Update: convert weights again (#2)

Browse files

- update weights (1bc8a030652932585c0ec8c628670338c23c9019)

Co-authored-by: Raushan Turganbay <[email protected]>

Files changed (3) hide show

model-00007-of-00008.safetensors +2 -2
model-00008-of-00008.safetensors +2 -2
model.safetensors.index.json +410 -410

model-00007-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10a9680ffbd0b011e923553e1268a52a26b5d5dfc2d57ff08226ca64b15a181f
-size 4999930560

 version https://git-lfs.github.com/spec/v1
+oid sha256:6624fed3f3931ccd1168d58190599c06048bdbd61d40f48bc99a4b9ba952cf12
+size 4999932864

model-00008-of-00008.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4c65f1cf90ec40ccb777d60c888455671b50afd375e08539235671645488da4
-size 450196868

 version https://git-lfs.github.com/spec/v1
+oid sha256:332c5b0d8c78f7b1d963adbd1f2c64c684a5f47aee4e1a83ff65675b915d7c50
+size 450198548

model.safetensors.index.json CHANGED Viewed

@@ -298,52 +298,52 @@
     "vqmodel.decoder.conv_in.weight": "model-00007-of-00008.safetensors",
     "vqmodel.decoder.conv_out.bias": "model-00008-of-00008.safetensors",
     "vqmodel.decoder.conv_out.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.k.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.k.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.norm.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.norm.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.norm.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.norm.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.norm.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.norm.norm_layer.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.proj_out.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.proj_out.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.q.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.q.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.v.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.attn_1.v.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.mid.block_2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
     "vqmodel.decoder.norm_out.conv_b.bias": "model-00008-of-00008.safetensors",
     "vqmodel.decoder.norm_out.conv_b.weight": "model-00008-of-00008.safetensors",
     "vqmodel.decoder.norm_out.conv_y.bias": "model-00008-of-00008.safetensors",
@@ -382,374 +382,374 @@
     "vqmodel.decoder.time_res_stack.1.norm2.running_mean": "model-00007-of-00008.safetensors",
     "vqmodel.decoder.time_res_stack.1.norm2.running_var": "model-00007-of-00008.safetensors",
     "vqmodel.decoder.time_res_stack.1.norm2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.0.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.0.block.2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.conv2.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.conv2.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.0.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.conv1.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.conv1.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.conv2.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.conv2.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.1.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.conv1.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.conv1.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.conv2.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.conv2.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.block.2.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.upsample.conv.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.1.upsample.conv.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.conv1.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.conv1.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.conv2.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.conv2.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.nin_shortcut.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.nin_shortcut.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.0.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.conv1.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.conv1.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.conv2.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.conv2.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.1.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.conv1.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.conv1.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.conv2.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.conv2.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.block.2.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.upsample.conv.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.2.upsample.conv.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.k.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.k.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.norm.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.norm.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.norm.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.norm.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.norm.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.norm.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.proj_out.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.proj_out.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.q.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.q.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.v.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.0.v.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.k.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.k.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.norm.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.norm.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.norm.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.norm.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.norm.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.norm.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.proj_out.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.proj_out.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.q.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.q.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.v.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.1.v.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.k.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.k.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.norm.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.norm.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.norm.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.norm.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.norm.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.norm.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.proj_out.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.proj_out.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.q.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.q.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.v.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.attn.2.v.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.conv1.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.conv1.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.conv2.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.conv2.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.0.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.conv1.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.conv1.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.conv2.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.conv2.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.1.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.conv1.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.conv1.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.conv2.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.conv2.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.block.2.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.upsample.conv.bias": "model-00008-of-00008.safetensors",
-    "vqmodel.decoder.up.3.upsample.conv.weight": "model-00008-of-00008.safetensors",
     "vqmodel.encoder.conv_in.bias": "model-00007-of-00008.safetensors",
     "vqmodel.encoder.conv_in.weight": "model-00007-of-00008.safetensors",
     "vqmodel.encoder.conv_out.bias": "model-00007-of-00008.safetensors",
     "vqmodel.encoder.conv_out.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.0.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.0.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.0.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.0.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.0.norm1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.0.norm1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.0.norm2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.0.norm2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.1.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.1.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.1.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.1.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.1.norm1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.1.norm1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.1.norm2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.block.1.norm2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.downsample.conv.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.0.downsample.conv.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.0.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.0.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.0.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.0.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.0.norm1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.0.norm1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.0.norm2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.0.norm2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.1.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.1.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.1.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.1.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.1.norm1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.1.norm1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.1.norm2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.block.1.norm2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.downsample.conv.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.1.downsample.conv.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.0.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.0.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.0.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.0.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.0.norm1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.0.norm1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.0.norm2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.0.norm2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.1.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.1.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.1.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.1.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.1.norm1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.1.norm1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.1.norm2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.block.1.norm2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.downsample.conv.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.2.downsample.conv.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.0.k.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.0.k.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.0.norm.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.0.norm.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.0.proj_out.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.0.proj_out.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.0.q.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.0.q.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.0.v.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.0.v.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.1.k.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.1.k.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.1.norm.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.1.norm.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.1.proj_out.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.1.proj_out.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.1.q.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.1.q.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.1.v.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.attn.1.v.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.0.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.0.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.0.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.0.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.0.norm1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.0.norm1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.0.norm2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.0.norm2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.1.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.1.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.1.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.1.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.1.norm1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.1.norm1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.1.norm2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.down.3.block.1.norm2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.attn_1.k.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.attn_1.k.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.attn_1.norm.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.attn_1.norm.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.attn_1.proj_out.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.attn_1.proj_out.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.attn_1.q.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.attn_1.q.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.attn_1.v.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.attn_1.v.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_1.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_1.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_1.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_1.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_1.norm1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_1.norm1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_1.norm2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_1.norm2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_2.conv1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_2.conv1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_2.conv2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_2.conv2.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_2.norm1.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_2.norm1.weight": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_2.norm2.bias": "model-00007-of-00008.safetensors",
-    "vqmodel.encoder.mid.block_2.norm2.weight": "model-00007-of-00008.safetensors",
     "vqmodel.encoder.norm_out.bias": "model-00007-of-00008.safetensors",
     "vqmodel.encoder.norm_out.weight": "model-00007-of-00008.safetensors",
     "vqmodel.encoder.time_conv.0.conv.conv.bias": "model-00007-of-00008.safetensors",

     "vqmodel.decoder.conv_in.weight": "model-00007-of-00008.safetensors",
     "vqmodel.decoder.conv_out.bias": "model-00008-of-00008.safetensors",
     "vqmodel.decoder.conv_out.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_1.k_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_1.k_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_1.out_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_1.out_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_1.q_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_1.q_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_1.v_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_1.v_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_norm.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_norm.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_norm.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_norm.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_norm.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.attn_norm.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.middle_block.block_2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
     "vqmodel.decoder.norm_out.conv_b.bias": "model-00008-of-00008.safetensors",
     "vqmodel.decoder.norm_out.conv_b.weight": "model-00008-of-00008.safetensors",
     "vqmodel.decoder.norm_out.conv_y.bias": "model-00008-of-00008.safetensors",
     "vqmodel.decoder.time_res_stack.1.norm2.running_mean": "model-00007-of-00008.safetensors",
     "vqmodel.decoder.time_res_stack.1.norm2.running_var": "model-00007-of-00008.safetensors",
     "vqmodel.decoder.time_res_stack.1.norm2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.0.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.0.block.2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.conv2.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.conv2.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.0.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.conv1.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.conv1.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.conv2.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.conv2.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.1.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.conv1.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.conv1.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.conv2.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.conv2.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.block.2.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.upsample.conv.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.1.upsample.conv.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.conv1.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.conv1.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.conv2.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.conv2.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.nin_shortcut.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.nin_shortcut.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.0.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.conv1.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.conv1.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.conv2.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.conv2.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.1.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.conv1.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.conv1.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.conv2.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.conv2.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.block.2.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.upsample.conv.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.2.upsample.conv.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.0.k_proj.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.0.k_proj.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.0.out_proj.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.0.out_proj.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.0.q_proj.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.0.q_proj.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.0.v_proj.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.0.v_proj.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.1.k_proj.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.1.k_proj.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.1.out_proj.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.1.out_proj.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.1.q_proj.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.1.q_proj.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.1.v_proj.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.1.v_proj.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.2.k_proj.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.2.k_proj.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.2.out_proj.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.2.out_proj.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.2.q_proj.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.2.q_proj.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.2.v_proj.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn.2.v_proj.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.0.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.0.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.0.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.0.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.0.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.0.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.1.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.1.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.1.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.1.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.1.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.1.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.2.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.2.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.2.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.2.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.2.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.attn_norms.2.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.conv1.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.conv1.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.conv2.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.conv2.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.0.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.conv1.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.conv1.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.conv2.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.conv2.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.1.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.conv1.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.conv1.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.conv2.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.conv2.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.block.2.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.upsample.conv.bias": "model-00008-of-00008.safetensors",
+    "vqmodel.decoder.up_block.up.3.upsample.conv.weight": "model-00008-of-00008.safetensors",
     "vqmodel.encoder.conv_in.bias": "model-00007-of-00008.safetensors",
     "vqmodel.encoder.conv_in.weight": "model-00007-of-00008.safetensors",
     "vqmodel.encoder.conv_out.bias": "model-00007-of-00008.safetensors",
     "vqmodel.encoder.conv_out.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.0.norm1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.0.norm1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.0.norm2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.0.norm2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.1.norm1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.1.norm1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.1.norm2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.block.1.norm2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.downsample.conv.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.0.downsample.conv.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.0.norm1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.0.norm1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.0.norm2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.0.norm2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.1.norm1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.1.norm1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.1.norm2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.block.1.norm2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.downsample.conv.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.1.downsample.conv.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.0.norm1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.0.norm1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.0.norm2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.0.norm2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.1.norm1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.1.norm1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.1.norm2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.block.1.norm2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.downsample.conv.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.2.downsample.conv.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.0.k_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.0.k_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.0.out_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.0.out_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.0.q_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.0.q_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.0.v_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.0.v_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.1.k_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.1.k_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.1.out_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.1.out_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.1.q_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.1.q_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.1.v_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn.1.v_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn_norms.0.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn_norms.0.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn_norms.1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.attn_norms.1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.0.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.0.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.0.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.0.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.0.norm1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.0.norm1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.0.norm2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.0.norm2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.1.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.1.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.1.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.1.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.1.norm1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.1.norm1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.1.norm2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.down_block.down.3.block.1.norm2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.attn_1.k_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.attn_1.k_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.attn_1.out_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.attn_1.out_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.attn_1.q_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.attn_1.q_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.attn_1.v_proj.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.attn_1.v_proj.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.attn_norm.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.attn_norm.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_1.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_1.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_1.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_1.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_1.norm1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_1.norm1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_1.norm2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_1.norm2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_2.conv1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_2.conv1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_2.conv2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_2.conv2.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_2.norm1.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_2.norm1.weight": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_2.norm2.bias": "model-00007-of-00008.safetensors",
+    "vqmodel.encoder.middle_block.block_2.norm2.weight": "model-00007-of-00008.safetensors",
     "vqmodel.encoder.norm_out.bias": "model-00007-of-00008.safetensors",
     "vqmodel.encoder.norm_out.weight": "model-00007-of-00008.safetensors",
     "vqmodel.encoder.time_conv.0.conv.conv.bias": "model-00007-of-00008.safetensors",