phixtral-2x2_8 / model.safetensors.index.json
mlabonne's picture
Upload folder using huggingface_hub
857806b
raw history blame
No virus
40.2 kB
{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"transformer.embd.wte.weight": "model-00001-of-00001.safetensors", "lm_head.linear.bias": "model-00001-of-00001.safetensors", "lm_head.linear.weight": "model-00001-of-00001.safetensors", "lm_head.ln.bias": "model-00001-of-00001.safetensors", "lm_head.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.0.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.1.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.2.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.3.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.4.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.5.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.6.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.7.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.8.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.9.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.10.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.11.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.12.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.13.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.14.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.15.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.16.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.17.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.18.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.19.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.20.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.21.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.22.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.23.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.24.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.25.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.26.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.27.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.28.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.29.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.30.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.31.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.0.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.1.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.2.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.3.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.4.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.5.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.6.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.7.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.8.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.9.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.10.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.11.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.12.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.13.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.14.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.15.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.16.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.17.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.18.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.19.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.20.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.21.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.22.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.23.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.24.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.25.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.26.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.27.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.28.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.29.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.30.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.31.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.12.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.13.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.14.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.15.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.16.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.17.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.18.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.19.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.20.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.21.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.22.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.23.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.24.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.25.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.26.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.27.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.28.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.29.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.30.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.31.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.12.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.13.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.14.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.15.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.16.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.17.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.18.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.19.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.20.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.21.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.22.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.23.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.24.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.25.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.26.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.27.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.28.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.29.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.30.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.31.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.20.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.21.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.22.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.23.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.24.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.25.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.26.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.27.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.28.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.29.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.30.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.31.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.19.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.20.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.21.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.22.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.23.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.24.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.25.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.26.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.27.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.28.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.29.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.30.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.31.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors"}}