19.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.19.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.19.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.20.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.20.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.20.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.21.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.21.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.21.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.22.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.22.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.22.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.23.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.23.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.23.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.24.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.24.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.24.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.25.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.25.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.25.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.26.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.26.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.26.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.27.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.27.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.27.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.28.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.28.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.28.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.29.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.29.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.29.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.30.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.30.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.30.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.31.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.31.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.31.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.32.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.32.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.32.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.33.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.33.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.33.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.34.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.34.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.34.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.35.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.35.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.35.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.36.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.36.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.36.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.37.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.37.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.37.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.38.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.38.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.38.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.39.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.39.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.39.w3.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.40.w1.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.40.w2.weight": "model-00124-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.40.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.41.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.41.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.41.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.42.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.42.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.42.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.43.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.43.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.43.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.44.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.44.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.44.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.45.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.45.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.45.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.46.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.46.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.46.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.47.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.47.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.47.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.48.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.48.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.48.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.49.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.49.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.49.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.50.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.50.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.50.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.51.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.51.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.51.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.52.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.52.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.52.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.53.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.53.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.53.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.54.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.54.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.54.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.55.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.55.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.55.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.56.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.56.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.56.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.57.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.57.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.57.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.58.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.58.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.58.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.59.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.59.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.59.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.60.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.60.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.60.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.61.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.61.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.61.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.62.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.62.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.62.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.63.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.63.w2.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.63.w3.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.64.w1.weight": "model-00125-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.64.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.64.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.65.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.65.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.65.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.66.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.66.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.66.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.67.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.67.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.67.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.68.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.68.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.68.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.69.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.69.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.69.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.70.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.70.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.70.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.71.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.71.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.71.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.72.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.72.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.72.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.73.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.73.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.73.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.74.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.74.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.74.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.75.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.75.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.75.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.76.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.76.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.76.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.77.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.77.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.77.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.78.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.78.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.78.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.79.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.79.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.79.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.8.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.8.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.8.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.80.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.80.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.80.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.81.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.81.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.81.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.82.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.82.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.82.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.83.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.83.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.83.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.84.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.84.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.84.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.85.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.85.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.85.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.86.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.86.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.86.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.87.w1.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.87.w2.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.87.w3.weight": "model-00126-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.88.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.88.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.88.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.89.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.89.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.89.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.9.w1.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.9.w2.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.9.w3.weight": "model-00123-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.90.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.90.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.90.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.91.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.91.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.91.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.92.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.92.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.92.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.93.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.93.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.93.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.94.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.94.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.94.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.95.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.95.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.95.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.96.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.96.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.96.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.97.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.97.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.97.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.98.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.98.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.98.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.99.w1.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.99.w2.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.experts.99.w3.weight": "model-00127-of-00195.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00123-of-00195.safetensors", "model.layers.22.input_layernorm.weight": "model-00128-of-00195.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00128-of-00195.safetensors", "model.layers.22.residual_layernorm.weight": "model-00128-of-00195.safetensors", "model.layers.22.residual_mlp.w1.weight": "model-00128-of-00195.safetensors", "model.layers.22.residual_mlp.w2.weight": "model-00128-of-00195.safetensors", "model.layers.22.residual_mlp.w3.weight": "model-00128-of-00195.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00123-of-00195.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00123-of-00195.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00123-of-00195.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00123-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00128-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00128-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00128-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00128-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00128-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00128-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.10.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.10.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.10.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.100.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.100.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.100.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.101.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.101.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.101.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.102.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.102.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.102.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.103.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.103.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.103.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.104.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.104.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.104.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.105.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.105.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.105.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.106.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.106.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.106.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.107.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.107.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.107.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.108.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.108.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.108.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.109.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.109.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.109.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.11.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.11.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.11.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.110.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.110.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.110.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.111.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.111.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.111.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.112.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.112.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.112.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.113.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.113.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.113.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.114.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.114.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.114.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.115.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.115.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.115.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.116.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.116.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.116.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.117.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.117.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.117.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.118.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.118.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.118.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.119.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.119.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.119.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.12.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.12.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.12.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.120.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.120.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.120.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.121.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.121.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.121.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.122.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.122.w2.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.122.w3.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.123.w1.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.123.w2.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.123.w3.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.124.w1.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.124.w2.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.124.w3.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.125.w1.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.125.w2.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.125.w3.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.126.w1.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.126.w2.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.126.w3.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.127.w1.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.127.w2.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.127.w3.weight": "model-00134-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.13.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.13.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.13.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.14.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.14.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.14.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.15.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.15.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.15.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.16.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.16.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.16.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.17.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.17.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.17.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.18.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.18.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.18.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.19.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.19.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.19.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00128-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00128-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00128-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.20.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.20.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.20.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.21.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.21.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.21.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.22.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.22.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.22.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.23.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.23.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.23.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.24.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.24.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.24.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.25.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.25.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.25.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.26.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.26.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.26.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.27.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.27.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.27.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.28.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.28.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.28.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.29.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.29.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.29.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00128-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00128-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00128-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.30.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.30.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.30.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.31.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.31.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.31.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.32.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.32.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.32.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.33.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.33.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.33.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.34.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.34.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.34.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.35.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.35.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.35.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.36.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.36.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.36.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.37.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.37.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.37.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.38.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.38.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.38.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.39.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.39.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.39.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.40.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.40.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.40.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.41.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.41.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.41.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.42.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.42.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.42.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.43.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.43.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.43.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.44.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.44.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.44.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.45.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.45.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.45.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.46.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.46.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.46.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.47.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.47.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.47.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.48.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.48.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.48.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.49.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.49.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.49.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.50.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.50.w2.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.50.w3.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.51.w1.weight": "model-00130-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.51.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.51.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.52.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.52.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.52.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.53.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.53.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.53.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.54.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.54.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.54.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.55.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.55.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.55.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.56.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.56.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.56.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.57.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.57.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.57.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.58.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.58.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.58.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.59.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.59.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.59.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.60.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.60.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.60.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.61.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.61.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.61.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.62.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.62.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.62.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.63.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.63.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.63.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.64.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.64.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.64.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.65.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.65.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.65.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.66.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.66.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.66.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.67.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.67.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.67.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.68.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.68.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.68.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.69.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.69.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.69.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.70.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.70.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.70.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.71.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.71.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.71.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.72.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.72.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.72.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.73.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.73.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.73.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.74.w1.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.74.w2.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.74.w3.weight": "model-00131-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.75.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.75.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.75.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.76.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.76.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.76.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.77.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.77.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.77.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.78.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.78.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.78.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.79.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.79.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.79.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.8.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.8.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.8.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.80.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.80.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.80.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.81.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.81.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.81.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.82.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.82.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.82.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.83.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.83.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.83.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.84.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.84.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.84.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.85.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.85.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.85.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.86.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.86.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.86.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.87.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.87.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.87.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.88.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.88.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.88.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.89.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.89.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.89.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.9.w1.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.9.w2.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.9.w3.weight": "model-00129-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.90.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.90.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.90.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.91.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.91.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.91.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.92.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.92.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.92.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.93.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.93.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.93.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.94.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.94.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.94.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.95.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.95.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.95.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.96.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.96.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.96.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.97.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.97.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.97.w3.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.98.w1.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.98.w2.weight": "model-00132-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.98.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.99.w1.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.99.w2.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.experts.99.w3.weight": "model-00133-of-00195.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00128-of-00195.safetensors", "model.layers.23.input_layernorm.weight": "model-00134-of-00195.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00134-of-00195.safetensors", "model.layers.23.residual_layernorm.weight": "model-00134-of-00195.safetensors", "model.layers.23.residual_mlp.w1.weight": "model-00134-of-00195.safetensors", "model.layers.23.residual_mlp.w2.weight": "model-00134-of-00195.safetensors", "model.layers.23.residual_mlp.w3.weight": "model-00134-of-00195.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00128-of-00195.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00128-of-00195.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00128-of-00195.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00128-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.10.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.10.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.10.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.100.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.100.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.100.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.101.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.101.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.101.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.102.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.102.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.102.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.103.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.103.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.103.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.104.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.104.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.104.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.105.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.105.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.105.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.106.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.106.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.106.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.107.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.107.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.107.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.108.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.108.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.108.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.109.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.109.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.109.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.11.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.11.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.11.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.110.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.110.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.110.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.111.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.111.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.111.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.112.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.112.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.112.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.113.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.113.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.113.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.114.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.114.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.114.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.115.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.115.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.115.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.116.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.116.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.116.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.117.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.117.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.117.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.118.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.118.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.118.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.119.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.119.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.119.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.12.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.12.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.12.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.120.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.120.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.120.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.121.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.121.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.121.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.122.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.122.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.122.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.123.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.123.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.123.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.124.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.124.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.124.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.125.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.125.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.125.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.126.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.126.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.126.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.127.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.127.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.127.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.13.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.13.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.13.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.14.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.14.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.14.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.15.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.15.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.15.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.16.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.16.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.16.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.17.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.17.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.17.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.18.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.18.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.18.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.19.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.19.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.19.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.20.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.20.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.20.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.21.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.21.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.21.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.22.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.22.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.22.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.23.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.23.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.23.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.24.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.24.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.24.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.25.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.25.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.25.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.26.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.26.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.26.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.27.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.27.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.27.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.28.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.28.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.28.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.29.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.29.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.29.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.30.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.30.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.30.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.31.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.31.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.31.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.32.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.32.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.32.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.33.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.33.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.33.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.34.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.34.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.34.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.35.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.35.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.35.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.36.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.36.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.36.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.37.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.37.w2.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.37.w3.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.38.w1.weight": "model-00135-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.38.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.38.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.39.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.39.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.39.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.40.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.40.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.40.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.41.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.41.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.41.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.42.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.42.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.42.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.43.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.43.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.43.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.44.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.44.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.44.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.45.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.45.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.45.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.46.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.46.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.46.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.47.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.47.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.47.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.48.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.48.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.48.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.49.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.49.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.49.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.50.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.50.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.50.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.51.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.51.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.51.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.52.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.52.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.52.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.53.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.53.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.53.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.54.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.54.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.54.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.55.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.55.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.55.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.56.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.56.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.56.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.57.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.57.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.57.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.58.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.58.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.58.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.59.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.59.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.59.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.60.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.60.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.60.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.61.w1.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.61.w2.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.61.w3.weight": "model-00136-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.62.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.62.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.62.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.63.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.63.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.63.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.64.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.64.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.64.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.65.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.65.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.65.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.66.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.66.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.66.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.67.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.67.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.67.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.68.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.68.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.68.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.69.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.69.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.69.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.70.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.70.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.70.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.71.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.71.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.71.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.72.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.72.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.72.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.73.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.73.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.73.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.74.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.74.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.74.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.75.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.75.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.75.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.76.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.76.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.76.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.77.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.77.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.77.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.78.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.78.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.78.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.79.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.79.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.79.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.8.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.8.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.8.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.80.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.80.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.80.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.81.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.81.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.81.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.82.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.82.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.82.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.83.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.83.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.83.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.84.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.84.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.84.w3.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.85.w1.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.85.w2.weight": "model-00137-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.85.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.86.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.86.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.86.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.87.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.87.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.87.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.88.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.88.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.88.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.89.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.89.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.89.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.9.w1.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.9.w2.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.9.w3.weight": "model-00134-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.90.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.90.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.90.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.91.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.91.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.91.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.92.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.92.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.92.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.93.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.93.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.93.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.94.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.94.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.94.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.95.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.95.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.95.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.96.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.96.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.96.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.97.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.97.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.97.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.98.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.98.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.98.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.99.w1.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.99.w2.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.experts.99.w3.weight": "model-00138-of-00195.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00134-of-00195.safetensors", "model.layers.24.input_layernorm.weight": "model-00139-of-00195.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00139-of-00195.safetensors", "model.layers.24.residual_layernorm.weight": "model-00139-of-00195.safetensors", "model.layers.24.residual_mlp.w1.weight": "model-00139-of-00195.safetensors", "model.layers.24.residual_mlp.w2.weight": "model-00139-of-00195.safetensors", "model.layers.24.residual_mlp.w3.weight": "model-00139-of-00195.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00134-of-00195.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00134-of-00195.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00134-of-00195.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00134-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00139-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00139-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00139-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00139-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00139-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.10.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.10.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.10.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.100.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.100.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.100.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.101.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.101.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.101.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.102.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.102.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.102.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.103.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.103.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.103.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.104.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.104.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.104.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.105.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.105.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.105.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.106.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.106.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.106.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.107.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.107.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.107.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.108.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.108.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.108.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.109.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.109.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.109.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.11.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.11.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.11.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.110.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.110.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.110.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.111.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.111.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.111.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.112.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.112.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.112.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.113.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.113.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.113.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.114.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.114.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.114.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.115.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.115.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.115.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.116.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.116.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.116.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.117.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.117.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.117.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.118.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.118.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.118.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.119.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.119.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.119.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.12.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.12.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.12.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.120.w1.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.120.w2.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.120.w3.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.121.w1.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.121.w2.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.121.w3.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.122.w1.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.122.w2.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.122.w3.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.123.w1.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.123.w2.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.123.w3.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.124.w1.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.124.w2.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.124.w3.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.125.w1.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.125.w2.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.125.w3.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.126.w1.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.126.w2.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.126.w3.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.127.w1.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.127.w2.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.127.w3.weight": "model-00145-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.13.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.13.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.13.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.14.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.14.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.14.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.15.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.15.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.15.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.16.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.16.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.16.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.17.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.17.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.17.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.18.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.18.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.18.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.19.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.19.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.19.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.20.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.20.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.20.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.21.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.21.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.21.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.22.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.22.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.22.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.23.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.23.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.23.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.24.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.24.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.24.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.25.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.25.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.25.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.26.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.26.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.26.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.27.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.27.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.27.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.28.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.28.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.28.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.29.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.29.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.29.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.30.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.30.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.30.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.31.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.31.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.31.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.32.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.32.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.32.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.33.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.33.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.33.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.34.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.34.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.34.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.35.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.35.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.35.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.36.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.36.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.36.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.37.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.37.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.37.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.38.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.38.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.38.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.39.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.39.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.39.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.40.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.40.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.40.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.41.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.41.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.41.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.42.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.42.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.42.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.43.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.43.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.43.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.44.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.44.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.44.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.45.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.45.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.45.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.46.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.46.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.46.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.47.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.47.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.47.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.48.w1.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.48.w2.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.48.w3.weight": "model-00141-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.49.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.49.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.49.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.50.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.50.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.50.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.51.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.51.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.51.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.52.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.52.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.52.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.53.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.53.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.53.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.54.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.54.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.54.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.55.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.55.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.55.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.56.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.56.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.56.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.57.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.57.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.57.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.58.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.58.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.58.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.59.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.59.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.59.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.60.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.60.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.60.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.61.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.61.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.61.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.62.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.62.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.62.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.63.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.63.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.63.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.64.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.64.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.64.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.65.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.65.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.65.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.66.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.66.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.66.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.67.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.67.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.67.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.68.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.68.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.68.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.69.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.69.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.69.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.70.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.70.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.70.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.71.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.71.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.71.w3.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.72.w1.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.72.w2.weight": "model-00142-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.72.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.73.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.73.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.73.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.74.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.74.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.74.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.75.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.75.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.75.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.76.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.76.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.76.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.77.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.77.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.77.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.78.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.78.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.78.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.79.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.79.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.79.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.8.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.8.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.8.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.80.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.80.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.80.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.81.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.81.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.81.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.82.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.82.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.82.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.83.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.83.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.83.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.84.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.84.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.84.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.85.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.85.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.85.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.86.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.86.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.86.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.87.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.87.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.87.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.88.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.88.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.88.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.89.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.89.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.89.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.9.w1.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.9.w2.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.9.w3.weight": "model-00140-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.90.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.90.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.90.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.91.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.91.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.91.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.92.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.92.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.92.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.93.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.93.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.93.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.94.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.94.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.94.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.95.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.95.w2.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.95.w3.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.96.w1.weight": "model-00143-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.96.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.96.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.97.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.97.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.97.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.98.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.98.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.98.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.99.w1.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.99.w2.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.experts.99.w3.weight": "model-00144-of-00195.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00139-of-00195.safetensors", "model.layers.25.input_layernorm.weight": "model-00145-of-00195.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00145-of-00195.safetensors", "model.layers.25.residual_layernorm.weight": "model-00145-of-00195.safetensors", "model.layers.25.residual_mlp.w1.weight": "model-00145-of-00195.safetensors", "model.layers.25.residual_mlp.w2.weight": "model-00145-of-00195.safetensors", "model.layers.25.residual_mlp.w3.weight": "model-00145-of-00195.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00139-of-00195.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00139-of-00195.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00139-of-00195.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00139-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.10.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.10.w2.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.10.w3.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.100.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.100.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.100.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.101.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.101.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.101.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.102.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.102.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.102.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.103.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.103.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.103.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.104.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.104.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.104.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.105.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.105.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.105.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.106.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.106.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.106.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.107.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.107.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.107.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.108.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.108.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.108.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.109.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.109.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.109.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.11.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.11.w2.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.11.w3.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.110.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.110.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.110.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.111.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.111.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.111.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.112.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.112.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.112.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.113.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.113.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.113.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.114.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.114.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.114.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.115.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.115.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.115.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.116.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.116.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.116.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.117.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.117.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.117.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.118.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.118.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.118.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.119.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.119.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.119.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.12.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.12.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.12.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.120.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.120.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.120.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.121.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.121.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.121.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.122.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.122.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.122.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.123.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.123.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.123.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.124.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.124.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.124.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.125.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.125.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.125.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.126.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.126.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.126.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.127.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.127.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.127.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.13.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.13.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.13.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.14.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.14.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.14.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.15.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.15.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.15.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.16.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.16.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.16.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.17.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.17.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.17.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.18.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.18.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.18.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.19.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.19.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.19.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.20.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.20.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.20.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.21.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.21.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.21.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.22.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.22.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.22.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.23.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.23.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.23.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.24.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.24.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.24.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.25.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.25.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.25.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.26.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.26.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.26.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.27.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.27.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.27.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.28.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.28.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.28.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.29.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.29.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.29.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.30.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.30.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.30.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.31.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.31.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.31.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.32.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.32.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.32.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.33.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.33.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.33.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.34.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.34.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.34.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.35.w1.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.35.w2.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.35.w3.weight": "model-00146-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.36.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.36.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.36.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.37.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.37.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.37.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.38.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.38.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.38.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.39.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.39.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.39.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.40.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.40.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.40.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.41.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.41.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.41.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.42.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.42.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.42.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.43.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.43.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.43.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.44.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.44.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.44.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.45.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.45.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.45.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.46.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.46.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.46.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.47.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.47.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.47.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.48.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.48.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.48.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.49.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.49.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.49.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.50.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.50.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.50.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.51.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.51.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.51.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.52.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.52.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.52.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.53.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.53.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.53.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.54.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.54.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.54.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.55.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.55.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.55.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.56.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.56.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.56.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.57.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.57.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.57.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.58.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.58.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.58.w3.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.59.w1.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.59.w2.weight": "model-00147-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.59.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.60.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.60.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.60.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.61.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.61.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.61.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.62.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.62.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.62.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.63.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.63.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.63.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.64.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.64.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.64.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.65.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.65.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.65.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.66.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.66.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.66.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.67.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.67.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.67.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.68.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.68.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.68.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.69.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.69.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.69.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.70.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.70.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.70.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.71.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.71.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.71.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.72.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.72.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.72.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.73.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.73.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.73.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.74.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.74.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.74.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.75.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.75.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.75.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.76.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.76.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.76.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.77.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.77.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.77.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.78.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.78.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.78.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.79.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.79.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.79.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.8.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.8.w2.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.8.w3.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.80.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.80.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.80.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.81.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.81.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.81.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.82.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.82.w2.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.82.w3.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.83.w1.weight": "model-00148-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.83.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.83.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.84.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.84.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.84.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.85.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.85.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.85.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.86.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.86.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.86.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.87.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.87.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.87.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.88.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.88.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.88.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.89.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.89.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.89.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.9.w1.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.9.w2.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.9.w3.weight": "model-00145-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.90.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.90.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.90.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.91.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.91.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.91.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.92.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.92.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.92.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.93.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.93.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.93.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.94.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.94.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.94.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.95.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.95.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.95.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.96.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.96.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.96.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.97.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.97.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.97.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.98.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.98.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.98.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.99.w1.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.99.w2.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.experts.99.w3.weight": "model-00149-of-00195.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00145-of-00195.safetensors", "model.layers.26.input_layernorm.weight": "model-00150-of-00195.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00150-of-00195.safetensors", "model.layers.26.residual_layernorm.weight": "model-00150-of-00195.safetensors", "model.layers.26.residual_mlp.w1.weight": "model-00150-of-00195.safetensors", "model.layers.26.residual_mlp.w2.weight": "model-00150-of-00195.safetensors", "model.layers.26.residual_mlp.w3.weight": "model-00150-of-00195.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00145-of-00195.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00145-of-00195.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00145-of-00195.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00145-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.10.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.10.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.10.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.100.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.100.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.100.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.101.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.101.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.101.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.102.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.102.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.102.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.103.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.103.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.103.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.104.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.104.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.104.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.105.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.105.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.105.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.106.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.106.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.106.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.107.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.107.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.107.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.108.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.108.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.108.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.109.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.109.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.109.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.11.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.11.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.11.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.110.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.110.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.110.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.111.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.111.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.111.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.112.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.112.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.112.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.113.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.113.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.113.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.114.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.114.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.114.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.115.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.115.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.115.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.116.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.116.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.116.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.117.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.117.w2.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.117.w3.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.118.w1.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.118.w2.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.118.w3.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.119.w1.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.119.w2.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.119.w3.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.12.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.12.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.12.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.120.w1.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.120.w2.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.120.w3.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.121.w1.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.121.w2.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.121.w3.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.122.w1.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.122.w2.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.122.w3.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.123.w1.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.123.w2.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.123.w3.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.124.w1.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.124.w2.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.124.w3.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.125.w1.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.125.w2.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.125.w3.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.126.w1.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.126.w2.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.126.w3.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.127.w1.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.127.w2.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.127.w3.weight": "model-00156-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.13.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.13.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.13.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.14.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.14.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.14.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.15.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.15.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.15.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.16.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.16.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.16.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.17.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.17.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.17.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.18.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.18.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.18.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.19.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.19.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.19.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.20.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.20.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.20.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.21.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.21.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.21.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.22.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.22.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.22.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.23.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.23.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.23.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.24.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.24.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.24.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.25.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.25.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.25.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.26.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.26.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.26.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.27.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.27.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.27.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.28.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.28.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.28.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.29.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.29.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.29.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.30.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.30.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.30.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.31.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.31.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.31.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.32.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.32.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.32.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.33.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.33.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.33.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.34.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.34.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.34.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.35.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.35.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.35.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.36.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.36.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.36.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.37.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.37.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.37.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.38.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.38.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.38.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.39.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.39.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.39.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.40.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.40.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.40.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.41.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.41.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.41.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.42.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.42.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.42.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.43.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.43.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.43.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.44.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.44.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.44.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.45.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.45.w2.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.45.w3.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.46.w1.weight": "model-00152-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.46.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.46.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.47.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.47.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.47.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.48.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.48.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.48.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.49.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.49.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.49.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.50.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.50.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.50.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.51.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.51.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.51.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.52.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.52.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.52.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.53.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.53.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.53.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.54.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.54.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.54.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.55.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.55.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.55.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.56.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.56.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.56.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.57.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.57.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.57.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.58.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.58.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.58.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.59.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.59.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.59.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.60.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.60.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.60.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.61.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.61.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.61.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.62.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.62.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.62.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.63.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.63.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.63.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.64.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.64.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.64.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.65.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.65.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.65.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.66.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.66.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.66.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.67.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.67.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.67.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.68.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.68.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.68.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.69.w1.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.69.w2.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.69.w3.weight": "model-00153-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.70.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.70.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.70.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.71.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.71.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.71.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.72.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.72.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.72.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.73.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.73.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.73.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.74.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.74.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.74.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.75.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.75.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.75.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.76.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.76.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.76.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.77.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.77.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.77.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.78.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.78.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.78.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.79.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.79.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.79.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.8.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.8.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.8.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.80.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.80.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.80.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.81.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.81.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.81.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.82.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.82.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.82.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.83.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.83.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.83.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.84.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.84.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.84.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.85.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.85.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.85.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.86.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.86.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.86.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.87.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.87.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.87.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.88.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.88.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.88.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.89.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.89.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.89.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.9.w1.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.9.w2.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.9.w3.weight": "model-00151-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.90.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.90.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.90.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.91.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.91.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.91.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.92.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.92.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.92.w3.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.93.w1.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.93.w2.weight": "model-00154-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.93.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.94.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.94.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.94.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.95.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.95.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.95.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.96.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.96.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.96.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.97.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.97.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.97.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.98.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.98.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.98.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.99.w1.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.99.w2.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.experts.99.w3.weight": "model-00155-of-00195.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00151-of-00195.safetensors", "model.layers.27.input_layernorm.weight": "model-00156-of-00195.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00156-of-00195.safetensors", "model.layers.27.residual_layernorm.weight": "model-00156-of-00195.safetensors", "model.layers.27.residual_mlp.w1.weight": "model-00156-of-00195.safetensors", "model.layers.27.residual_mlp.w2.weight": "model-00156-of-00195.safetensors", "model.layers.27.residual_mlp.w3.weight": "model-00156-of-00195.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00150-of-00195.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00151-of-00195.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00150-of-00195.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00151-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.10.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.10.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.10.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.100.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.100.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.100.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.101.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.101.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.101.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.102.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.102.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.102.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.103.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.103.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.103.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.104.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.104.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.104.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.105.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.105.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.105.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.106.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.106.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.106.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.107.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.107.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.107.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.108.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.108.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.108.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.109.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.109.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.109.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.11.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.11.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.11.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.110.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.110.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.110.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.111.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.111.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.111.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.112.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.112.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.112.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.113.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.113.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.113.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.114.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.114.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.114.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.115.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.115.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.115.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.116.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.116.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.116.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.117.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.117.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.117.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.118.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.118.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.118.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.119.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.119.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.119.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.12.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.12.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.12.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.120.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.120.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.120.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.121.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.121.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.121.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.122.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.122.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.122.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.123.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.123.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.123.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.124.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.124.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.124.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.125.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.125.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.125.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.126.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.126.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.126.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.127.w1.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.127.w2.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.127.w3.weight": "model-00161-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.13.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.13.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.13.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.14.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.14.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.14.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.15.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.15.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.15.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.16.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.16.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.16.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.17.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.17.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.17.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.18.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.18.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.18.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.19.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.19.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.19.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.20.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.20.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.20.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.21.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.21.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.21.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.22.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.22.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.22.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.23.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.23.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.23.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.24.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.24.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.24.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.25.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.25.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.25.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.26.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.26.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.26.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.27.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.27.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.27.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.28.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.28.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.28.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.29.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.29.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.29.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.30.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.30.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.30.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.31.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.31.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.31.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.32.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.32.w2.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.32.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.33.w1.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.33.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.33.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.34.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.34.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.34.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.35.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.35.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.35.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.36.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.36.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.36.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.37.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.37.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.37.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.38.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.38.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.38.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.39.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.39.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.39.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.40.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.40.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.40.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.41.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.41.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.41.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.42.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.42.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.42.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.43.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.43.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.43.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.44.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.44.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.44.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.45.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.45.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.45.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.46.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.46.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.46.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.47.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.47.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.47.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.48.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.48.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.48.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.49.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.49.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.49.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.50.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.50.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.50.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.51.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.51.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.51.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.52.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.52.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.52.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.53.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.53.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.53.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.54.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.54.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.54.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.55.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.55.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.55.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.56.w1.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.56.w2.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.56.w3.weight": "model-00158-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.57.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.57.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.57.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.58.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.58.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.58.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.59.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.59.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.59.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.60.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.60.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.60.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.61.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.61.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.61.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.62.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.62.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.62.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.63.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.63.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.63.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.64.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.64.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.64.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.65.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.65.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.65.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.66.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.66.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.66.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.67.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.67.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.67.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.68.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.68.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.68.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.69.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.69.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.69.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.70.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.70.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.70.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.71.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.71.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.71.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.72.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.72.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.72.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.73.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.73.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.73.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.74.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.74.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.74.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.75.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.75.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.75.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.76.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.76.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.76.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.77.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.77.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.77.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.78.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.78.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.78.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.79.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.79.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.79.w3.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.8.w1.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.8.w2.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.8.w3.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.80.w1.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.80.w2.weight": "model-00159-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.80.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.81.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.81.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.81.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.82.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.82.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.82.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.83.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.83.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.83.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.84.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.84.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.84.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.85.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.85.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.85.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.86.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.86.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.86.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.87.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.87.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.87.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.88.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.88.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.88.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.89.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.89.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.89.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.9.w1.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.9.w2.weight": "model-00156-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.9.w3.weight": "model-00157-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.90.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.90.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.90.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.91.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.91.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.91.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.92.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.92.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.92.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.93.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.93.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.93.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.94.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.94.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.94.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.95.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.95.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.95.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.96.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.96.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.96.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.97.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.97.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.97.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.98.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.98.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.98.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.99.w1.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.99.w2.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.experts.99.w3.weight": "model-00160-of-00195.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00156-of-00195.safetensors", "model.layers.28.input_layernorm.weight": "model-00161-of-00195.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00161-of-00195.safetensors", "model.layers.28.residual_layernorm.weight": "model-00161-of-00195.safetensors", "model.layers.28.residual_mlp.w1.weight": "model-00162-of-00195.safetensors", "model.layers.28.residual_mlp.w2.weight": "model-00162-of-00195.safetensors", "model.layers.28.residual_mlp.w3.weight": "model-00162-of-00195.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00156-of-00195.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00156-of-00195.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00156-of-00195.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00156-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.10.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.10.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.10.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.100.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.100.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.100.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.101.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.101.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.101.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.102.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.102.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.102.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.103.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.103.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.103.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.104.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.104.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.104.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.105.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.105.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.105.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.106.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.106.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.106.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.107.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.107.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.107.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.108.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.108.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.108.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.109.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.109.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.109.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.11.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.11.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.11.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.110.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.110.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.110.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.111.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.111.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.111.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.112.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.112.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.112.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.113.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.113.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.113.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.114.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.114.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.114.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.115.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.115.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.115.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.116.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.116.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.116.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.117.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.117.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.117.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.118.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.118.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.118.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.119.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.119.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.119.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.12.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.12.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.12.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.120.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.120.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.120.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.121.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.121.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.121.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.122.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.122.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.122.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.123.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.123.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.123.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.124.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.124.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.124.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.125.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.125.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.125.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.126.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.126.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.126.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.127.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.127.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.127.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.13.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.13.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.13.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.14.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.14.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.14.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.15.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.15.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.15.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.16.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.16.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.16.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.17.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.17.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.17.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.18.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.18.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.18.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.19.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.19.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.19.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.20.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.20.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.20.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.21.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.21.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.21.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.22.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.22.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.22.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.23.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.23.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.23.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.24.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.24.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.24.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.25.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.25.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.25.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.26.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.26.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.26.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.27.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.27.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.27.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.28.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.28.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.28.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.29.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.29.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.29.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.30.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.30.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.30.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.31.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.31.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.31.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.32.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.32.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.32.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.33.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.33.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.33.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.34.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.34.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.34.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.35.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.35.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.35.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.36.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.36.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.36.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.37.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.37.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.37.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.38.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.38.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.38.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.39.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.39.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.39.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.40.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.40.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.40.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.41.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.41.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.41.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.42.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.42.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.42.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.43.w1.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.43.w2.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.43.w3.weight": "model-00163-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.44.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.44.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.44.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.45.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.45.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.45.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.46.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.46.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.46.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.47.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.47.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.47.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.48.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.48.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.48.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.49.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.49.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.49.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.50.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.50.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.50.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.51.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.51.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.51.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.52.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.52.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.52.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.53.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.53.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.53.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.54.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.54.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.54.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.55.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.55.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.55.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.56.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.56.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.56.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.57.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.57.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.57.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.58.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.58.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.58.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.59.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.59.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.59.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.60.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.60.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.60.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.61.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.61.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.61.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.62.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.62.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.62.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.63.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.63.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.63.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.64.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.64.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.64.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.65.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.65.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.65.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.66.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.66.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.66.w3.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.67.w1.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.67.w2.weight": "model-00164-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.67.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.68.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.68.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.68.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.69.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.69.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.69.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.70.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.70.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.70.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.71.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.71.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.71.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.72.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.72.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.72.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.73.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.73.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.73.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.74.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.74.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.74.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.75.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.75.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.75.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.76.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.76.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.76.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.77.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.77.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.77.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.78.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.78.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.78.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.79.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.79.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.79.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.8.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.8.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.8.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.80.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.80.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.80.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.81.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.81.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.81.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.82.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.82.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.82.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.83.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.83.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.83.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.84.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.84.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.84.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.85.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.85.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.85.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.86.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.86.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.86.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.87.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.87.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.87.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.88.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.88.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.88.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.89.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.89.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.89.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.9.w1.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.9.w2.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.9.w3.weight": "model-00162-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.90.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.90.w2.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.90.w3.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.91.w1.weight": "model-00165-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.91.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.91.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.92.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.92.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.92.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.93.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.93.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.93.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.94.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.94.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.94.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.95.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.95.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.95.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.96.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.96.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.96.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.97.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.97.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.97.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.98.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.98.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.98.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.99.w1.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.99.w2.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.experts.99.w3.weight": "model-00166-of-00195.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00162-of-00195.safetensors", "model.layers.29.input_layernorm.weight": "model-00167-of-00195.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00167-of-00195.safetensors", "model.layers.29.residual_layernorm.weight": "model-00167-of-00195.safetensors", "model.layers.29.residual_mlp.w1.weight": "model-00167-of-00195.safetensors", "model.layers.29.residual_mlp.w2.weight": "model-00167-of-00195.safetensors", "model.layers.29.residual_mlp.w3.weight": "model-00167-of-00195.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00162-of-00195.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00162-of-00195.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00162-of-00195.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00162-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.10.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.10.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.10.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.100.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.100.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.100.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.101.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.101.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.101.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.102.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.102.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.102.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.103.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.103.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.103.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.104.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.104.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.104.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.105.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.105.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.105.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.106.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.106.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.106.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.107.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.107.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.107.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.108.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.108.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.108.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.109.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.109.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.109.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.11.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.11.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.11.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.110.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.110.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.110.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.111.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.111.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.111.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.112.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.112.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.112.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.113.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.113.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.113.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.114.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.114.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.114.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.115.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.115.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.115.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.116.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.116.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.116.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.117.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.117.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.117.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.118.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.118.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.118.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.119.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.119.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.119.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.12.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.12.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.12.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.120.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.120.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.120.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.121.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.121.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.121.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.122.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.122.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.122.w3.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.123.w1.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.123.w2.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.123.w3.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.124.w1.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.124.w2.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.124.w3.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.125.w1.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.125.w2.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.125.w3.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.126.w1.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.126.w2.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.126.w3.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.127.w1.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.127.w2.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.127.w3.weight": "model-00023-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.13.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.13.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.13.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.14.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.14.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.14.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.15.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.15.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.15.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.16.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.16.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.16.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.17.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.17.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.17.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.18.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.18.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.18.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.19.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.19.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.19.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.20.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.20.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.20.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.21.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.21.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.21.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.22.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.22.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.22.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.23.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.23.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.23.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.24.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.24.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.24.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.25.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.25.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.25.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.26.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.26.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.26.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.27.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.27.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.27.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.28.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.28.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.28.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.29.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.29.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.29.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.30.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.30.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.30.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.31.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.31.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.31.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.32.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.32.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.32.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.33.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.33.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.33.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.34.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.34.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.34.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.35.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.35.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.35.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.36.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.36.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.36.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.37.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.37.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.37.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.38.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.38.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.38.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.39.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.39.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.39.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.40.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.40.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.40.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.41.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.41.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.41.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.42.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.42.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.42.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.43.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.43.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.43.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.44.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.44.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.44.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.45.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.45.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.45.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.46.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.46.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.46.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.47.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.47.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.47.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.48.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.48.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.48.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.49.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.49.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.49.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.50.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.50.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.50.w3.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.51.w1.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.51.w2.weight": "model-00019-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.51.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.52.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.52.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.52.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.53.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.53.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.53.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.54.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.54.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.54.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.55.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.55.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.55.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.56.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.56.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.56.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.57.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.57.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.57.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.58.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.58.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.58.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.59.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.59.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.59.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.60.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.60.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.60.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.61.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.61.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.61.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.62.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.62.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.62.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.63.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.63.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.63.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.64.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.64.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.64.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.65.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.65.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.65.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.66.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.66.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.66.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.67.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.67.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.67.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.68.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.68.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.68.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.69.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.69.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.69.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.70.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.70.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.70.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.71.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.71.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.71.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.72.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.72.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.72.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.73.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.73.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.73.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.74.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.74.w2.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.74.w3.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.75.w1.weight": "model-00020-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.75.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.75.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.76.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.76.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.76.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.77.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.77.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.77.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.78.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.78.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.78.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.79.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.79.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.79.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.8.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.8.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.8.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.80.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.80.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.80.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.81.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.81.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.81.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.82.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.82.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.82.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.83.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.83.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.83.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.84.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.84.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.84.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.85.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.85.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.85.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.86.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.86.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.86.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.87.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.87.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.87.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.88.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.88.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.88.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.89.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.89.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.89.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.9.w1.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.9.w2.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.9.w3.weight": "model-00018-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.90.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.90.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.90.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.91.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.91.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.91.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.92.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.92.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.92.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.93.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.93.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.93.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.94.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.94.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.94.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.95.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.95.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.95.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.96.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.96.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.96.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.97.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.97.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.97.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.98.w1.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.98.w2.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.98.w3.weight": "model-00021-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.99.w1.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.99.w2.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.experts.99.w3.weight": "model-00022-of-00195.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00017-of-00195.safetensors", "model.layers.3.input_layernorm.weight": "model-00023-of-00195.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00023-of-00195.safetensors", "model.layers.3.residual_layernorm.weight": "model-00023-of-00195.safetensors", "model.layers.3.residual_mlp.w1.weight": "model-00023-of-00195.safetensors", "model.layers.3.residual_mlp.w2.weight": "model-00023-of-00195.safetensors", "model.layers.3.residual_mlp.w3.weight": "model-00023-of-00195.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00195.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00195.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00195.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.10.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.10.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.10.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.100.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.100.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.100.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.101.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.101.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.101.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.102.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.102.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.102.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.103.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.103.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.103.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.104.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.104.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.104.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.105.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.105.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.105.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.106.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.106.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.106.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.107.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.107.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.107.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.108.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.108.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.108.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.109.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.109.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.109.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.11.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.11.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.11.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.110.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.110.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.110.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.111.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.111.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.111.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.112.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.112.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.112.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.113.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.113.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.113.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.114.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.114.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.114.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.115.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.115.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.115.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.116.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.116.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.116.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.117.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.117.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.117.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.118.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.118.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.118.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.119.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.119.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.119.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.12.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.12.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.12.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.120.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.120.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.120.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.121.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.121.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.121.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.122.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.122.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.122.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.123.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.123.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.123.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.124.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.124.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.124.w3.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.125.w1.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.125.w2.weight": "model-00172-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.125.w3.weight": "model-00173-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.126.w1.weight": "model-00173-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.126.w2.weight": "model-00173-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.126.w3.weight": "model-00173-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.127.w1.weight": "model-00173-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.127.w2.weight": "model-00173-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.127.w3.weight": "model-00173-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.13.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.13.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.13.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.14.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.14.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.14.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.15.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.15.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.15.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.16.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.16.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.16.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.17.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.17.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.17.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.18.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.18.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.18.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.19.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.19.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.19.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.20.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.20.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.20.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.21.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.21.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.21.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.22.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.22.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.22.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.23.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.23.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.23.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.24.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.24.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.24.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.25.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.25.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.25.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.26.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.26.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.26.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.27.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.27.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.27.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.28.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.28.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.28.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.29.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.29.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.29.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.30.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.30.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.30.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.31.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.31.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.31.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.32.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.32.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.32.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.33.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.33.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.33.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.34.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.34.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.34.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.35.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.35.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.35.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.36.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.36.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.36.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.37.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.37.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.37.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.38.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.38.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.38.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.39.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.39.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.39.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.40.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.40.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.40.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.41.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.41.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.41.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.42.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.42.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.42.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.43.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.43.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.43.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.44.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.44.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.44.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.45.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.45.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.45.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.46.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.46.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.46.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.47.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.47.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.47.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.48.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.48.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.48.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.49.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.49.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.49.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.50.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.50.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.50.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.51.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.51.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.51.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.52.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.52.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.52.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.53.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.53.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.53.w3.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.54.w1.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.54.w2.weight": "model-00169-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.54.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.55.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.55.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.55.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.56.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.56.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.56.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.57.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.57.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.57.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.58.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.58.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.58.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.59.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.59.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.59.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.60.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.60.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.60.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.61.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.61.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.61.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.62.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.62.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.62.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.63.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.63.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.63.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.64.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.64.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.64.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.65.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.65.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.65.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.66.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.66.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.66.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.67.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.67.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.67.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.68.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.68.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.68.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.69.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.69.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.69.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00167-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.70.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.70.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.70.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.71.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.71.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.71.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.72.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.72.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.72.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.73.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.73.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.73.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.74.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.74.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.74.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.75.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.75.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.75.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.76.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.76.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.76.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.77.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.77.w2.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.77.w3.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.78.w1.weight": "model-00170-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.78.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.78.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.79.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.79.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.79.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.8.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.8.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.8.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.80.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.80.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.80.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.81.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.81.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.81.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.82.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.82.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.82.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.83.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.83.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.83.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.84.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.84.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.84.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.85.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.85.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.85.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.86.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.86.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.86.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.87.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.87.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.87.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.88.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.88.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.88.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.89.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.89.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.89.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.9.w1.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.9.w2.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.9.w3.weight": "model-00168-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.90.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.90.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.90.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.91.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.91.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.91.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.92.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.92.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.92.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.93.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.93.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.93.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.94.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.94.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.94.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.95.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.95.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.95.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.96.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.96.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.96.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.97.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.97.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.97.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.98.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.98.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.98.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.99.w1.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.99.w2.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.experts.99.w3.weight": "model-00171-of-00195.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00167-of-00195.safetensors", "model.layers.30.input_layernorm.weight": "model-00173-of-00195.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00173-of-00195.safetensors", "model.layers.30.residual_layernorm.weight": "model-00173-of-00195.safetensors", "model.layers.30.residual_mlp.w1.weight": "model-00173-of-00195.safetensors", "model.layers.30.residual_mlp.w2.weight": "model-00173-of-00195.safetensors", "model.layers.30.residual_mlp.w3.weight": "model-00173-of-00195.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00167-of-00195.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00167-of-00195.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00167-of-00195.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00167-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.10.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.10.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.10.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.100.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.100.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.100.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.101.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.101.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.101.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.102.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.102.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.102.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.103.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.103.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.103.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.104.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.104.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.104.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.105.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.105.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.105.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.106.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.106.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.106.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.107.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.107.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.107.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.108.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.108.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.108.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.109.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.109.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.109.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.11.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.11.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.11.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.110.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.110.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.110.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.111.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.111.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.111.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.112.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.112.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.112.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.113.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.113.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.113.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.114.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.114.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.114.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.115.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.115.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.115.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.116.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.116.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.116.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.117.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.117.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.117.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.118.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.118.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.118.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.119.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.119.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.119.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.12.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.12.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.12.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.120.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.120.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.120.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.121.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.121.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.121.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.122.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.122.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.122.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.123.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.123.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.123.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.124.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.124.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.124.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.125.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.125.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.125.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.126.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.126.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.126.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.127.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.127.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.127.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.13.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.13.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.13.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.14.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.14.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.14.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.15.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.15.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.15.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.16.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.16.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.16.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.17.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.17.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.17.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.18.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.18.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.18.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.19.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.19.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.19.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.20.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.20.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.20.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.21.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.21.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.21.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.22.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.22.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.22.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.23.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.23.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.23.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.24.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.24.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.24.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.25.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.25.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.25.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.26.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.26.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.26.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.27.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.27.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.27.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.28.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.28.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.28.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.29.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.29.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.29.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.30.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.30.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.30.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.31.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.31.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.31.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.32.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.32.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.32.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.33.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.33.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.33.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.34.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.34.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.34.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.35.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.35.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.35.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.36.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.36.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.36.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.37.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.37.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.37.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.38.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.38.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.38.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.39.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.39.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.39.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.40.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.40.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.40.w3.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.41.w1.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.41.w2.weight": "model-00174-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.41.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.42.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.42.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.42.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.43.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.43.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.43.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.44.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.44.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.44.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.45.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.45.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.45.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.46.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.46.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.46.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.47.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.47.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.47.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.48.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.48.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.48.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.49.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.49.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.49.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.50.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.50.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.50.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.51.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.51.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.51.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.52.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.52.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.52.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.53.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.53.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.53.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.54.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.54.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.54.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.55.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.55.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.55.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.56.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.56.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.56.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.57.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.57.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.57.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.58.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.58.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.58.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.59.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.59.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.59.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.60.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.60.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.60.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.61.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.61.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.61.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.62.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.62.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.62.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.63.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.63.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.63.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.64.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.64.w2.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.64.w3.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.65.w1.weight": "model-00175-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.65.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.65.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.66.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.66.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.66.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.67.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.67.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.67.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.68.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.68.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.68.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.69.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.69.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.69.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.70.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.70.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.70.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.71.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.71.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.71.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.72.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.72.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.72.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.73.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.73.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.73.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.74.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.74.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.74.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.75.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.75.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.75.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.76.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.76.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.76.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.77.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.77.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.77.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.78.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.78.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.78.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.79.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.79.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.79.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.8.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.8.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.8.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.80.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.80.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.80.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.81.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.81.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.81.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.82.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.82.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.82.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.83.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.83.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.83.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.84.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.84.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.84.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.85.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.85.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.85.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.86.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.86.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.86.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.87.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.87.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.87.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.88.w1.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.88.w2.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.88.w3.weight": "model-00176-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.89.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.89.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.89.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.9.w1.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.9.w2.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.9.w3.weight": "model-00173-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.90.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.90.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.90.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.91.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.91.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.91.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.92.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.92.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.92.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.93.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.93.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.93.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.94.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.94.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.94.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.95.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.95.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.95.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.96.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.96.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.96.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.97.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.97.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.97.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.98.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.98.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.98.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.99.w1.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.99.w2.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.experts.99.w3.weight": "model-00177-of-00195.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00173-of-00195.safetensors", "model.layers.31.input_layernorm.weight": "model-00178-of-00195.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00178-of-00195.safetensors", "model.layers.31.residual_layernorm.weight": "model-00178-of-00195.safetensors", "model.layers.31.residual_mlp.w1.weight": "model-00178-of-00195.safetensors", "model.layers.31.residual_mlp.w2.weight": "model-00178-of-00195.safetensors", "model.layers.31.residual_mlp.w3.weight": "model-00178-of-00195.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00173-of-00195.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00173-of-00195.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00173-of-00195.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00173-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.10.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.10.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.10.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.100.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.100.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.100.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.101.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.101.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.101.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.102.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.102.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.102.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.103.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.103.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.103.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.104.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.104.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.104.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.105.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.105.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.105.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.106.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.106.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.106.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.107.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.107.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.107.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.108.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.108.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.108.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.109.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.109.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.109.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.11.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.11.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.11.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.110.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.110.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.110.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.111.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.111.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.111.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.112.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.112.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.112.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.113.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.113.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.113.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.114.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.114.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.114.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.115.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.115.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.115.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.116.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.116.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.116.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.117.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.117.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.117.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.118.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.118.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.118.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.119.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.119.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.119.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.12.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.12.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.12.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.120.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.120.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.120.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.121.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.121.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.121.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.122.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.122.w2.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.122.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.123.w1.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.123.w2.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.123.w3.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.124.w1.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.124.w2.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.124.w3.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.125.w1.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.125.w2.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.125.w3.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.126.w1.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.126.w2.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.126.w3.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.127.w1.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.127.w2.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.127.w3.weight": "model-00184-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.13.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.13.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.13.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.14.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.14.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.14.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.15.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.15.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.15.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.16.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.16.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.16.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.17.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.17.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.17.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.18.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.18.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.18.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.19.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.19.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.19.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.20.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.20.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.20.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.21.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.21.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.21.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.22.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.22.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.22.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.23.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.23.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.23.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.24.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.24.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.24.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.25.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.25.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.25.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.26.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.26.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.26.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.27.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.27.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.27.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.28.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.28.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.28.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.29.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.29.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.29.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.30.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.30.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.30.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.31.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.31.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.31.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.32.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.32.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.32.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.33.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.33.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.33.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.34.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.34.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.34.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.35.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.35.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.35.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.36.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.36.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.36.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.37.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.37.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.37.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.38.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.38.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.38.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.39.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.39.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.39.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.4.w1.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.4.w2.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.4.w3.weight": "model-00178-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.40.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.40.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.40.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.41.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.41.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.41.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.42.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.42.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.42.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.43.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.43.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.43.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.44.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.44.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.44.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.45.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.45.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.45.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.46.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.46.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.46.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.47.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.47.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.47.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.48.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.48.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.48.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.49.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.49.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.49.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.5.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.5.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.5.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.50.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.50.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.50.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.51.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.51.w2.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.51.w3.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.52.w1.weight": "model-00180-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.52.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.52.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.53.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.53.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.53.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.54.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.54.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.54.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.55.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.55.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.55.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.56.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.56.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.56.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.57.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.57.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.57.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.58.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.58.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.58.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.59.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.59.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.59.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.6.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.6.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.6.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.60.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.60.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.60.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.61.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.61.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.61.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.62.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.62.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.62.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.63.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.63.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.63.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.64.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.64.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.64.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.65.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.65.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.65.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.66.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.66.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.66.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.67.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.67.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.67.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.68.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.68.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.68.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.69.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.69.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.69.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.7.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.7.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.7.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.70.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.70.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.70.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.71.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.71.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.71.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.72.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.72.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.72.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.73.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.73.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.73.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.74.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.74.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.74.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.75.w1.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.75.w2.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.75.w3.weight": "model-00181-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.76.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.76.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.76.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.77.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.77.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.77.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.78.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.78.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.78.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.79.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.79.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.79.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.8.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.8.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.8.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.80.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.80.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.80.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.81.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.81.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.81.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.82.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.82.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.82.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.83.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.83.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.83.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.84.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.84.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.84.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.85.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.85.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.85.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.86.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.86.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.86.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.87.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.87.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.87.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.88.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.88.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.88.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.89.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.89.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.89.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.9.w1.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.9.w2.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.9.w3.weight": "model-00179-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.90.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.90.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.90.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.91.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.91.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.91.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.92.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.92.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.92.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.93.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.93.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.93.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.94.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.94.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.94.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.95.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.95.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.95.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.96.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.96.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.96.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.97.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.97.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.97.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.98.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.98.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.98.w3.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.99.w1.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.99.w2.weight": "model-00182-of-00195.safetensors", "model.layers.32.block_sparse_moe.experts.99.w3.weight": "model-00183-of-00195.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00178-of-00195.safetensors", "model.layers.32.input_layernorm.weight": "model-00184-of-00195.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00184-of-00195.safetensors", "model.layers.32.residual_layernorm.weight": "model-00184-of-00195.safetensors", "model.layers.32.residual_mlp.w1.weight": "model-00184-of-00195.safetensors", "model.layers.32.residual_mlp.w2.weight": "model-00184-of-00195.safetensors", "model.layers.32.residual_mlp.w3.weight": "model-00184-of-00195.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00178-of-00195.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00178-of-00195.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00178-of-00195.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00178-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.10.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.10.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.10.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.100.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.100.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.100.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.101.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.101.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.101.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.102.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.102.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.102.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.103.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.103.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.103.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.104.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.104.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.104.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.105.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.105.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.105.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.106.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.106.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.106.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.107.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.107.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.107.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.108.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.108.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.108.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.109.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.109.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.109.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.11.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.11.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.11.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.110.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.110.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.110.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.111.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.111.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.111.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.112.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.112.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.112.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.113.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.113.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.113.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.114.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.114.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.114.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.115.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.115.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.115.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.116.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.116.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.116.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.117.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.117.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.117.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.118.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.118.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.118.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.119.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.119.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.119.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.12.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.12.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.12.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.120.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.120.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.120.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.121.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.121.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.121.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.122.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.122.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.122.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.123.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.123.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.123.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.124.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.124.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.124.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.125.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.125.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.125.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.126.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.126.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.126.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.127.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.127.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.127.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.13.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.13.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.13.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.14.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.14.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.14.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.15.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.15.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.15.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.16.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.16.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.16.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.17.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.17.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.17.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.18.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.18.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.18.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.19.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.19.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.19.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.20.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.20.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.20.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.21.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.21.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.21.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.22.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.22.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.22.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.23.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.23.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.23.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.24.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.24.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.24.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.25.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.25.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.25.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.26.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.26.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.26.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.27.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.27.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.27.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.28.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.28.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.28.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.29.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.29.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.29.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.30.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.30.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.30.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.31.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.31.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.31.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.32.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.32.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.32.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.33.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.33.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.33.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.34.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.34.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.34.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.35.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.35.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.35.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.36.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.36.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.36.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.37.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.37.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.37.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.38.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.38.w2.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.38.w3.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.39.w1.weight": "model-00185-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.39.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.39.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.4.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.4.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.4.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.40.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.40.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.40.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.41.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.41.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.41.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.42.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.42.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.42.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.43.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.43.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.43.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.44.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.44.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.44.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.45.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.45.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.45.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.46.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.46.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.46.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.47.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.47.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.47.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.48.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.48.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.48.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.49.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.49.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.49.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.5.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.5.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.5.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.50.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.50.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.50.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.51.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.51.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.51.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.52.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.52.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.52.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.53.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.53.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.53.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.54.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.54.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.54.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.55.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.55.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.55.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.56.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.56.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.56.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.57.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.57.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.57.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.58.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.58.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.58.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.59.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.59.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.59.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.6.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.6.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.6.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.60.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.60.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.60.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.61.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.61.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.61.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.62.w1.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.62.w2.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.62.w3.weight": "model-00186-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.63.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.63.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.63.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.64.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.64.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.64.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.65.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.65.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.65.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.66.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.66.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.66.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.67.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.67.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.67.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.68.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.68.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.68.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.69.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.69.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.69.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.7.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.7.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.7.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.70.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.70.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.70.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.71.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.71.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.71.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.72.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.72.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.72.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.73.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.73.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.73.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.74.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.74.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.74.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.75.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.75.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.75.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.76.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.76.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.76.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.77.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.77.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.77.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.78.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.78.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.78.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.79.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.79.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.79.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.8.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.8.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.8.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.80.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.80.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.80.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.81.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.81.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.81.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.82.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.82.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.82.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.83.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.83.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.83.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.84.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.84.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.84.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.85.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.85.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.85.w3.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.86.w1.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.86.w2.weight": "model-00187-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.86.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.87.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.87.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.87.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.88.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.88.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.88.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.89.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.89.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.89.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.9.w1.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.9.w2.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.9.w3.weight": "model-00184-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.90.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.90.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.90.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.91.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.91.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.91.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.92.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.92.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.92.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.93.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.93.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.93.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.94.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.94.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.94.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.95.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.95.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.95.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.96.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.96.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.96.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.97.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.97.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.97.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.98.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.98.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.98.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.99.w1.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.99.w2.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.experts.99.w3.weight": "model-00188-of-00195.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00184-of-00195.safetensors", "model.layers.33.input_layernorm.weight": "model-00189-of-00195.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00189-of-00195.safetensors", "model.layers.33.residual_layernorm.weight": "model-00189-of-00195.safetensors", "model.layers.33.residual_mlp.w1.weight": "model-00189-of-00195.safetensors", "model.layers.33.residual_mlp.w2.weight": "model-00189-of-00195.safetensors", "model.layers.33.residual_mlp.w3.weight": "model-00189-of-00195.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00184-of-00195.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00184-of-00195.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00184-of-00195.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00184-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00189-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00189-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00189-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00189-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00189-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00189-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.10.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.10.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.10.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.100.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.100.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.100.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.101.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.101.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.101.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.102.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.102.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.102.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.103.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.103.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.103.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.104.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.104.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.104.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.105.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.105.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.105.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.106.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.106.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.106.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.107.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.107.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.107.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.108.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.108.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.108.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.109.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.109.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.109.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.11.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.11.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.11.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.110.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.110.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.110.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.111.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.111.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.111.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.112.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.112.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.112.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.113.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.113.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.113.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.114.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.114.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.114.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.115.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.115.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.115.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.116.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.116.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.116.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.117.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.117.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.117.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.118.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.118.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.118.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.119.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.119.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.119.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.12.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.12.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.12.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.120.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.120.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.120.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.121.w1.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.121.w2.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.121.w3.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.122.w1.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.122.w2.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.122.w3.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.123.w1.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.123.w2.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.123.w3.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.124.w1.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.124.w2.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.124.w3.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.125.w1.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.125.w2.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.125.w3.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.126.w1.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.126.w2.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.126.w3.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.127.w1.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.127.w2.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.127.w3.weight": "model-00195-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.13.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.13.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.13.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.14.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.14.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.14.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.15.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.15.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.15.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.16.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.16.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.16.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.17.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.17.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.17.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.18.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.18.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.18.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.19.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.19.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.19.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00189-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00189-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.20.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.20.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.20.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.21.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.21.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.21.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.22.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.22.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.22.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.23.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.23.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.23.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.24.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.24.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.24.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.25.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.25.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.25.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.26.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.26.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.26.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.27.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.27.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.27.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.28.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.28.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.28.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.29.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.29.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.29.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.30.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.30.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.30.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.31.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.31.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.31.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.32.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.32.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.32.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.33.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.33.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.33.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.34.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.34.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.34.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.35.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.35.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.35.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.36.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.36.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.36.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.37.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.37.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.37.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.38.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.38.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.38.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.39.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.39.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.39.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.4.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.4.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.4.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.40.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.40.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.40.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.41.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.41.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.41.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.42.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.42.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.42.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.43.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.43.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.43.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.44.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.44.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.44.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.45.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.45.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.45.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.46.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.46.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.46.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.47.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.47.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.47.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.48.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.48.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.48.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.49.w1.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.49.w2.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.49.w3.weight": "model-00191-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.5.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.5.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.5.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.50.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.50.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.50.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.51.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.51.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.51.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.52.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.52.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.52.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.53.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.53.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.53.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.54.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.54.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.54.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.55.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.55.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.55.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.56.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.56.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.56.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.57.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.57.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.57.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.58.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.58.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.58.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.59.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.59.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.59.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.6.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.6.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.6.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.60.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.60.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.60.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.61.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.61.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.61.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.62.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.62.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.62.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.63.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.63.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.63.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.64.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.64.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.64.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.65.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.65.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.65.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.66.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.66.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.66.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.67.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.67.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.67.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.68.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.68.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.68.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.69.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.69.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.69.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.7.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.7.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.7.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.70.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.70.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.70.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.71.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.71.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.71.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.72.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.72.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.72.w3.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.73.w1.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.73.w2.weight": "model-00192-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.73.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.74.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.74.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.74.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.75.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.75.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.75.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.76.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.76.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.76.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.77.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.77.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.77.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.78.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.78.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.78.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.79.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.79.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.79.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.8.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.8.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.8.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.80.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.80.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.80.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.81.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.81.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.81.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.82.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.82.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.82.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.83.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.83.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.83.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.84.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.84.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.84.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.85.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.85.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.85.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.86.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.86.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.86.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.87.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.87.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.87.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.88.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.88.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.88.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.89.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.89.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.89.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.9.w1.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.9.w2.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.9.w3.weight": "model-00190-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.90.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.90.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.90.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.91.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.91.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.91.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.92.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.92.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.92.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.93.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.93.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.93.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.94.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.94.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.94.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.95.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.95.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.95.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.96.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.96.w2.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.96.w3.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.97.w1.weight": "model-00193-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.97.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.97.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.98.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.98.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.98.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.99.w1.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.99.w2.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.experts.99.w3.weight": "model-00194-of-00195.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00189-of-00195.safetensors", "model.layers.34.input_layernorm.weight": "model-00195-of-00195.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00195-of-00195.safetensors", "model.layers.34.residual_layernorm.weight": "model-00195-of-00195.safetensors", "model.layers.34.residual_mlp.w1.weight": "model-00195-of-00195.safetensors", "model.layers.34.residual_mlp.w2.weight": "model-00195-of-00195.safetensors", "model.layers.34.residual_mlp.w3.weight": "model-00195-of-00195.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00189-of-00195.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00189-of-00195.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00189-of-00195.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00189-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.10.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.10.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.10.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.100.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.100.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.100.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.101.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.101.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.101.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.102.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.102.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.102.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.103.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.103.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.103.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.104.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.104.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.104.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.105.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.105.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.105.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.106.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.106.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.106.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.107.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.107.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.107.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.108.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.108.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.108.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.109.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.109.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.109.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.11.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.11.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.11.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.110.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.110.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.110.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.111.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.111.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.111.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.112.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.112.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.112.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.113.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.113.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.113.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.114.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.114.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.114.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.115.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.115.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.115.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.116.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.116.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.116.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.117.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.117.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.117.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.118.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.118.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.118.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.119.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.119.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.119.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.12.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.12.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.12.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.120.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.120.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.120.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.121.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.121.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.121.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.122.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.122.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.122.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.123.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.123.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.123.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.124.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.124.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.124.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.125.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.125.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.125.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.126.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.126.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.126.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.127.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.127.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.127.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.13.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.13.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.13.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.14.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.14.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.14.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.15.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.15.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.15.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.16.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.16.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.16.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.17.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.17.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.17.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.18.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.18.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.18.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.19.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.19.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.19.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.20.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.20.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.20.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.21.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.21.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.21.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.22.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.22.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.22.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.23.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.23.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.23.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.24.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.24.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.24.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.25.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.25.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.25.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.26.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.26.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.26.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.27.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.27.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.27.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.28.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.28.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.28.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.29.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.29.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.29.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.30.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.30.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.30.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.31.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.31.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.31.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.32.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.32.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.32.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.33.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.33.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.33.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.34.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.34.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.34.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.35.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.35.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.35.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.36.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.36.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.36.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.37.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.37.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.37.w3.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.38.w1.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.38.w2.weight": "model-00024-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.38.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.39.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.39.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.39.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.40.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.40.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.40.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.41.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.41.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.41.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.42.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.42.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.42.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.43.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.43.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.43.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.44.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.44.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.44.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.45.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.45.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.45.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.46.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.46.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.46.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.47.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.47.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.47.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.48.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.48.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.48.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.49.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.49.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.49.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.50.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.50.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.50.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.51.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.51.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.51.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.52.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.52.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.52.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.53.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.53.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.53.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.54.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.54.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.54.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.55.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.55.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.55.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.56.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.56.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.56.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.57.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.57.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.57.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.58.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.58.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.58.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.59.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.59.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.59.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.60.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.60.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.60.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.61.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.61.w2.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.61.w3.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.62.w1.weight": "model-00025-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.62.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.62.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.63.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.63.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.63.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.64.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.64.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.64.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.65.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.65.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.65.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.66.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.66.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.66.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.67.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.67.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.67.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.68.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.68.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.68.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.69.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.69.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.69.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.70.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.70.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.70.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.71.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.71.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.71.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.72.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.72.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.72.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.73.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.73.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.73.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.74.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.74.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.74.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.75.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.75.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.75.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.76.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.76.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.76.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.77.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.77.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.77.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.78.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.78.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.78.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.79.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.79.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.79.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.8.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.8.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.8.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.80.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.80.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.80.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.81.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.81.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.81.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.82.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.82.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.82.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.83.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.83.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.83.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.84.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.84.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.84.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.85.w1.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.85.w2.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.85.w3.weight": "model-00026-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.86.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.86.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.86.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.87.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.87.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.87.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.88.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.88.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.88.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.89.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.89.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.89.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.9.w1.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.9.w2.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.9.w3.weight": "model-00023-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.90.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.90.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.90.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.91.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.91.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.91.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.92.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.92.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.92.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.93.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.93.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.93.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.94.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.94.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.94.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.95.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.95.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.95.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.96.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.96.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.96.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.97.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.97.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.97.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.98.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.98.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.98.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.99.w1.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.99.w2.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.experts.99.w3.weight": "model-00027-of-00195.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00023-of-00195.safetensors", "model.layers.4.input_layernorm.weight": "model-00028-of-00195.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00028-of-00195.safetensors", "model.layers.4.residual_layernorm.weight": "model-00028-of-00195.safetensors", "model.layers.4.residual_mlp.w1.weight": "model-00028-of-00195.safetensors", "model.layers.4.residual_mlp.w2.weight": "model-00028-of-00195.safetensors", "model.layers.4.residual_mlp.w3.weight": "model-00028-of-00195.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00023-of-00195.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00023-of-00195.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00023-of-00195.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00023-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.10.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.10.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.10.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.100.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.100.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.100.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.101.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.101.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.101.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.102.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.102.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.102.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.103.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.103.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.103.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.104.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.104.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.104.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.105.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.105.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.105.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.106.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.106.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.106.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.107.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.107.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.107.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.108.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.108.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.108.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.109.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.109.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.109.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.11.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.11.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.11.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.110.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.110.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.110.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.111.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.111.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.111.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.112.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.112.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.112.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.113.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.113.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.113.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.114.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.114.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.114.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.115.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.115.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.115.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.116.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.116.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.116.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.117.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.117.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.117.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.118.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.118.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.118.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.119.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.119.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.119.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.12.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.12.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.12.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.120.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.120.w2.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.120.w3.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.121.w1.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.121.w2.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.121.w3.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.122.w1.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.122.w2.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.122.w3.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.123.w1.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.123.w2.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.123.w3.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.124.w1.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.124.w2.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.124.w3.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.125.w1.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.125.w2.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.125.w3.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.126.w1.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.126.w2.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.126.w3.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.127.w1.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.127.w2.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.127.w3.weight": "model-00034-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.13.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.13.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.13.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.14.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.14.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.14.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.15.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.15.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.15.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.16.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.16.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.16.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.17.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.17.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.17.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.18.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.18.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.18.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.19.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.19.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.19.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.20.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.20.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.20.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.21.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.21.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.21.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.22.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.22.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.22.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.23.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.23.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.23.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.24.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.24.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.24.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.25.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.25.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.25.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.26.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.26.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.26.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.27.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.27.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.27.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.28.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.28.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.28.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.29.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.29.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.29.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.30.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.30.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.30.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.31.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.31.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.31.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.32.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.32.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.32.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.33.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.33.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.33.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.34.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.34.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.34.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.35.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.35.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.35.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.36.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.36.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.36.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.37.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.37.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.37.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.38.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.38.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.38.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.39.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.39.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.39.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.40.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.40.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.40.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.41.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.41.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.41.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.42.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.42.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.42.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.43.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.43.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.43.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.44.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.44.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.44.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.45.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.45.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.45.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.46.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.46.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.46.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.47.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.47.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.47.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.48.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.48.w2.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.48.w3.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.49.w1.weight": "model-00030-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.49.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.49.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.50.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.50.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.50.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.51.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.51.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.51.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.52.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.52.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.52.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.53.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.53.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.53.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.54.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.54.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.54.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.55.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.55.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.55.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.56.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.56.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.56.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.57.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.57.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.57.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.58.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.58.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.58.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.59.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.59.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.59.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.60.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.60.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.60.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.61.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.61.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.61.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.62.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.62.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.62.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.63.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.63.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.63.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.64.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.64.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.64.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.65.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.65.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.65.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.66.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.66.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.66.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.67.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.67.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.67.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.68.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.68.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.68.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.69.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.69.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.69.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.70.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.70.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.70.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.71.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.71.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.71.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.72.w1.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.72.w2.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.72.w3.weight": "model-00031-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.73.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.73.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.73.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.74.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.74.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.74.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.75.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.75.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.75.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.76.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.76.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.76.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.77.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.77.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.77.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.78.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.78.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.78.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.79.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.79.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.79.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.8.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.8.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.8.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.80.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.80.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.80.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.81.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.81.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.81.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.82.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.82.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.82.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.83.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.83.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.83.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.84.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.84.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.84.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.85.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.85.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.85.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.86.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.86.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.86.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.87.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.87.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.87.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.88.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.88.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.88.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.89.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.89.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.89.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.9.w1.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.9.w2.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.9.w3.weight": "model-00029-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.90.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.90.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.90.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.91.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.91.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.91.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.92.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.92.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.92.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.93.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.93.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.93.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.94.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.94.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.94.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.95.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.95.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.95.w3.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.96.w1.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.96.w2.weight": "model-00032-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.96.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.97.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.97.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.97.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.98.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.98.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.98.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.99.w1.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.99.w2.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.experts.99.w3.weight": "model-00033-of-00195.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00028-of-00195.safetensors", "model.layers.5.input_layernorm.weight": "model-00034-of-00195.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00034-of-00195.safetensors", "model.layers.5.residual_layernorm.weight": "model-00034-of-00195.safetensors", "model.layers.5.residual_mlp.w1.weight": "model-00034-of-00195.safetensors", "model.layers.5.residual_mlp.w2.weight": "model-00034-of-00195.safetensors", "model.layers.5.residual_mlp.w3.weight": "model-00034-of-00195.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00028-of-00195.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00028-of-00195.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00028-of-00195.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00028-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.10.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.10.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.10.w3.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.100.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.100.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.100.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.101.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.101.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.101.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.102.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.102.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.102.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.103.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.103.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.103.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.104.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.104.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.104.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.105.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.105.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.105.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.106.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.106.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.106.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.107.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.107.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.107.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.108.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.108.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.108.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.109.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.109.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.109.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.11.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.11.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.11.w3.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.110.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.110.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.110.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.111.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.111.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.111.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.112.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.112.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.112.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.113.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.113.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.113.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.114.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.114.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.114.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.115.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.115.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.115.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.116.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.116.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.116.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.117.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.117.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.117.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.118.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.118.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.118.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.119.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.119.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.119.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.12.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.12.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.12.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.120.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.120.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.120.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.121.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.121.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.121.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.122.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.122.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.122.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.123.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.123.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.123.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.124.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.124.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.124.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.125.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.125.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.125.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.126.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.126.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.126.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.127.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.127.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.127.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.13.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.13.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.13.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.14.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.14.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.14.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.15.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.15.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.15.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.16.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.16.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.16.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.17.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.17.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.17.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.18.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.18.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.18.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.19.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.19.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.19.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.20.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.20.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.20.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.21.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.21.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.21.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.22.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.22.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.22.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.23.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.23.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.23.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.24.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.24.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.24.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.25.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.25.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.25.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.26.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.26.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.26.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.27.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.27.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.27.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.28.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.28.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.28.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.29.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.29.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.29.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.30.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.30.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.30.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.31.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.31.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.31.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.32.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.32.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.32.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.33.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.33.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.33.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.34.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.34.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.34.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.35.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.35.w2.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.35.w3.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.36.w1.weight": "model-00035-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.36.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.36.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.37.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.37.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.37.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.38.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.38.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.38.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.39.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.39.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.39.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.40.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.40.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.40.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.41.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.41.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.41.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.42.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.42.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.42.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.43.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.43.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.43.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.44.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.44.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.44.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.45.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.45.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.45.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.46.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.46.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.46.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.47.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.47.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.47.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.48.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.48.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.48.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.49.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.49.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.49.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.50.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.50.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.50.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.51.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.51.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.51.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.52.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.52.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.52.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.53.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.53.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.53.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.54.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.54.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.54.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.55.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.55.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.55.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.56.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.56.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.56.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.57.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.57.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.57.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.58.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.58.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.58.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.59.w1.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.59.w2.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.59.w3.weight": "model-00036-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.60.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.60.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.60.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.61.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.61.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.61.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.62.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.62.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.62.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.63.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.63.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.63.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.64.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.64.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.64.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.65.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.65.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.65.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.66.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.66.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.66.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.67.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.67.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.67.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.68.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.68.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.68.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.69.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.69.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.69.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.70.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.70.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.70.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.71.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.71.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.71.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.72.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.72.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.72.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.73.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.73.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.73.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.74.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.74.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.74.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.75.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.75.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.75.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.76.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.76.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.76.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.77.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.77.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.77.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.78.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.78.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.78.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.79.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.79.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.79.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.8.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.8.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.8.w3.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.80.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.80.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.80.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.81.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.81.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.81.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.82.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.82.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.82.w3.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.83.w1.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.83.w2.weight": "model-00037-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.83.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.84.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.84.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.84.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.85.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.85.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.85.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.86.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.86.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.86.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.87.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.87.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.87.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.88.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.88.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.88.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.89.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.89.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.89.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.9.w1.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.9.w2.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.9.w3.weight": "model-00034-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.90.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.90.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.90.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.91.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.91.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.91.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.92.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.92.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.92.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.93.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.93.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.93.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.94.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.94.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.94.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.95.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.95.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.95.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.96.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.96.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.96.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.97.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.97.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.97.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.98.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.98.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.98.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.99.w1.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.99.w2.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.experts.99.w3.weight": "model-00038-of-00195.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00034-of-00195.safetensors", "model.layers.6.input_layernorm.weight": "model-00039-of-00195.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00039-of-00195.safetensors", "model.layers.6.residual_layernorm.weight": "model-00039-of-00195.safetensors", "model.layers.6.residual_mlp.w1.weight": "model-00039-of-00195.safetensors", "model.layers.6.residual_mlp.w2.weight": "model-00039-of-00195.safetensors", "model.layers.6.residual_mlp.w3.weight": "model-00039-of-00195.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00034-of-00195.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00034-of-00195.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00034-of-00195.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00034-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.10.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.10.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.10.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.100.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.100.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.100.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.101.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.101.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.101.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.102.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.102.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.102.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.103.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.103.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.103.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.104.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.104.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.104.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.105.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.105.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.105.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.106.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.106.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.106.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.107.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.107.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.107.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.108.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.108.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.108.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.109.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.109.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.109.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.11.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.11.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.11.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.110.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.110.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.110.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.111.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.111.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.111.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.112.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.112.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.112.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.113.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.113.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.113.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.114.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.114.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.114.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.115.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.115.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.115.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.116.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.116.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.116.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.117.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.117.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.117.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.118.w1.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.118.w2.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.118.w3.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.119.w1.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.119.w2.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.119.w3.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.12.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.12.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.12.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.120.w1.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.120.w2.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.120.w3.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.121.w1.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.121.w2.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.121.w3.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.122.w1.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.122.w2.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.122.w3.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.123.w1.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.123.w2.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.123.w3.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.124.w1.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.124.w2.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.124.w3.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.125.w1.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.125.w2.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.125.w3.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.126.w1.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.126.w2.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.126.w3.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.127.w1.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.127.w2.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.127.w3.weight": "model-00045-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.13.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.13.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.13.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.14.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.14.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.14.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.15.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.15.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.15.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.16.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.16.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.16.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.17.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.17.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.17.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.18.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.18.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.18.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.19.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.19.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.19.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.20.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.20.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.20.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.21.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.21.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.21.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.22.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.22.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.22.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.23.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.23.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.23.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.24.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.24.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.24.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.25.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.25.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.25.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.26.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.26.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.26.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.27.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.27.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.27.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.28.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.28.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.28.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.29.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.29.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.29.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.30.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.30.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.30.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.31.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.31.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.31.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.32.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.32.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.32.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.33.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.33.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.33.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.34.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.34.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.34.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.35.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.35.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.35.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.36.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.36.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.36.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.37.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.37.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.37.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.38.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.38.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.38.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.39.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.39.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.39.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.40.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.40.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.40.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.41.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.41.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.41.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.42.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.42.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.42.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.43.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.43.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.43.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.44.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.44.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.44.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.45.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.45.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.45.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.46.w1.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.46.w2.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.46.w3.weight": "model-00041-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.47.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.47.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.47.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.48.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.48.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.48.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.49.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.49.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.49.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.50.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.50.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.50.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.51.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.51.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.51.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.52.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.52.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.52.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.53.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.53.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.53.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.54.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.54.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.54.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.55.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.55.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.55.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.56.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.56.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.56.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.57.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.57.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.57.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.58.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.58.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.58.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.59.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.59.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.59.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.60.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.60.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.60.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.61.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.61.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.61.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.62.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.62.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.62.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.63.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.63.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.63.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.64.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.64.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.64.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.65.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.65.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.65.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.66.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.66.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.66.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.67.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.67.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.67.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.68.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.68.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.68.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.69.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.69.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.69.w3.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.70.w1.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.70.w2.weight": "model-00042-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.70.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.71.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.71.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.71.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.72.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.72.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.72.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.73.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.73.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.73.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.74.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.74.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.74.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.75.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.75.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.75.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.76.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.76.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.76.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.77.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.77.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.77.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.78.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.78.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.78.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.79.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.79.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.79.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.8.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.8.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.8.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.80.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.80.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.80.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.81.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.81.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.81.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.82.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.82.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.82.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.83.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.83.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.83.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.84.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.84.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.84.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.85.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.85.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.85.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.86.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.86.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.86.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.87.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.87.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.87.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.88.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.88.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.88.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.89.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.89.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.89.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.9.w1.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.9.w2.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.9.w3.weight": "model-00040-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.90.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.90.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.90.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.91.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.91.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.91.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.92.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.92.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.92.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.93.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.93.w2.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.93.w3.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.94.w1.weight": "model-00043-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.94.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.94.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.95.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.95.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.95.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.96.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.96.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.96.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.97.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.97.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.97.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.98.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.98.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.98.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.99.w1.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.99.w2.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.experts.99.w3.weight": "model-00044-of-00195.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00040-of-00195.safetensors", "model.layers.7.input_layernorm.weight": "model-00045-of-00195.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00045-of-00195.safetensors", "model.layers.7.residual_layernorm.weight": "model-00045-of-00195.safetensors", "model.layers.7.residual_mlp.w1.weight": "model-00045-of-00195.safetensors", "model.layers.7.residual_mlp.w2.weight": "model-00045-of-00195.safetensors", "model.layers.7.residual_mlp.w3.weight": "model-00045-of-00195.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00039-of-00195.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00040-of-00195.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00039-of-00195.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00039-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.10.w1.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.10.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.10.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.100.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.100.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.100.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.101.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.101.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.101.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.102.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.102.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.102.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.103.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.103.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.103.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.104.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.104.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.104.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.105.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.105.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.105.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.106.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.106.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.106.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.107.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.107.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.107.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.108.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.108.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.108.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.109.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.109.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.109.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.11.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.11.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.11.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.110.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.110.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.110.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.111.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.111.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.111.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.112.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.112.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.112.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.113.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.113.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.113.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.114.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.114.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.114.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.115.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.115.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.115.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.116.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.116.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.116.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.117.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.117.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.117.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.118.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.118.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.118.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.119.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.119.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.119.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.12.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.12.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.12.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.120.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.120.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.120.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.121.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.121.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.121.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.122.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.122.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.122.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.123.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.123.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.123.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.124.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.124.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.124.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.125.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.125.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.125.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.126.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.126.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.126.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.127.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.127.w2.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.127.w3.weight": "model-00050-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.13.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.13.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.13.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.14.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.14.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.14.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.15.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.15.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.15.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.16.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.16.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.16.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.17.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.17.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.17.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.18.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.18.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.18.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.19.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.19.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.19.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.20.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.20.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.20.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.21.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.21.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.21.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.22.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.22.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.22.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.23.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.23.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.23.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.24.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.24.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.24.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.25.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.25.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.25.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.26.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.26.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.26.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.27.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.27.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.27.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.28.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.28.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.28.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.29.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.29.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.29.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.30.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.30.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.30.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.31.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.31.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.31.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.32.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.32.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.32.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.33.w1.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.33.w2.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.33.w3.weight": "model-00046-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.34.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.34.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.34.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.35.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.35.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.35.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.36.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.36.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.36.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.37.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.37.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.37.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.38.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.38.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.38.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.39.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.39.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.39.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.40.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.40.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.40.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.41.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.41.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.41.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.42.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.42.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.42.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.43.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.43.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.43.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.44.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.44.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.44.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.45.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.45.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.45.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.46.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.46.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.46.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.47.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.47.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.47.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.48.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.48.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.48.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.49.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.49.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.49.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.50.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.50.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.50.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.51.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.51.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.51.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.52.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.52.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.52.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.53.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.53.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.53.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.54.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.54.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.54.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.55.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.55.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.55.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.56.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.56.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.56.w3.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.57.w1.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.57.w2.weight": "model-00047-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.57.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.58.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.58.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.58.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.59.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.59.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.59.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.60.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.60.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.60.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.61.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.61.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.61.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.62.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.62.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.62.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.63.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.63.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.63.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.64.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.64.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.64.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.65.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.65.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.65.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.66.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.66.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.66.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.67.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.67.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.67.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.68.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.68.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.68.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.69.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.69.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.69.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.70.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.70.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.70.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.71.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.71.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.71.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.72.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.72.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.72.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.73.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.73.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.73.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.74.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.74.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.74.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.75.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.75.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.75.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.76.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.76.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.76.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.77.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.77.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.77.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.78.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.78.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.78.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.79.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.79.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.79.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.8.w1.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.8.w2.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.8.w3.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.80.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.80.w2.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.80.w3.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.81.w1.weight": "model-00048-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.81.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.81.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.82.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.82.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.82.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.83.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.83.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.83.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.84.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.84.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.84.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.85.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.85.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.85.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.86.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.86.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.86.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.87.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.87.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.87.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.88.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.88.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.88.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.89.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.89.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.89.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.9.w1.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.9.w2.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.9.w3.weight": "model-00045-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.90.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.90.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.90.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.91.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.91.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.91.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.92.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.92.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.92.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.93.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.93.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.93.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.94.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.94.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.94.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.95.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.95.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.95.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.96.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.96.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.96.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.97.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.97.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.97.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.98.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.98.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.98.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.99.w1.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.99.w2.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.experts.99.w3.weight": "model-00049-of-00195.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00045-of-00195.safetensors", "model.layers.8.input_layernorm.weight": "model-00050-of-00195.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00050-of-00195.safetensors", "model.layers.8.residual_layernorm.weight": "model-00050-of-00195.safetensors", "model.layers.8.residual_mlp.w1.weight": "model-00050-of-00195.safetensors", "model.layers.8.residual_mlp.w2.weight": "model-00051-of-00195.safetensors", "model.layers.8.residual_mlp.w3.weight": "model-00051-of-00195.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00045-of-00195.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00045-of-00195.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00045-of-00195.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00045-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.10.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.10.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.10.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.100.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.100.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.100.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.101.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.101.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.101.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.102.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.102.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.102.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.103.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.103.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.103.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.104.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.104.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.104.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.105.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.105.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.105.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.106.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.106.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.106.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.107.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.107.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.107.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.108.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.108.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.108.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.109.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.109.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.109.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.11.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.11.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.11.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.110.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.110.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.110.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.111.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.111.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.111.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.112.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.112.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.112.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.113.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.113.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.113.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.114.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.114.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.114.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.115.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.115.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.115.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.116.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.116.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.116.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.117.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.117.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.117.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.118.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.118.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.118.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.119.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.119.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.119.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.12.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.12.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.12.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.120.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.120.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.120.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.121.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.121.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.121.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.122.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.122.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.122.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.123.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.123.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.123.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.124.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.124.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.124.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.125.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.125.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.125.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.126.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.126.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.126.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.127.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.127.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.127.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.13.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.13.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.13.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.14.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.14.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.14.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.15.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.15.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.15.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.16.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.16.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.16.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.17.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.17.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.17.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.18.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.18.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.18.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.19.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.19.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.19.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.20.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.20.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.20.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.21.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.21.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.21.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.22.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.22.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.22.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.23.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.23.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.23.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.24.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.24.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.24.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.25.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.25.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.25.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.26.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.26.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.26.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.27.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.27.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.27.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.28.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.28.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.28.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.29.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.29.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.29.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.30.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.30.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.30.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.31.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.31.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.31.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.32.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.32.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.32.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.33.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.33.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.33.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.34.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.34.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.34.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.35.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.35.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.35.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.36.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.36.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.36.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.37.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.37.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.37.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.38.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.38.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.38.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.39.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.39.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.39.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.40.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.40.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.40.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.41.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.41.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.41.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.42.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.42.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.42.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.43.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.43.w2.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.43.w3.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.44.w1.weight": "model-00052-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.44.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.44.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.45.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.45.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.45.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.46.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.46.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.46.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.47.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.47.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.47.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.48.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.48.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.48.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.49.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.49.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.49.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.50.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.50.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.50.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.51.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.51.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.51.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.52.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.52.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.52.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.53.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.53.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.53.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.54.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.54.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.54.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.55.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.55.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.55.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.56.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.56.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.56.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.57.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.57.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.57.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.58.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.58.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.58.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.59.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.59.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.59.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.60.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.60.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.60.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.61.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.61.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.61.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.62.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.62.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.62.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.63.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.63.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.63.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.64.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.64.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.64.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.65.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.65.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.65.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.66.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.66.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.66.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.67.w1.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.67.w2.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.67.w3.weight": "model-00053-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.68.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.68.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.68.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.69.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.69.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.69.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.70.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.70.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.70.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.71.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.71.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.71.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.72.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.72.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.72.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.73.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.73.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.73.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.74.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.74.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.74.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.75.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.75.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.75.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.76.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.76.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.76.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.77.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.77.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.77.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.78.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.78.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.78.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.79.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.79.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.79.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.8.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.8.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.8.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.80.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.80.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.80.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.81.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.81.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.81.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.82.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.82.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.82.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.83.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.83.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.83.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.84.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.84.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.84.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.85.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.85.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.85.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.86.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.86.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.86.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.87.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.87.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.87.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.88.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.88.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.88.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.89.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.89.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.89.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.9.w1.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.9.w2.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.9.w3.weight": "model-00051-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.90.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.90.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.90.w3.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.91.w1.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.91.w2.weight": "model-00054-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.91.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.92.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.92.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.92.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.93.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.93.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.93.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.94.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.94.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.94.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.95.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.95.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.95.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.96.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.96.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.96.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.97.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.97.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.97.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.98.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.98.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.98.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.99.w1.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.99.w2.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.experts.99.w3.weight": "model-00055-of-00195.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00051-of-00195.safetensors", "model.layers.9.input_layernorm.weight": "model-00056-of-00195.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00056-of-00195.safetensors", "model.layers.9.residual_layernorm.weight": "model-00056-of-00195.safetensors", "model.layers.9.residual_mlp.w1.weight": "model-00056-of-00195.safetensors", "model.layers.9.residual_mlp.w2.weight": "model-00056-of-00195.safetensors", "model.layers.9.residual_mlp.w3.weight": "model-00056-of-00195.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00051-of-00195.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00051-of-00195.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00051-of-00195.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00051-of-00195.safetensors", "model.norm.weight": "model-00195-of-00195.safetensors" } }