{ "metadata": { "audio_proj_in.bias": "{\"_type\": \"Tensor\"}", "audio_proj_in.weight": "{\"_type\": \"Tensor\"}", "audio_proj_out.bias": "{\"_type\": \"Tensor\"}", "audio_proj_out.weight": "{\"_type\": \"Tensor\"}", "context_embedder.bias": "{\"_type\": \"Tensor\"}", "context_embedder.weight": "{\"_type\": \"Tensor\"}", "norm_out.linear.bias": "{\"_type\": \"Tensor\"}", "norm_out.linear.weight": "{\"_type\": \"Tensor\"}", "norm_out.norm.weight": "{\"_type\": \"Tensor\"}", "proj_in.bias": "{\"_type\": \"Tensor\"}", "proj_in.weight": "{\"_type\": \"Tensor\"}", "proj_out.bias": "{\"_type\": \"Tensor\"}", "proj_out.weight": "{\"_type\": \"Tensor\"}", "tensor_names": "[\"proj_in.weight\", \"proj_in.bias\", \"audio_proj_in.weight\", \"audio_proj_in.bias\", \"context_embedder.weight\", \"context_embedder.bias\", \"time_embedder.linear_1.weight\", \"time_embedder.linear_1.bias\", \"time_embedder.linear_2.weight\", \"time_embedder.linear_2.bias\", \"token_refiner.refiner_blocks.0.norm1.weight\", \"token_refiner.refiner_blocks.0.attn.to_q.weight\", \"token_refiner.refiner_blocks.0.attn.to_k.weight\", \"token_refiner.refiner_blocks.0.attn.to_v.weight\", \"token_refiner.refiner_blocks.0.attn.norm_q.weight\", \"token_refiner.refiner_blocks.0.attn.norm_k.weight\", \"token_refiner.refiner_blocks.0.attn.to_out.0.weight\", \"token_refiner.refiner_blocks.0.norm2.weight\", \"token_refiner.refiner_blocks.0.ff.net.0.proj.weight\", \"token_refiner.refiner_blocks.0.ff.net.2.weight\", \"token_refiner.refiner_blocks.1.norm1.weight\", \"token_refiner.refiner_blocks.1.attn.to_q.weight\", \"token_refiner.refiner_blocks.1.attn.to_k.weight\", \"token_refiner.refiner_blocks.1.attn.to_v.weight\", \"token_refiner.refiner_blocks.1.attn.norm_q.weight\", \"token_refiner.refiner_blocks.1.attn.norm_k.weight\", \"token_refiner.refiner_blocks.1.attn.to_out.0.weight\", \"token_refiner.refiner_blocks.1.norm2.weight\", \"token_refiner.refiner_blocks.1.ff.net.0.proj.weight\", \"token_refiner.refiner_blocks.1.ff.net.2.weight\", \"token_refiner.final_norm.weight\", \"transformer_blocks.0.norm1.weight\", \"transformer_blocks.0.attn.to_q.weight\", \"transformer_blocks.0.attn.to_k.weight\", \"transformer_blocks.0.attn.to_v.weight\", \"transformer_blocks.0.attn.norm_q.weight\", \"transformer_blocks.0.attn.norm_k.weight\", \"transformer_blocks.0.attn.to_out.0.weight\", \"transformer_blocks.0.norm2.weight\", \"transformer_blocks.0.ff.net.0.proj.weight\", \"transformer_blocks.0.ff.net.2.weight\", \"transformer_blocks.0.adaln_proj.linear.weight\", \"transformer_blocks.0.adaln_proj.linear.bias\", \"transformer_blocks.1.norm1.weight\", \"transformer_blocks.1.attn.to_q.weight\", \"transformer_blocks.1.attn.to_k.weight\", \"transformer_blocks.1.attn.to_v.weight\", \"transformer_blocks.1.attn.norm_q.weight\", \"transformer_blocks.1.attn.norm_k.weight\", \"transformer_blocks.1.attn.to_out.0.weight\", \"transformer_blocks.1.norm2.weight\", \"transformer_blocks.1.ff.net.0.proj.weight\", \"transformer_blocks.1.ff.net.2.weight\", \"transformer_blocks.1.adaln_proj.linear.weight\", \"transformer_blocks.1.adaln_proj.linear.bias\", \"transformer_blocks.2.norm1.weight\", \"transformer_blocks.2.attn.to_q.weight\", \"transformer_blocks.2.attn.to_k.weight\", \"transformer_blocks.2.attn.to_v.weight\", \"transformer_blocks.2.attn.norm_q.weight\", \"transformer_blocks.2.attn.norm_k.weight\", \"transformer_blocks.2.attn.to_out.0.weight\", \"transformer_blocks.2.norm2.weight\", \"transformer_blocks.2.ff.net.0.proj.weight\", \"transformer_blocks.2.ff.net.2.weight\", \"transformer_blocks.2.adaln_proj.linear.weight\", \"transformer_blocks.2.adaln_proj.linear.bias\", \"transformer_blocks.3.norm1.weight\", \"transformer_blocks.3.attn.to_q.weight\", \"transformer_blocks.3.attn.to_k.weight\", \"transformer_blocks.3.attn.to_v.weight\", \"transformer_blocks.3.attn.norm_q.weight\", \"transformer_blocks.3.attn.norm_k.weight\", \"transformer_blocks.3.attn.to_out.0.weight\", \"transformer_blocks.3.norm2.weight\", \"transformer_blocks.3.ff.net.0.proj.weight\", \"transformer_blocks.3.ff.net.2.weight\", \"transformer_blocks.3.adaln_proj.linear.weight\", \"transformer_blocks.3.adaln_proj.linear.bias\", \"transformer_blocks.4.norm1.weight\", \"transformer_blocks.4.attn.to_q.weight\", \"transformer_blocks.4.attn.to_k.weight\", \"transformer_blocks.4.attn.to_v.weight\", \"transformer_blocks.4.attn.norm_q.weight\", \"transformer_blocks.4.attn.norm_k.weight\", \"transformer_blocks.4.attn.to_out.0.weight\", \"transformer_blocks.4.norm2.weight\", \"transformer_blocks.4.ff.net.0.proj.weight\", \"transformer_blocks.4.ff.net.2.weight\", \"transformer_blocks.4.adaln_proj.linear.weight\", \"transformer_blocks.4.adaln_proj.linear.bias\", \"transformer_blocks.5.norm1.weight\", \"transformer_blocks.5.attn.to_q.weight\", \"transformer_blocks.5.attn.to_k.weight\", \"transformer_blocks.5.attn.to_v.weight\", \"transformer_blocks.5.attn.norm_q.weight\", \"transformer_blocks.5.attn.norm_k.weight\", \"transformer_blocks.5.attn.to_out.0.weight\", \"transformer_blocks.5.norm2.weight\", \"transformer_blocks.5.ff.net.0.proj.weight\", \"transformer_blocks.5.ff.net.2.weight\", \"transformer_blocks.5.adaln_proj.linear.weight\", \"transformer_blocks.5.adaln_proj.linear.bias\", \"transformer_blocks.6.norm1.weight\", \"transformer_blocks.6.attn.to_q.weight\", \"transformer_blocks.6.attn.to_k.weight\", \"transformer_blocks.6.attn.to_v.weight\", \"transformer_blocks.6.attn.norm_q.weight\", \"transformer_blocks.6.attn.norm_k.weight\", \"transformer_blocks.6.attn.to_out.0.weight\", \"transformer_blocks.6.norm2.weight\", \"transformer_blocks.6.ff.net.0.proj.weight\", \"transformer_blocks.6.ff.net.2.weight\", \"transformer_blocks.6.adaln_proj.linear.weight\", \"transformer_blocks.6.adaln_proj.linear.bias\", \"transformer_blocks.7.norm1.weight\", \"transformer_blocks.7.attn.to_q.weight\", \"transformer_blocks.7.attn.to_k.weight\", \"transformer_blocks.7.attn.to_v.weight\", \"transformer_blocks.7.attn.norm_q.weight\", \"transformer_blocks.7.attn.norm_k.weight\", \"transformer_blocks.7.attn.to_out.0.weight\", \"transformer_blocks.7.norm2.weight\", \"transformer_blocks.7.ff.net.0.proj.weight\", \"transformer_blocks.7.ff.net.2.weight\", \"transformer_blocks.7.adaln_proj.linear.weight\", \"transformer_blocks.7.adaln_proj.linear.bias\", \"transformer_blocks.8.norm1.weight\", \"transformer_blocks.8.attn.to_q.weight\", \"transformer_blocks.8.attn.to_k.weight\", \"transformer_blocks.8.attn.to_v.weight\", \"transformer_blocks.8.attn.norm_q.weight\", \"transformer_blocks.8.attn.norm_k.weight\", \"transformer_blocks.8.attn.to_out.0.weight\", \"transformer_blocks.8.norm2.weight\", \"transformer_blocks.8.ff.net.0.proj.weight\", \"transformer_blocks.8.ff.net.2.weight\", \"transformer_blocks.8.adaln_proj.linear.weight\", \"transformer_blocks.8.adaln_proj.linear.bias\", \"transformer_blocks.9.norm1.weight\", \"transformer_blocks.9.attn.to_q.weight\", \"transformer_blocks.9.attn.to_k.weight\", \"transformer_blocks.9.attn.to_v.weight\", \"transformer_blocks.9.attn.norm_q.weight\", \"transformer_blocks.9.attn.norm_k.weight\", \"transformer_blocks.9.attn.to_out.0.weight\", \"transformer_blocks.9.norm2.weight\", \"transformer_blocks.9.ff.net.0.proj.weight\", \"transformer_blocks.9.ff.net.2.weight\", \"transformer_blocks.9.adaln_proj.linear.weight\", \"transformer_blocks.9.adaln_proj.linear.bias\", \"transformer_blocks.10.norm1.weight\", \"transformer_blocks.10.attn.to_q.weight\", \"transformer_blocks.10.attn.to_k.weight\", \"transformer_blocks.10.attn.to_v.weight\", \"transformer_blocks.10.attn.norm_q.weight\", \"transformer_blocks.10.attn.norm_k.weight\", \"transformer_blocks.10.attn.to_out.0.weight\", \"transformer_blocks.10.norm2.weight\", \"transformer_blocks.10.ff.net.0.proj.weight\", \"transformer_blocks.10.ff.net.2.weight\", \"transformer_blocks.10.adaln_proj.linear.weight\", \"transformer_blocks.10.adaln_proj.linear.bias\", \"transformer_blocks.11.norm1.weight\", \"transformer_blocks.11.attn.to_q.weight\", \"transformer_blocks.11.attn.to_k.weight\", \"transformer_blocks.11.attn.to_v.weight\", \"transformer_blocks.11.attn.norm_q.weight\", \"transformer_blocks.11.attn.norm_k.weight\", \"transformer_blocks.11.attn.to_out.0.weight\", \"transformer_blocks.11.norm2.weight\", \"transformer_blocks.11.ff.net.0.proj.weight\", \"transformer_blocks.11.ff.net.2.weight\", \"transformer_blocks.11.adaln_proj.linear.weight\", \"transformer_blocks.11.adaln_proj.linear.bias\", \"transformer_blocks.12.norm1.weight\", \"transformer_blocks.12.attn.to_q.weight\", \"transformer_blocks.12.attn.to_k.weight\", \"transformer_blocks.12.attn.to_v.weight\", \"transformer_blocks.12.attn.norm_q.weight\", \"transformer_blocks.12.attn.norm_k.weight\", \"transformer_blocks.12.attn.to_out.0.weight\", \"transformer_blocks.12.norm2.weight\", \"transformer_blocks.12.ff.net.0.proj.weight\", \"transformer_blocks.12.ff.net.2.weight\", \"transformer_blocks.12.adaln_proj.linear.weight\", \"transformer_blocks.12.adaln_proj.linear.bias\", \"transformer_blocks.13.norm1.weight\", \"transformer_blocks.13.attn.to_q.weight\", \"transformer_blocks.13.attn.to_k.weight\", \"transformer_blocks.13.attn.to_v.weight\", \"transformer_blocks.13.attn.norm_q.weight\", \"transformer_blocks.13.attn.norm_k.weight\", \"transformer_blocks.13.attn.to_out.0.weight\", \"transformer_blocks.13.norm2.weight\", \"transformer_blocks.13.ff.net.0.proj.weight\", \"transformer_blocks.13.ff.net.2.weight\", \"transformer_blocks.13.adaln_proj.linear.weight\", \"transformer_blocks.13.adaln_proj.linear.bias\", \"transformer_blocks.14.norm1.weight\", \"transformer_blocks.14.attn.to_q.weight\", \"transformer_blocks.14.attn.to_k.weight\", \"transformer_blocks.14.attn.to_v.weight\", \"transformer_blocks.14.attn.norm_q.weight\", \"transformer_blocks.14.attn.norm_k.weight\", \"transformer_blocks.14.attn.to_out.0.weight\", \"transformer_blocks.14.norm2.weight\", \"transformer_blocks.14.ff.net.0.proj.weight\", \"transformer_blocks.14.ff.net.2.weight\", \"transformer_blocks.14.adaln_proj.linear.weight\", \"transformer_blocks.14.adaln_proj.linear.bias\", \"transformer_blocks.15.norm1.weight\", \"transformer_blocks.15.attn.to_q.weight\", \"transformer_blocks.15.attn.to_k.weight\", \"transformer_blocks.15.attn.to_v.weight\", \"transformer_blocks.15.attn.norm_q.weight\", \"transformer_blocks.15.attn.norm_k.weight\", \"transformer_blocks.15.attn.to_out.0.weight\", \"transformer_blocks.15.norm2.weight\", \"transformer_blocks.15.ff.net.0.proj.weight\", \"transformer_blocks.15.ff.net.2.weight\", \"transformer_blocks.15.adaln_proj.linear.weight\", \"transformer_blocks.15.adaln_proj.linear.bias\", \"transformer_blocks.16.norm1.weight\", \"transformer_blocks.16.attn.to_q.weight\", \"transformer_blocks.16.attn.to_k.weight\", \"transformer_blocks.16.attn.to_v.weight\", \"transformer_blocks.16.attn.norm_q.weight\", \"transformer_blocks.16.attn.norm_k.weight\", \"transformer_blocks.16.attn.to_out.0.weight\", \"transformer_blocks.16.norm2.weight\", \"transformer_blocks.16.ff.net.0.proj.weight\", \"transformer_blocks.16.ff.net.2.weight\", \"transformer_blocks.16.adaln_proj.linear.weight\", \"transformer_blocks.16.adaln_proj.linear.bias\", \"transformer_blocks.17.norm1.weight\", \"transformer_blocks.17.attn.to_q.weight\", \"transformer_blocks.17.attn.to_k.weight\", \"transformer_blocks.17.attn.to_v.weight\", \"transformer_blocks.17.attn.norm_q.weight\", \"transformer_blocks.17.attn.norm_k.weight\", \"transformer_blocks.17.attn.to_out.0.weight\", \"transformer_blocks.17.norm2.weight\", \"transformer_blocks.17.ff.net.0.proj.weight\", \"transformer_blocks.17.ff.net.2.weight\", \"transformer_blocks.17.adaln_proj.linear.weight\", \"transformer_blocks.17.adaln_proj.linear.bias\", \"transformer_blocks.18.norm1.weight\", \"transformer_blocks.18.attn.to_q.weight\", \"transformer_blocks.18.attn.to_k.weight\", \"transformer_blocks.18.attn.to_v.weight\", \"transformer_blocks.18.attn.norm_q.weight\", \"transformer_blocks.18.attn.norm_k.weight\", \"transformer_blocks.18.attn.to_out.0.weight\", \"transformer_blocks.18.norm2.weight\", \"transformer_blocks.18.ff.net.0.proj.weight\", \"transformer_blocks.18.ff.net.2.weight\", \"transformer_blocks.18.adaln_proj.linear.weight\", \"transformer_blocks.18.adaln_proj.linear.bias\", \"transformer_blocks.19.norm1.weight\", \"transformer_blocks.19.attn.to_q.weight\", \"transformer_blocks.19.attn.to_k.weight\", \"transformer_blocks.19.attn.to_v.weight\", \"transformer_blocks.19.attn.norm_q.weight\", \"transformer_blocks.19.attn.norm_k.weight\", \"transformer_blocks.19.attn.to_out.0.weight\", \"transformer_blocks.19.norm2.weight\", \"transformer_blocks.19.ff.net.0.proj.weight\", \"transformer_blocks.19.ff.net.2.weight\", \"transformer_blocks.19.adaln_proj.linear.weight\", \"transformer_blocks.19.adaln_proj.linear.bias\", \"transformer_blocks.20.norm1.weight\", \"transformer_blocks.20.attn.to_q.weight\", \"transformer_blocks.20.attn.to_k.weight\", \"transformer_blocks.20.attn.to_v.weight\", \"transformer_blocks.20.attn.norm_q.weight\", \"transformer_blocks.20.attn.norm_k.weight\", \"transformer_blocks.20.attn.to_out.0.weight\", \"transformer_blocks.20.norm2.weight\", \"transformer_blocks.20.ff.net.0.proj.weight\", \"transformer_blocks.20.ff.net.2.weight\", \"transformer_blocks.20.adaln_proj.linear.weight\", \"transformer_blocks.20.adaln_proj.linear.bias\", \"transformer_blocks.21.norm1.weight\", \"transformer_blocks.21.attn.to_q.weight\", \"transformer_blocks.21.attn.to_k.weight\", \"transformer_blocks.21.attn.to_v.weight\", \"transformer_blocks.21.attn.norm_q.weight\", \"transformer_blocks.21.attn.norm_k.weight\", \"transformer_blocks.21.attn.to_out.0.weight\", \"transformer_blocks.21.norm2.weight\", \"transformer_blocks.21.ff.net.0.proj.weight\", \"transformer_blocks.21.ff.net.2.weight\", \"transformer_blocks.21.adaln_proj.linear.weight\", \"transformer_blocks.21.adaln_proj.linear.bias\", \"transformer_blocks.22.norm1.weight\", \"transformer_blocks.22.attn.to_q.weight\", \"transformer_blocks.22.attn.to_k.weight\", \"transformer_blocks.22.attn.to_v.weight\", \"transformer_blocks.22.attn.norm_q.weight\", \"transformer_blocks.22.attn.norm_k.weight\", \"transformer_blocks.22.attn.to_out.0.weight\", \"transformer_blocks.22.norm2.weight\", \"transformer_blocks.22.ff.net.0.proj.weight\", \"transformer_blocks.22.ff.net.2.weight\", \"transformer_blocks.22.adaln_proj.linear.weight\", \"transformer_blocks.22.adaln_proj.linear.bias\", \"transformer_blocks.23.norm1.weight\", \"transformer_blocks.23.attn.to_q.weight\", \"transformer_blocks.23.attn.to_k.weight\", \"transformer_blocks.23.attn.to_v.weight\", \"transformer_blocks.23.attn.norm_q.weight\", \"transformer_blocks.23.attn.norm_k.weight\", \"transformer_blocks.23.attn.to_out.0.weight\", \"transformer_blocks.23.norm2.weight\", \"transformer_blocks.23.ff.net.0.proj.weight\", \"transformer_blocks.23.ff.net.2.weight\", \"transformer_blocks.23.adaln_proj.linear.weight\", \"transformer_blocks.23.adaln_proj.linear.bias\", \"transformer_blocks.24.norm1.weight\", \"transformer_blocks.24.attn.to_q.weight\", \"transformer_blocks.24.attn.to_k.weight\", \"transformer_blocks.24.attn.to_v.weight\", \"transformer_blocks.24.attn.norm_q.weight\", \"transformer_blocks.24.attn.norm_k.weight\", \"transformer_blocks.24.attn.to_out.0.weight\", \"transformer_blocks.24.norm2.weight\", \"transformer_blocks.24.ff.net.0.proj.weight\", \"transformer_blocks.24.ff.net.2.weight\", \"transformer_blocks.24.adaln_proj.linear.weight\", \"transformer_blocks.24.adaln_proj.linear.bias\", \"transformer_blocks.25.norm1.weight\", \"transformer_blocks.25.attn.to_q.weight\", \"transformer_blocks.25.attn.to_k.weight\", \"transformer_blocks.25.attn.to_v.weight\", \"transformer_blocks.25.attn.norm_q.weight\", \"transformer_blocks.25.attn.norm_k.weight\", \"transformer_blocks.25.attn.to_out.0.weight\", \"transformer_blocks.25.norm2.weight\", \"transformer_blocks.25.ff.net.0.proj.weight\", \"transformer_blocks.25.ff.net.2.weight\", \"transformer_blocks.25.adaln_proj.linear.weight\", \"transformer_blocks.25.adaln_proj.linear.bias\", \"transformer_blocks.26.norm1.weight\", \"transformer_blocks.26.attn.to_q.weight\", \"transformer_blocks.26.attn.to_k.weight\", \"transformer_blocks.26.attn.to_v.weight\", \"transformer_blocks.26.attn.norm_q.weight\", \"transformer_blocks.26.attn.norm_k.weight\", \"transformer_blocks.26.attn.to_out.0.weight\", \"transformer_blocks.26.norm2.weight\", \"transformer_blocks.26.ff.net.0.proj.weight\", \"transformer_blocks.26.ff.net.2.weight\", \"transformer_blocks.26.adaln_proj.linear.weight\", \"transformer_blocks.26.adaln_proj.linear.bias\", \"transformer_blocks.27.norm1.weight\", \"transformer_blocks.27.attn.to_q.weight\", \"transformer_blocks.27.attn.to_k.weight\", \"transformer_blocks.27.attn.to_v.weight\", \"transformer_blocks.27.attn.norm_q.weight\", \"transformer_blocks.27.attn.norm_k.weight\", \"transformer_blocks.27.attn.to_out.0.weight\", \"transformer_blocks.27.norm2.weight\", \"transformer_blocks.27.ff.net.0.proj.weight\", \"transformer_blocks.27.ff.net.2.weight\", \"transformer_blocks.27.adaln_proj.linear.weight\", \"transformer_blocks.27.adaln_proj.linear.bias\", \"transformer_blocks.28.norm1.weight\", \"transformer_blocks.28.attn.to_q.weight\", \"transformer_blocks.28.attn.to_k.weight\", \"transformer_blocks.28.attn.to_v.weight\", \"transformer_blocks.28.attn.norm_q.weight\", \"transformer_blocks.28.attn.norm_k.weight\", \"transformer_blocks.28.attn.to_out.0.weight\", \"transformer_blocks.28.norm2.weight\", \"transformer_blocks.28.ff.net.0.proj.weight\", \"transformer_blocks.28.ff.net.2.weight\", \"transformer_blocks.28.adaln_proj.linear.weight\", \"transformer_blocks.28.adaln_proj.linear.bias\", \"transformer_blocks.29.norm1.weight\", \"transformer_blocks.29.attn.to_q.weight\", \"transformer_blocks.29.attn.to_k.weight\", \"transformer_blocks.29.attn.to_v.weight\", \"transformer_blocks.29.attn.norm_q.weight\", \"transformer_blocks.29.attn.norm_k.weight\", \"transformer_blocks.29.attn.to_out.0.weight\", \"transformer_blocks.29.norm2.weight\", \"transformer_blocks.29.ff.net.0.proj.weight\", \"transformer_blocks.29.ff.net.2.weight\", \"transformer_blocks.29.adaln_proj.linear.weight\", \"transformer_blocks.29.adaln_proj.linear.bias\", \"transformer_blocks.30.norm1.weight\", \"transformer_blocks.30.attn.to_q.weight\", \"transformer_blocks.30.attn.to_k.weight\", \"transformer_blocks.30.attn.to_v.weight\", \"transformer_blocks.30.attn.norm_q.weight\", \"transformer_blocks.30.attn.norm_k.weight\", \"transformer_blocks.30.attn.to_out.0.weight\", \"transformer_blocks.30.norm2.weight\", \"transformer_blocks.30.ff.net.0.proj.weight\", \"transformer_blocks.30.ff.net.2.weight\", \"transformer_blocks.30.adaln_proj.linear.weight\", \"transformer_blocks.30.adaln_proj.linear.bias\", \"transformer_blocks.31.norm1.weight\", \"transformer_blocks.31.attn.to_q.weight\", \"transformer_blocks.31.attn.to_k.weight\", \"transformer_blocks.31.attn.to_v.weight\", \"transformer_blocks.31.attn.norm_q.weight\", \"transformer_blocks.31.attn.norm_k.weight\", \"transformer_blocks.31.attn.to_out.0.weight\", \"transformer_blocks.31.norm2.weight\", \"transformer_blocks.31.ff.net.0.proj.weight\", \"transformer_blocks.31.ff.net.2.weight\", \"transformer_blocks.31.adaln_proj.linear.weight\", \"transformer_blocks.31.adaln_proj.linear.bias\", \"transformer_blocks.32.norm1.weight\", \"transformer_blocks.32.attn.to_q.weight\", \"transformer_blocks.32.attn.to_k.weight\", \"transformer_blocks.32.attn.to_v.weight\", \"transformer_blocks.32.attn.norm_q.weight\", \"transformer_blocks.32.attn.norm_k.weight\", \"transformer_blocks.32.attn.to_out.0.weight\", \"transformer_blocks.32.norm2.weight\", \"transformer_blocks.32.ff.net.0.proj.weight\", \"transformer_blocks.32.ff.net.2.weight\", \"transformer_blocks.32.adaln_proj.linear.weight\", \"transformer_blocks.32.adaln_proj.linear.bias\", \"transformer_blocks.33.norm1.weight\", \"transformer_blocks.33.attn.to_q.weight\", \"transformer_blocks.33.attn.to_k.weight\", \"transformer_blocks.33.attn.to_v.weight\", \"transformer_blocks.33.attn.norm_q.weight\", \"transformer_blocks.33.attn.norm_k.weight\", \"transformer_blocks.33.attn.to_out.0.weight\", \"transformer_blocks.33.norm2.weight\", \"transformer_blocks.33.ff.net.0.proj.weight\", \"transformer_blocks.33.ff.net.2.weight\", \"transformer_blocks.33.adaln_proj.linear.weight\", \"transformer_blocks.33.adaln_proj.linear.bias\", \"transformer_blocks.34.norm1.weight\", \"transformer_blocks.34.attn.to_q.weight\", \"transformer_blocks.34.attn.to_k.weight\", \"transformer_blocks.34.attn.to_v.weight\", \"transformer_blocks.34.attn.norm_q.weight\", \"transformer_blocks.34.attn.norm_k.weight\", \"transformer_blocks.34.attn.to_out.0.weight\", \"transformer_blocks.34.norm2.weight\", \"transformer_blocks.34.ff.net.0.proj.weight\", \"transformer_blocks.34.ff.net.2.weight\", \"transformer_blocks.34.adaln_proj.linear.weight\", \"transformer_blocks.34.adaln_proj.linear.bias\", \"transformer_blocks.35.norm1.weight\", \"transformer_blocks.35.attn.to_q.weight\", \"transformer_blocks.35.attn.to_k.weight\", \"transformer_blocks.35.attn.to_v.weight\", \"transformer_blocks.35.attn.norm_q.weight\", \"transformer_blocks.35.attn.norm_k.weight\", \"transformer_blocks.35.attn.to_out.0.weight\", \"transformer_blocks.35.norm2.weight\", \"transformer_blocks.35.ff.net.0.proj.weight\", \"transformer_blocks.35.ff.net.2.weight\", \"transformer_blocks.35.adaln_proj.linear.weight\", \"transformer_blocks.35.adaln_proj.linear.bias\", \"transformer_blocks.36.norm1.weight\", \"transformer_blocks.36.attn.to_q.weight\", \"transformer_blocks.36.attn.to_k.weight\", \"transformer_blocks.36.attn.to_v.weight\", \"transformer_blocks.36.attn.norm_q.weight\", \"transformer_blocks.36.attn.norm_k.weight\", \"transformer_blocks.36.attn.to_out.0.weight\", \"transformer_blocks.36.norm2.weight\", \"transformer_blocks.36.ff.net.0.proj.weight\", \"transformer_blocks.36.ff.net.2.weight\", \"transformer_blocks.36.adaln_proj.linear.weight\", \"transformer_blocks.36.adaln_proj.linear.bias\", \"transformer_blocks.37.norm1.weight\", \"transformer_blocks.37.attn.to_q.weight\", \"transformer_blocks.37.attn.to_k.weight\", \"transformer_blocks.37.attn.to_v.weight\", \"transformer_blocks.37.attn.norm_q.weight\", \"transformer_blocks.37.attn.norm_k.weight\", \"transformer_blocks.37.attn.to_out.0.weight\", \"transformer_blocks.37.norm2.weight\", \"transformer_blocks.37.ff.net.0.proj.weight\", \"transformer_blocks.37.ff.net.2.weight\", \"transformer_blocks.37.adaln_proj.linear.weight\", \"transformer_blocks.37.adaln_proj.linear.bias\", \"transformer_blocks.38.norm1.weight\", \"transformer_blocks.38.attn.to_q.weight\", \"transformer_blocks.38.attn.to_k.weight\", \"transformer_blocks.38.attn.to_v.weight\", \"transformer_blocks.38.attn.norm_q.weight\", \"transformer_blocks.38.attn.norm_k.weight\", \"transformer_blocks.38.attn.to_out.0.weight\", \"transformer_blocks.38.norm2.weight\", \"transformer_blocks.38.ff.net.0.proj.weight\", \"transformer_blocks.38.ff.net.2.weight\", \"transformer_blocks.38.adaln_proj.linear.weight\", \"transformer_blocks.38.adaln_proj.linear.bias\", \"transformer_blocks.39.norm1.weight\", \"transformer_blocks.39.attn.to_q.weight\", \"transformer_blocks.39.attn.to_k.weight\", \"transformer_blocks.39.attn.to_v.weight\", \"transformer_blocks.39.attn.norm_q.weight\", \"transformer_blocks.39.attn.norm_k.weight\", \"transformer_blocks.39.attn.to_out.0.weight\", \"transformer_blocks.39.norm2.weight\", \"transformer_blocks.39.ff.net.0.proj.weight\", \"transformer_blocks.39.ff.net.2.weight\", \"transformer_blocks.39.adaln_proj.linear.weight\", \"transformer_blocks.39.adaln_proj.linear.bias\", \"transformer_blocks.40.norm1.weight\", \"transformer_blocks.40.attn.to_q.weight\", \"transformer_blocks.40.attn.to_k.weight\", \"transformer_blocks.40.attn.to_v.weight\", \"transformer_blocks.40.attn.norm_q.weight\", \"transformer_blocks.40.attn.norm_k.weight\", \"transformer_blocks.40.attn.to_out.0.weight\", \"transformer_blocks.40.norm2.weight\", \"transformer_blocks.40.ff.net.0.proj.weight\", \"transformer_blocks.40.ff.net.2.weight\", \"transformer_blocks.40.adaln_proj.linear.weight\", \"transformer_blocks.40.adaln_proj.linear.bias\", \"transformer_blocks.41.norm1.weight\", \"transformer_blocks.41.attn.to_q.weight\", \"transformer_blocks.41.attn.to_k.weight\", \"transformer_blocks.41.attn.to_v.weight\", \"transformer_blocks.41.attn.norm_q.weight\", \"transformer_blocks.41.attn.norm_k.weight\", \"transformer_blocks.41.attn.to_out.0.weight\", \"transformer_blocks.41.norm2.weight\", \"transformer_blocks.41.ff.net.0.proj.weight\", \"transformer_blocks.41.ff.net.2.weight\", \"transformer_blocks.41.adaln_proj.linear.weight\", \"transformer_blocks.41.adaln_proj.linear.bias\", \"transformer_blocks.42.norm1.weight\", \"transformer_blocks.42.attn.to_q.weight\", \"transformer_blocks.42.attn.to_k.weight\", \"transformer_blocks.42.attn.to_v.weight\", \"transformer_blocks.42.attn.norm_q.weight\", \"transformer_blocks.42.attn.norm_k.weight\", \"transformer_blocks.42.attn.to_out.0.weight\", \"transformer_blocks.42.norm2.weight\", \"transformer_blocks.42.ff.net.0.proj.weight\", \"transformer_blocks.42.ff.net.2.weight\", \"transformer_blocks.42.adaln_proj.linear.weight\", \"transformer_blocks.42.adaln_proj.linear.bias\", \"transformer_blocks.43.norm1.weight\", \"transformer_blocks.43.attn.to_q.weight\", \"transformer_blocks.43.attn.to_k.weight\", \"transformer_blocks.43.attn.to_v.weight\", \"transformer_blocks.43.attn.norm_q.weight\", \"transformer_blocks.43.attn.norm_k.weight\", \"transformer_blocks.43.attn.to_out.0.weight\", \"transformer_blocks.43.norm2.weight\", \"transformer_blocks.43.ff.net.0.proj.weight\", \"transformer_blocks.43.ff.net.2.weight\", \"transformer_blocks.43.adaln_proj.linear.weight\", \"transformer_blocks.43.adaln_proj.linear.bias\", \"transformer_blocks.44.norm1.weight\", \"transformer_blocks.44.attn.to_q.weight\", \"transformer_blocks.44.attn.to_k.weight\", \"transformer_blocks.44.attn.to_v.weight\", \"transformer_blocks.44.attn.norm_q.weight\", \"transformer_blocks.44.attn.norm_k.weight\", \"transformer_blocks.44.attn.to_out.0.weight\", \"transformer_blocks.44.norm2.weight\", \"transformer_blocks.44.ff.net.0.proj.weight\", \"transformer_blocks.44.ff.net.2.weight\", \"transformer_blocks.44.adaln_proj.linear.weight\", \"transformer_blocks.44.adaln_proj.linear.bias\", \"transformer_blocks.45.norm1.weight\", \"transformer_blocks.45.attn.to_q.weight\", \"transformer_blocks.45.attn.to_k.weight\", \"transformer_blocks.45.attn.to_v.weight\", \"transformer_blocks.45.attn.norm_q.weight\", \"transformer_blocks.45.attn.norm_k.weight\", \"transformer_blocks.45.attn.to_out.0.weight\", \"transformer_blocks.45.norm2.weight\", \"transformer_blocks.45.ff.net.0.proj.weight\", \"transformer_blocks.45.ff.net.2.weight\", \"transformer_blocks.45.adaln_proj.linear.weight\", \"transformer_blocks.45.adaln_proj.linear.bias\", \"transformer_blocks.46.norm1.weight\", \"transformer_blocks.46.attn.to_q.weight\", \"transformer_blocks.46.attn.to_k.weight\", \"transformer_blocks.46.attn.to_v.weight\", \"transformer_blocks.46.attn.norm_q.weight\", \"transformer_blocks.46.attn.norm_k.weight\", \"transformer_blocks.46.attn.to_out.0.weight\", \"transformer_blocks.46.norm2.weight\", \"transformer_blocks.46.ff.net.0.proj.weight\", \"transformer_blocks.46.ff.net.2.weight\", \"transformer_blocks.46.adaln_proj.linear.weight\", \"transformer_blocks.46.adaln_proj.linear.bias\", \"transformer_blocks.47.norm1.weight\", \"transformer_blocks.47.attn.to_q.weight\", \"transformer_blocks.47.attn.to_k.weight\", \"transformer_blocks.47.attn.to_v.weight\", \"transformer_blocks.47.attn.norm_q.weight\", \"transformer_blocks.47.attn.norm_k.weight\", \"transformer_blocks.47.attn.to_out.0.weight\", \"transformer_blocks.47.norm2.weight\", \"transformer_blocks.47.ff.net.0.proj.weight\", \"transformer_blocks.47.ff.net.2.weight\", \"transformer_blocks.47.adaln_proj.linear.weight\", \"transformer_blocks.47.adaln_proj.linear.bias\", \"transformer_blocks.48.norm1.weight\", \"transformer_blocks.48.attn.to_q.weight\", \"transformer_blocks.48.attn.to_k.weight\", \"transformer_blocks.48.attn.to_v.weight\", \"transformer_blocks.48.attn.norm_q.weight\", \"transformer_blocks.48.attn.norm_k.weight\", \"transformer_blocks.48.attn.to_out.0.weight\", \"transformer_blocks.48.norm2.weight\", \"transformer_blocks.48.ff.net.0.proj.weight\", \"transformer_blocks.48.ff.net.2.weight\", \"transformer_blocks.48.adaln_proj.linear.weight\", \"transformer_blocks.48.adaln_proj.linear.bias\", \"transformer_blocks.49.norm1.weight\", \"transformer_blocks.49.attn.to_q.weight\", \"transformer_blocks.49.attn.to_k.weight\", \"transformer_blocks.49.attn.to_v.weight\", \"transformer_blocks.49.attn.norm_q.weight\", \"transformer_blocks.49.attn.norm_k.weight\", \"transformer_blocks.49.attn.to_out.0.weight\", \"transformer_blocks.49.norm2.weight\", \"transformer_blocks.49.ff.net.0.proj.weight\", \"transformer_blocks.49.ff.net.2.weight\", \"transformer_blocks.49.adaln_proj.linear.weight\", \"transformer_blocks.49.adaln_proj.linear.bias\", \"norm_out.norm.weight\", \"norm_out.linear.weight\", \"norm_out.linear.bias\", \"proj_out.weight\", \"proj_out.bias\", \"audio_proj_out.weight\", \"audio_proj_out.bias\"]", "time_embedder.linear_1.bias": "{\"_type\": \"Tensor\"}", "time_embedder.linear_1.weight": "{\"_type\": \"Tensor\"}", "time_embedder.linear_2.bias": "{\"_type\": \"Tensor\"}", "time_embedder.linear_2.weight": "{\"_type\": \"Tensor\"}", "token_refiner.final_norm.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.0.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.0.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.0.attn.to_k.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.0.attn.to_out.0.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.0.attn.to_q.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.0.attn.to_v.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.0.ff.net.0.proj.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.0.ff.net.2.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.0.norm1.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.0.norm2.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.1.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.1.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.1.attn.to_k.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.1.attn.to_out.0.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.1.attn.to_q.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.1.attn.to_v.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.1.ff.net.0.proj.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.1.ff.net.2.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.1.norm1.weight": "{\"_type\": \"Tensor\"}", "token_refiner.refiner_blocks.1.norm2.weight": "{\"_type\": \"Tensor\"}", "total_size": 34046650880, "transformer_blocks.0.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.0.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.0.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.0.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.0.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.0.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.0.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.0.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.0.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.0.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.0.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.0.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.1.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.1.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.1.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.1.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.1.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.1.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.1.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.1.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.1.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.1.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.1.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.1.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.10.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.10.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.10.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.10.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.10.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.10.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.10.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.10.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.10.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.10.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.10.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.10.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.11.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.11.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.11.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.11.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.11.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.11.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.11.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.11.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.11.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.11.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.11.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.11.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.12.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.12.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.12.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.12.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.12.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.12.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.12.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.12.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.12.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.12.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.12.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.12.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.13.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.13.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.13.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.13.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.13.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.13.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.13.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.13.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.13.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.13.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.13.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.13.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.14.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.14.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.14.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.14.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.14.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.14.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.14.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.14.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.14.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.14.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.14.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.14.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.15.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.15.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.15.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.15.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.15.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.15.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.15.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.15.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.15.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.15.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.15.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.15.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.16.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.16.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.16.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.16.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.16.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.16.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.16.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.16.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.16.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.16.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.16.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.16.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.17.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.17.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.17.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.17.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.17.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.17.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.17.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.17.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.17.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.17.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.17.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.17.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.18.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.18.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.18.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.18.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.18.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.18.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.18.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.18.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.18.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.18.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.18.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.18.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.19.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.19.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.19.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.19.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.19.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.19.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.19.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.19.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.19.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.19.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.19.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.19.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.2.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.2.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.2.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.2.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.2.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.2.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.2.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.2.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.2.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.2.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.2.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.2.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.20.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.20.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.20.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.20.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.20.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.20.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.20.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.20.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.20.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.20.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.20.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.20.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.21.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.21.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.21.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.21.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.21.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.21.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.21.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.21.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.21.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.21.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.21.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.21.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.22.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.22.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.22.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.22.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.22.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.22.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.22.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.22.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.22.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.22.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.22.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.22.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.23.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.23.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.23.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.23.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.23.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.23.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.23.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.23.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.23.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.23.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.23.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.23.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.24.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.24.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.24.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.24.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.24.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.24.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.24.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.24.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.24.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.24.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.24.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.24.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.25.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.25.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.25.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.25.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.25.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.25.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.25.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.25.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.25.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.25.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.25.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.25.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.26.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.26.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.26.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.26.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.26.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.26.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.26.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.26.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.26.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.26.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.26.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.26.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.27.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.27.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.27.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.27.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.27.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.27.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.27.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.27.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.27.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.27.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.27.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.27.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.28.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.28.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.28.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.28.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.28.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.28.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.28.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.28.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.28.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.28.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.28.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.28.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.29.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.29.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.29.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.29.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.29.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.29.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.29.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.29.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.29.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.29.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.29.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.29.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.3.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.3.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.3.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.3.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.3.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.3.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.3.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.3.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.3.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.3.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.3.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.3.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.30.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.30.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.30.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.30.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.30.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.30.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.30.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.30.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.30.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.30.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.30.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.30.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.31.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.31.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.31.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.31.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.31.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.31.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.31.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.31.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.31.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.31.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.31.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.31.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.32.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.32.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.32.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.32.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.32.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.32.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.32.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.32.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.32.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.32.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.32.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.32.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.33.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.33.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.33.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.33.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.33.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.33.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.33.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.33.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.33.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.33.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.33.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.33.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.34.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.34.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.34.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.34.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.34.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.34.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.34.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.34.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.34.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.34.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.34.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.34.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.35.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.35.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.35.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.35.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.35.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.35.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.35.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.35.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.35.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.35.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.35.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.35.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.36.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.36.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.36.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.36.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.36.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.36.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.36.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.36.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.36.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.36.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.36.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.36.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.37.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.37.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.37.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.37.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.37.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.37.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.37.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.37.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.37.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.37.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.37.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.37.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.38.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.38.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.38.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.38.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.38.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.38.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.38.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.38.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.38.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.38.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.38.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.38.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.39.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.39.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.39.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.39.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.39.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.39.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.39.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.39.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.39.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.39.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.39.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.39.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.4.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.4.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.4.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.4.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.4.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.4.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.4.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.4.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.4.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.4.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.4.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.4.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.40.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.40.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.40.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.40.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.40.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.40.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.40.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.40.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.40.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.40.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.40.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.40.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.41.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.41.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.41.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.41.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.41.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.41.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.41.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.41.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.41.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.41.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.41.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.41.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.42.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.42.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.42.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.42.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.42.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.42.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.42.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.42.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.42.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.42.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.42.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.42.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.43.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.43.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.43.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.43.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.43.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.43.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.43.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.43.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.43.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.43.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.43.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.43.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.44.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.44.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.44.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.44.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.44.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.44.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.44.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.44.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.44.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.44.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.44.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.44.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.45.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.45.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.45.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.45.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.45.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.45.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.45.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.45.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.45.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.45.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.45.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.45.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.46.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.46.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.46.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.46.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.46.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.46.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.46.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.46.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.46.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.46.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.46.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.46.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.47.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.47.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.47.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.47.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.47.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.47.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.47.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.47.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.47.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.47.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.47.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.47.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.48.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.48.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.48.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.48.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.48.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.48.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.48.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.48.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.48.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.48.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.48.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.48.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.49.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.49.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.49.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.49.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.49.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.49.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.49.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.49.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.49.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.49.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.49.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.49.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.5.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.5.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.5.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.5.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.5.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.5.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.5.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.5.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.5.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.5.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.5.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.5.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.6.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.6.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.6.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.6.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.6.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.6.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.6.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.6.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.6.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.6.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.6.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.6.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.7.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.7.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.7.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.7.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.7.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.7.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.7.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.7.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.7.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.7.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.7.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.7.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.8.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.8.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.8.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.8.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.8.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.8.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.8.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.8.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.8.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.8.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.8.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.8.norm2.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.9.adaln_proj.linear.bias": "{\"_type\": \"Tensor\"}", "transformer_blocks.9.adaln_proj.linear.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 2688], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.9.attn.norm_k.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.9.attn.norm_q.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.9.attn.to_k.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.9.attn.to_out.0.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 7168], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.9.attn.to_q.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.9.attn.to_v.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.9.ff.net.0.proj.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 5376], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.9.ff.net.2.weight": "{\"_type\": \"Int8Tensor\", \"_data\": {\"act_quant_kwargs\": null, \"reduce_range\": false, \"block_size\": [1, 14336], \"dtype\": {\"_type\": \"torch.dtype\", \"_data\": \"bfloat16\"}}, \"_tensor_data_names\": [\"zero_point\", \"qdata\", \"scale\"]}", "transformer_blocks.9.norm1.weight": "{\"_type\": \"Tensor\"}", "transformer_blocks.9.norm2.weight": "{\"_type\": \"Tensor\"}" }, "weight_map": { "audio_proj_in.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "audio_proj_in.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "audio_proj_out.bias": "diffusion_pytorch_model-00004-of-00004.safetensors", "audio_proj_out.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "context_embedder.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "context_embedder.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "norm_out.linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors", "norm_out.linear.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "norm_out.norm.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "proj_in.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "proj_in.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "proj_out.bias": "diffusion_pytorch_model-00004-of-00004.safetensors", "proj_out.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "time_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "time_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "time_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "time_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.final_norm.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "token_refiner.refiner_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.10.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.11.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.12.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.12.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.12.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.12.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.13.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.13.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.14.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.15.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.16.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.17.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.18.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.19.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.2.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.2.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.20.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.20.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.21.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.22.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.23.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.24.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.25.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.26.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.adaln_proj.linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.to_k._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.to_k._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.to_v._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.to_v._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.ff.net.2._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.ff.net.2._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.27.norm2.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.28.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.attn.to_q._weight_qdata": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.28.attn.to_q._weight_scale": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.28.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.28.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.28.norm1.weight": "diffusion_pytorch_model-00002-of-00004.safetensors", "transformer_blocks.28.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.29.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.3.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.3.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.30.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.30.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.31.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.32.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.33.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.34.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.35.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.36.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.37.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.38.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.39.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.4.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.4.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.40.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.40.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.41.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.adaln_proj.linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.ff.net.2._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.ff.net.2._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.42.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.43.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.43.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.43.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.43.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.to_k._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.to_k._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.to_q._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.to_q._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.to_v._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.to_v._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.ff.net.2._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.43.ff.net.2._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.43.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.43.norm1.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.43.norm2.weight": "diffusion_pytorch_model-00003-of-00004.safetensors", "transformer_blocks.44.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.to_k._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.to_k._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.to_q._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.to_q._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.to_v._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.to_v._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.ff.net.2._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.ff.net.2._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.norm1.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.44.norm2.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.to_k._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.to_k._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.to_q._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.to_q._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.to_v._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.to_v._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.ff.net.2._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.ff.net.2._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.norm1.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.45.norm2.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.to_k._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.to_k._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.to_q._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.to_q._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.to_v._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.to_v._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.ff.net.2._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.ff.net.2._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.norm1.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.46.norm2.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.to_k._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.to_k._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.to_q._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.to_q._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.to_v._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.to_v._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.ff.net.2._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.ff.net.2._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.norm1.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.47.norm2.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.to_k._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.to_k._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.to_q._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.to_q._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.to_v._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.to_v._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.ff.net.2._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.ff.net.2._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.norm1.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.48.norm2.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.adaln_proj.linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.to_k._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.to_k._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.to_q._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.to_q._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.to_v._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.to_v._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.ff.net.2._weight_qdata": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.ff.net.2._weight_scale": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.norm1.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.49.norm2.weight": "diffusion_pytorch_model-00004-of-00004.safetensors", "transformer_blocks.5.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.5.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.6.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.7.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.8.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.adaln_proj.linear._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.adaln_proj.linear._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.adaln_proj.linear._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.adaln_proj.linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.to_k._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.to_k._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.to_k._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.to_out.0._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.to_out.0._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.to_out.0._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.to_q._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.to_q._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.to_q._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.to_v._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.to_v._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.attn.to_v._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.ff.net.0.proj._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.ff.net.0.proj._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.ff.net.0.proj._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.ff.net.2._weight_qdata": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.ff.net.2._weight_scale": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.ff.net.2._weight_zero_point": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.norm1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors", "transformer_blocks.9.norm2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors" } }