Duplicate from GAIR/daVinci-MagiHuman

Co-authored-by: Jiadi Su <JoyBoy-Su@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+architecture.png filter=lfs diff=lfs merge=lfs -text

1080p_sr/model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46bf7f311131721e9b21f3b17de0538231e155758d4de4f6df37eed3153fad1f
+size 4874105568

1080p_sr/model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37cecd2480708b6a426c471f3d7c1f5522fd54657ffcb2af00b3b0c198f2954
+size 4870191376

1080p_sr/model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08faf375817d908bf6b0af970f644de4b9d6362d06ab4083c5c01d4988ccb017
+size 4940089808

1080p_sr/model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b75ba25bc4b7340168d520cc171cb0b45d4da0df679becf9d628270069553aa
+size 4678522392

1080p_sr/model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21a730d8ffa59aaa720dbf0f8940b46e80c471217b872b424fd69b103341d1b
+size 4481684512

1080p_sr/model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:468e59463d50d89ad9be933ae9933da53e4116131bc1b18cabb728d0dc42ab40
+size 4986435656

1080p_sr/model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7859c51dd129f5e7bf1e9e0be1852fba6bb8662a4b3b2507e1a829c955159dcc
+size 4450330144

1080p_sr/model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c994a1f25e26197ac50490b5688b3c1bb3e0c8045944296b73ac4c11378eac93
+size 4687594528

1080p_sr/model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b7f883831fa9c805551978b63339a95d69276caf79ca88cc73ba077708de11
+size 4963662600

1080p_sr/model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2888ebef8e71aa2be1d464f946b3f9823f550cb7c81aa82767ee7ac04ccaab20
+size 4870171744

1080p_sr/model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291a816f2a7c535b454ca283e9c977bb19ed3fc695c809f7bdd00ef49d779572
+size 4264313856

1080p_sr/model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07696b1cec970e4a628b8b7cbbf9e463db516e333fb4585aa6cc27b13977797
+size 4975132496

1080p_sr/model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df143097eae0ddc2e329d1bb266558a99b51624c70a5767c9d9aef5d7250635f
+size 4155480000

1080p_sr/model.safetensors.index.json

@@ -0,0 +1,338 @@
+{
+  "metadata": {
+    "total_size": 61197676608
+  },
+  "weight_map": {
+    "adapter.audio_embedder.bias": "model-00001-of-00013.safetensors",
+    "adapter.audio_embedder.weight": "model-00004-of-00013.safetensors",
+    "adapter.rope.bands": "model-00007-of-00013.safetensors",
+    "adapter.text_embedder.bias": "model-00002-of-00013.safetensors",
+    "adapter.text_embedder.weight": "model-00007-of-00013.safetensors",
+    "adapter.video_embedder.bias": "model-00009-of-00013.safetensors",
+    "adapter.video_embedder.weight": "model-00011-of-00013.safetensors",
+    "block.layers.0.attention.k_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.0.attention.linear_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.0.attention.linear_qkv.weight": "model-00003-of-00013.safetensors",
+    "block.layers.0.attention.pre_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.0.attention.q_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.0.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.0.mlp.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.0.mlp.up_gate_proj.weight": "model-00007-of-00013.safetensors",
+    "block.layers.1.attention.k_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.1.attention.linear_proj.weight": "model-00007-of-00013.safetensors",
+    "block.layers.1.attention.linear_qkv.weight": "model-00011-of-00013.safetensors",
+    "block.layers.1.attention.pre_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.1.attention.q_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.1.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "block.layers.1.mlp.pre_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.1.mlp.up_gate_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.10.attention.k_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.10.attention.linear_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.10.attention.linear_qkv.weight": "model-00008-of-00013.safetensors",
+    "block.layers.10.attention.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.10.attention.q_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.10.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.10.mlp.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.10.mlp.up_gate_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.11.attention.k_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.11.attention.linear_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.11.attention.linear_qkv.weight": "model-00012-of-00013.safetensors",
+    "block.layers.11.attention.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.11.attention.q_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.11.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.11.mlp.pre_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.11.mlp.up_gate_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.12.attention.k_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.12.attention.linear_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.12.attention.linear_qkv.weight": "model-00001-of-00013.safetensors",
+    "block.layers.12.attention.pre_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.12.attention.q_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.12.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.12.mlp.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.12.mlp.up_gate_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.13.attention.k_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.13.attention.linear_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.13.attention.linear_qkv.weight": "model-00010-of-00013.safetensors",
+    "block.layers.13.attention.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.13.attention.q_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.13.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.13.mlp.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.13.mlp.up_gate_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.14.attention.k_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.14.attention.linear_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.14.attention.linear_qkv.weight": "model-00012-of-00013.safetensors",
+    "block.layers.14.attention.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.14.attention.q_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.14.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.14.mlp.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.14.mlp.up_gate_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.15.attention.k_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.15.attention.linear_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.15.attention.linear_qkv.weight": "model-00001-of-00013.safetensors",
+    "block.layers.15.attention.pre_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.15.attention.q_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.15.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.15.mlp.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.15.mlp.up_gate_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.16.attention.k_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.16.attention.linear_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.16.attention.linear_qkv.weight": "model-00010-of-00013.safetensors",
+    "block.layers.16.attention.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.16.attention.q_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.16.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.16.mlp.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.16.mlp.up_gate_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.17.attention.k_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.17.attention.linear_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.17.attention.linear_qkv.weight": "model-00005-of-00013.safetensors",
+    "block.layers.17.attention.pre_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.17.attention.q_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.17.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.17.mlp.pre_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.17.mlp.up_gate_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.18.attention.k_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.18.attention.linear_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.18.attention.linear_qkv.weight": "model-00012-of-00013.safetensors",
+    "block.layers.18.attention.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.18.attention.q_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.18.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.18.mlp.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.18.mlp.up_gate_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.19.attention.k_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.19.attention.linear_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.19.attention.linear_qkv.weight": "model-00008-of-00013.safetensors",
+    "block.layers.19.attention.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.19.attention.q_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.19.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.19.mlp.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.19.mlp.up_gate_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.2.attention.k_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.2.attention.linear_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.2.attention.linear_qkv.weight": "model-00003-of-00013.safetensors",
+    "block.layers.2.attention.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.2.attention.q_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.2.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.2.mlp.pre_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.2.mlp.up_gate_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.20.attention.k_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.20.attention.linear_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.20.attention.linear_qkv.weight": "model-00010-of-00013.safetensors",
+    "block.layers.20.attention.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.20.attention.q_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.20.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.20.mlp.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.20.mlp.up_gate_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.21.attention.k_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.21.attention.linear_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.21.attention.linear_qkv.weight": "model-00004-of-00013.safetensors",
+    "block.layers.21.attention.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.21.attention.q_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.21.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.21.mlp.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.21.mlp.up_gate_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.22.attention.k_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.22.attention.linear_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.22.attention.linear_qkv.weight": "model-00002-of-00013.safetensors",
+    "block.layers.22.attention.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.22.attention.q_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.22.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.22.mlp.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.22.mlp.up_gate_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.23.attention.k_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.23.attention.linear_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.23.attention.linear_qkv.weight": "model-00006-of-00013.safetensors",
+    "block.layers.23.attention.pre_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.23.attention.q_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.23.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.23.mlp.pre_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.23.mlp.up_gate_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.24.attention.k_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.24.attention.linear_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.24.attention.linear_qkv.weight": "model-00012-of-00013.safetensors",
+    "block.layers.24.attention.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.24.attention.q_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.24.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.24.mlp.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.24.mlp.up_gate_proj.weight": "model-00013-of-00013.safetensors",
+    "block.layers.25.attention.k_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.25.attention.linear_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.25.attention.linear_qkv.weight": "model-00008-of-00013.safetensors",
+    "block.layers.25.attention.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.25.attention.q_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.25.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.25.mlp.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.25.mlp.up_gate_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.26.attention.k_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.26.attention.linear_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.26.attention.linear_qkv.weight": "model-00010-of-00013.safetensors",
+    "block.layers.26.attention.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.26.attention.q_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.26.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.26.mlp.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.26.mlp.up_gate_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.27.attention.k_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.27.attention.linear_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.27.attention.linear_qkv.weight": "model-00004-of-00013.safetensors",
+    "block.layers.27.attention.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.27.attention.q_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.27.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+    "block.layers.27.mlp.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.27.mlp.up_gate_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.28.attention.k_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.28.attention.linear_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.28.attention.linear_qkv.weight": "model-00002-of-00013.safetensors",
+    "block.layers.28.attention.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.28.attention.q_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.28.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.28.mlp.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.28.mlp.up_gate_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.29.attention.k_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.29.attention.linear_proj.weight": "model-00013-of-00013.safetensors",
+    "block.layers.29.attention.linear_qkv.weight": "model-00006-of-00013.safetensors",
+    "block.layers.29.attention.pre_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.29.attention.q_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.29.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.29.mlp.pre_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.29.mlp.up_gate_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.3.attention.k_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.3.attention.linear_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.3.attention.linear_qkv.weight": "model-00009-of-00013.safetensors",
+    "block.layers.3.attention.pre_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.3.attention.q_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.3.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.3.mlp.pre_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.3.mlp.up_gate_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.30.attention.k_norm.weight": "model-00013-of-00013.safetensors",
+    "block.layers.30.attention.linear_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.30.attention.linear_qkv.weight": "model-00013-of-00013.safetensors",
+    "block.layers.30.attention.pre_norm.weight": "model-00013-of-00013.safetensors",
+    "block.layers.30.attention.q_norm.weight": "model-00013-of-00013.safetensors",
+    "block.layers.30.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.30.mlp.pre_norm.weight": "model-00013-of-00013.safetensors",
+    "block.layers.30.mlp.up_gate_proj.weight": "model-00013-of-00013.safetensors",
+    "block.layers.31.attention.k_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.31.attention.linear_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.31.attention.linear_qkv.weight": "model-00008-of-00013.safetensors",
+    "block.layers.31.attention.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.31.attention.q_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.31.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.31.mlp.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.31.mlp.up_gate_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.32.attention.k_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.32.attention.linear_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.32.attention.linear_qkv.weight": "model-00011-of-00013.safetensors",
+    "block.layers.32.attention.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.32.attention.q_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.32.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.32.mlp.pre_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.32.mlp.up_gate_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.33.attention.k_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.33.attention.linear_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.33.attention.linear_qkv.weight": "model-00004-of-00013.safetensors",
+    "block.layers.33.attention.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.33.attention.q_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.33.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+    "block.layers.33.mlp.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.33.mlp.up_gate_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.34.attention.k_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.34.attention.linear_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.34.attention.linear_qkv.weight": "model-00002-of-00013.safetensors",
+    "block.layers.34.attention.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.34.attention.q_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.34.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.34.mlp.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.34.mlp.up_gate_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.35.attention.k_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.35.attention.linear_proj.weight": "model-00013-of-00013.safetensors",
+    "block.layers.35.attention.linear_qkv.weight": "model-00006-of-00013.safetensors",
+    "block.layers.35.attention.pre_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.35.attention.q_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.35.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.35.mlp.pre_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.35.mlp.up_gate_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.36.attention.k_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.36.attention.linear_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.36.attention.linear_qkv.weight": "model-00013-of-00013.safetensors",
+    "block.layers.36.attention.pre_norm.weight": "model-00013-of-00013.safetensors",
+    "block.layers.36.attention.q_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.36.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.36.mlp.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.36.mlp.up_gate_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.37.attention.k_norm.weight": "model-00013-of-00013.safetensors",
+    "block.layers.37.attention.linear_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.37.attention.linear_qkv.weight": "model-00002-of-00013.safetensors",
+    "block.layers.37.attention.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.37.attention.q_norm.weight": "model-00013-of-00013.safetensors",
+    "block.layers.37.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.37.mlp.pre_norm.weight": "model-00013-of-00013.safetensors",
+    "block.layers.37.mlp.up_gate_proj.weight": "model-00013-of-00013.safetensors",
+    "block.layers.38.attention.k_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.38.attention.linear_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.38.attention.linear_qkv.weight": "model-00009-of-00013.safetensors",
+    "block.layers.38.attention.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.38.attention.q_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.38.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.38.mlp.pre_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.38.mlp.up_gate_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.39.attention.k_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.39.attention.linear_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.39.attention.linear_qkv.weight": "model-00009-of-00013.safetensors",
+    "block.layers.39.attention.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.39.attention.q_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.39.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "block.layers.39.mlp.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.39.mlp.up_gate_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.4.attention.k_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.4.attention.linear_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.4.attention.linear_qkv.weight": "model-00007-of-00013.safetensors",
+    "block.layers.4.attention.pre_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.4.attention.q_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.4.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.4.mlp.pre_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.4.mlp.up_gate_proj.weight": "model-00007-of-00013.safetensors",
+    "block.layers.5.attention.k_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.5.attention.linear_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.5.attention.linear_qkv.weight": "model-00012-of-00013.safetensors",
+    "block.layers.5.attention.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.5.attention.q_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.5.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.5.mlp.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.5.mlp.up_gate_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.6.attention.k_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.6.attention.linear_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.6.attention.linear_qkv.weight": "model-00010-of-00013.safetensors",
+    "block.layers.6.attention.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.6.attention.q_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.6.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.6.mlp.pre_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.6.mlp.up_gate_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.7.attention.k_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.7.attention.linear_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.7.attention.linear_qkv.weight": "model-00012-of-00013.safetensors",
+    "block.layers.7.attention.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.7.attention.q_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.7.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.7.mlp.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.7.mlp.up_gate_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.8.attention.k_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.8.attention.linear_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.8.attention.linear_qkv.weight": "model-00010-of-00013.safetensors",
+    "block.layers.8.attention.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.8.attention.q_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.8.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.8.mlp.pre_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.8.mlp.up_gate_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.9.attention.k_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.9.attention.linear_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.9.attention.linear_qkv.weight": "model-00008-of-00013.safetensors",
+    "block.layers.9.attention.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.9.attention.q_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.9.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.9.mlp.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.9.mlp.up_gate_proj.weight": "model-00003-of-00013.safetensors",
+    "final_linear_audio.weight": "model-00004-of-00013.safetensors",
+    "final_linear_video.weight": "model-00004-of-00013.safetensors",
+    "final_norm_audio.weight": "model-00004-of-00013.safetensors",
+    "final_norm_video.weight": "model-00004-of-00013.safetensors"
+  }
+}

540p_sr/model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26df6656553627bb483a7058cd17a82c27e930be05e10fc09fd5075bb0491b4
+size 4920553248

540p_sr/model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2c12f0f0ef3bda55c895e27847b2aee6fa26f4b70d1bd19c6af80803f8b81a
+size 4520720320

540p_sr/model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1ae7b14e3f1b87277d8a48fd5886209fc3cb75553155e645987e560b20dfaf
+size 4924382952

540p_sr/model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9eb037df0801da8305b41b50d6c4dae2096e0345b99d68436b138f37451fbf5
+size 4897310104

540p_sr/model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c374d8ad7cddfce030f746538373701d195ed95f6ed83f0f4a19a2bc3de8b7
+size 4924382960

540p_sr/model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c17ce9f986fe59713eb0f8776b2ee2c0768fa722566d6559435668f497421b
+size 3507184032

540p_sr/model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e35800a677b124d21e148eaabac6337fdef61cd03469ae7bbcd32cba538606
+size 4542755784

540p_sr/model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f515f50518c7575c37f86e6ce1b411e85593c839101c61dc2d72f08835a41b99
+size 4680095328

540p_sr/model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a1885819d2fe338c220df39a635804312b1b6fdbaf2647766cb48cc7aadbf9
+size 4924382928

540p_sr/model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a989b9f2ce83d29692e987031e037272df8631c86a0808ccfc19446e4a3c80
+size 4897310104

540p_sr/model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a441cf8dfed32bcf93c70906c6347ff0652e811e4940bd918965cc0ffea7b010
+size 4924382960

540p_sr/model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6e50ce6b107ce539c354282408ed76242ce0915c48548f39bbf430ff2f8629
+size 4582800304

540p_sr/model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ae1d349df3320bc2a51c30e0d48cf1d72cda2109cde51f00ef738fe57c8d5e
+size 4951453752

540p_sr/model.safetensors.index.json

@@ -0,0 +1,338 @@
+{
+  "metadata": {
+    "total_size": 61197676608
+  },
+  "weight_map": {
+    "adapter.audio_embedder.bias": "model-00007-of-00013.safetensors",
+    "adapter.audio_embedder.weight": "model-00007-of-00013.safetensors",
+    "adapter.rope.bands": "model-00007-of-00013.safetensors",
+    "adapter.text_embedder.bias": "model-00007-of-00013.safetensors",
+    "adapter.text_embedder.weight": "model-00001-of-00013.safetensors",
+    "adapter.video_embedder.bias": "model-00001-of-00013.safetensors",
+    "adapter.video_embedder.weight": "model-00007-of-00013.safetensors",
+    "block.layers.0.attention.k_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.0.attention.linear_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.0.attention.linear_qkv.weight": "model-00007-of-00013.safetensors",
+    "block.layers.0.attention.pre_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.0.attention.q_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.0.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "block.layers.0.mlp.pre_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.0.mlp.up_gate_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.1.attention.k_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.1.attention.linear_proj.weight": "model-00007-of-00013.safetensors",
+    "block.layers.1.attention.linear_qkv.weight": "model-00001-of-00013.safetensors",
+    "block.layers.1.attention.pre_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.1.attention.q_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.1.mlp.pre_norm.weight": "model-00007-of-00013.safetensors",
+    "block.layers.1.mlp.up_gate_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.10.attention.k_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.10.attention.linear_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.10.attention.linear_qkv.weight": "model-00009-of-00013.safetensors",
+    "block.layers.10.attention.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.10.attention.q_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.10.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.10.mlp.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.10.mlp.up_gate_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.11.attention.k_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.11.attention.linear_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.11.attention.linear_qkv.weight": "model-00003-of-00013.safetensors",
+    "block.layers.11.attention.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.11.attention.q_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.11.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.11.mlp.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.11.mlp.up_gate_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.12.attention.k_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.12.attention.linear_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.12.attention.linear_qkv.weight": "model-00009-of-00013.safetensors",
+    "block.layers.12.attention.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.12.attention.q_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.12.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.12.mlp.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.12.mlp.up_gate_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.13.attention.k_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.13.attention.linear_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.13.attention.linear_qkv.weight": "model-00003-of-00013.safetensors",
+    "block.layers.13.attention.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.13.attention.q_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.13.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.13.mlp.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.13.mlp.up_gate_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.14.attention.k_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.14.attention.linear_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.14.attention.linear_qkv.weight": "model-00010-of-00013.safetensors",
+    "block.layers.14.attention.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.14.attention.q_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.14.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.14.mlp.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.14.mlp.up_gate_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.15.attention.k_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.15.attention.linear_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.15.attention.linear_qkv.weight": "model-00003-of-00013.safetensors",
+    "block.layers.15.attention.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.15.attention.q_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.15.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.15.mlp.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.15.mlp.up_gate_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.16.attention.k_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.16.attention.linear_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.16.attention.linear_qkv.weight": "model-00010-of-00013.safetensors",
+    "block.layers.16.attention.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.16.attention.q_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.16.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.16.mlp.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.16.mlp.up_gate_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.17.attention.k_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.17.attention.linear_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.17.attention.linear_qkv.weight": "model-00003-of-00013.safetensors",
+    "block.layers.17.attention.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.17.attention.q_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.17.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.17.mlp.pre_norm.weight": "model-00003-of-00013.safetensors",
+    "block.layers.17.mlp.up_gate_proj.weight": "model-00003-of-00013.safetensors",
+    "block.layers.18.attention.k_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.18.attention.linear_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.18.attention.linear_qkv.weight": "model-00010-of-00013.safetensors",
+    "block.layers.18.attention.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.18.attention.q_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.18.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.18.mlp.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.18.mlp.up_gate_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.19.attention.k_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.19.attention.linear_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.19.attention.linear_qkv.weight": "model-00004-of-00013.safetensors",
+    "block.layers.19.attention.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.19.attention.q_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.19.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.19.mlp.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.19.mlp.up_gate_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.2.attention.k_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.2.attention.linear_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.2.attention.linear_qkv.weight": "model-00008-of-00013.safetensors",
+    "block.layers.2.attention.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.2.attention.q_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.2.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.2.mlp.pre_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.2.mlp.up_gate_proj.weight": "model-00001-of-00013.safetensors",
+    "block.layers.20.attention.k_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.20.attention.linear_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.20.attention.linear_qkv.weight": "model-00010-of-00013.safetensors",
+    "block.layers.20.attention.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.20.attention.q_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.20.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.20.mlp.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.20.mlp.up_gate_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.21.attention.k_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.21.attention.linear_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.21.attention.linear_qkv.weight": "model-00004-of-00013.safetensors",
+    "block.layers.21.attention.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.21.attention.q_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.21.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.21.mlp.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.21.mlp.up_gate_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.22.attention.k_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.22.attention.linear_proj.weight": "model-00010-of-00013.safetensors",
+    "block.layers.22.attention.linear_qkv.weight": "model-00010-of-00013.safetensors",
+    "block.layers.22.attention.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.22.attention.q_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.22.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.22.mlp.pre_norm.weight": "model-00010-of-00013.safetensors",
+    "block.layers.22.mlp.up_gate_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.23.attention.k_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.23.attention.linear_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.23.attention.linear_qkv.weight": "model-00004-of-00013.safetensors",
+    "block.layers.23.attention.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.23.attention.q_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.23.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.23.mlp.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.23.mlp.up_gate_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.24.attention.k_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.24.attention.linear_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.24.attention.linear_qkv.weight": "model-00011-of-00013.safetensors",
+    "block.layers.24.attention.pre_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.24.attention.q_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.24.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.24.mlp.pre_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.24.mlp.up_gate_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.25.attention.k_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.25.attention.linear_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.25.attention.linear_qkv.weight": "model-00004-of-00013.safetensors",
+    "block.layers.25.attention.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.25.attention.q_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.25.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.25.mlp.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.25.mlp.up_gate_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.26.attention.k_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.26.attention.linear_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.26.attention.linear_qkv.weight": "model-00011-of-00013.safetensors",
+    "block.layers.26.attention.pre_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.26.attention.q_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.26.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.26.mlp.pre_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.26.mlp.up_gate_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.27.attention.k_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.27.attention.linear_proj.weight": "model-00004-of-00013.safetensors",
+    "block.layers.27.attention.linear_qkv.weight": "model-00004-of-00013.safetensors",
+    "block.layers.27.attention.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.27.attention.q_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.27.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.27.mlp.pre_norm.weight": "model-00004-of-00013.safetensors",
+    "block.layers.27.mlp.up_gate_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.28.attention.k_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.28.attention.linear_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.28.attention.linear_qkv.weight": "model-00011-of-00013.safetensors",
+    "block.layers.28.attention.pre_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.28.attention.q_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.28.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.28.mlp.pre_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.28.mlp.up_gate_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.29.attention.k_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.29.attention.linear_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.29.attention.linear_qkv.weight": "model-00005-of-00013.safetensors",
+    "block.layers.29.attention.pre_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.29.attention.q_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.29.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.29.mlp.pre_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.29.mlp.up_gate_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.3.attention.k_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.3.attention.linear_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.3.attention.linear_qkv.weight": "model-00002-of-00013.safetensors",
+    "block.layers.3.attention.pre_norm.weight": "model-00001-of-00013.safetensors",
+    "block.layers.3.attention.q_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.3.mlp.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.3.mlp.up_gate_proj.weight": "model-00008-of-00013.safetensors",
+    "block.layers.30.attention.k_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.30.attention.linear_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.30.attention.linear_qkv.weight": "model-00011-of-00013.safetensors",
+    "block.layers.30.attention.pre_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.30.attention.q_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.30.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.30.mlp.pre_norm.weight": "model-00011-of-00013.safetensors",
+    "block.layers.30.mlp.up_gate_proj.weight": "model-00011-of-00013.safetensors",
+    "block.layers.31.attention.k_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.31.attention.linear_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.31.attention.linear_qkv.weight": "model-00005-of-00013.safetensors",
+    "block.layers.31.attention.pre_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.31.attention.q_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.31.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.31.mlp.pre_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.31.mlp.up_gate_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.32.attention.k_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.32.attention.linear_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.32.attention.linear_qkv.weight": "model-00012-of-00013.safetensors",
+    "block.layers.32.attention.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.32.attention.q_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.32.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.32.mlp.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.32.mlp.up_gate_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.33.attention.k_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.33.attention.linear_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.33.attention.linear_qkv.weight": "model-00005-of-00013.safetensors",
+    "block.layers.33.attention.pre_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.33.attention.q_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.33.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.33.mlp.pre_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.33.mlp.up_gate_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.34.attention.k_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.34.attention.linear_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.34.attention.linear_qkv.weight": "model-00012-of-00013.safetensors",
+    "block.layers.34.attention.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.34.attention.q_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.34.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.34.mlp.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.34.mlp.up_gate_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.35.attention.k_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.35.attention.linear_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.35.attention.linear_qkv.weight": "model-00005-of-00013.safetensors",
+    "block.layers.35.attention.pre_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.35.attention.q_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.35.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.35.mlp.pre_norm.weight": "model-00005-of-00013.safetensors",
+    "block.layers.35.mlp.up_gate_proj.weight": "model-00005-of-00013.safetensors",
+    "block.layers.36.attention.k_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.36.attention.linear_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.36.attention.linear_qkv.weight": "model-00012-of-00013.safetensors",
+    "block.layers.36.attention.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.36.attention.q_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.36.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.36.mlp.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.36.mlp.up_gate_proj.weight": "model-00012-of-00013.safetensors",
+    "block.layers.37.attention.k_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.37.attention.linear_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.37.attention.linear_qkv.weight": "model-00006-of-00013.safetensors",
+    "block.layers.37.attention.pre_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.37.attention.q_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.37.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.37.mlp.pre_norm.weight": "model-00012-of-00013.safetensors",
+    "block.layers.37.mlp.up_gate_proj.weight": "model-00013-of-00013.safetensors",
+    "block.layers.38.attention.k_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.38.attention.linear_proj.weight": "model-00006-of-00013.safetensors",
+    "block.layers.38.attention.linear_qkv.weight": "model-00006-of-00013.safetensors",
+    "block.layers.38.attention.pre_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.38.attention.q_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.38.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+    "block.layers.38.mlp.pre_norm.weight": "model-00006-of-00013.safetensors",
+    "block.layers.38.mlp.up_gate_proj.weight": "model-00007-of-00013.safetensors",
+    "block.layers.39.attention.k_norm.weight": "model-00013-of-00013.safetensors",
+    "block.layers.39.attention.linear_proj.weight": "model-00013-of-00013.safetensors",
+    "block.layers.39.attention.linear_qkv.weight": "model-00013-of-00013.safetensors",
+    "block.layers.39.attention.pre_norm.weight": "model-00013-of-00013.safetensors",
+    "block.layers.39.attention.q_norm.weight": "model-00013-of-00013.safetensors",
+    "block.layers.39.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "block.layers.39.mlp.pre_norm.weight": "model-00013-of-00013.safetensors",
+    "block.layers.39.mlp.up_gate_proj.weight": "model-00013-of-00013.safetensors",
+    "block.layers.4.attention.k_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.4.attention.linear_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.4.attention.linear_qkv.weight": "model-00008-of-00013.safetensors",
+    "block.layers.4.attention.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.4.attention.q_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.4.mlp.pre_norm.weight": "model-00008-of-00013.safetensors",
+    "block.layers.4.mlp.up_gate_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.5.attention.k_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.5.attention.linear_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.5.attention.linear_qkv.weight": "model-00002-of-00013.safetensors",
+    "block.layers.5.attention.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.5.attention.q_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.5.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.5.mlp.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.5.mlp.up_gate_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.6.attention.k_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.6.attention.linear_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.6.attention.linear_qkv.weight": "model-00009-of-00013.safetensors",
+    "block.layers.6.attention.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.6.attention.q_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.6.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.6.mlp.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.6.mlp.up_gate_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.7.attention.k_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.7.attention.linear_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.7.attention.linear_qkv.weight": "model-00002-of-00013.safetensors",
+    "block.layers.7.attention.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.7.attention.q_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.7.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.7.mlp.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.7.mlp.up_gate_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.8.attention.k_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.8.attention.linear_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.8.attention.linear_qkv.weight": "model-00009-of-00013.safetensors",
+    "block.layers.8.attention.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.8.attention.q_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.8.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.8.mlp.pre_norm.weight": "model-00009-of-00013.safetensors",
+    "block.layers.8.mlp.up_gate_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.9.attention.k_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.9.attention.linear_proj.weight": "model-00002-of-00013.safetensors",
+    "block.layers.9.attention.linear_qkv.weight": "model-00002-of-00013.safetensors",
+    "block.layers.9.attention.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.9.attention.q_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.9.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "block.layers.9.mlp.pre_norm.weight": "model-00002-of-00013.safetensors",
+    "block.layers.9.mlp.up_gate_proj.weight": "model-00003-of-00013.safetensors",
+    "final_linear_audio.weight": "model-00007-of-00013.safetensors",
+    "final_linear_video.weight": "model-00007-of-00013.safetensors",
+    "final_norm_audio.weight": "model-00007-of-00013.safetensors",
+    "final_norm_video.weight": "model-00007-of-00013.safetensors"
+  }
+}

README.md

@@ -0,0 +1,197 @@
+---
+license: apache-2.0
+language:
+  - en
+  - zh
+  - ja
+  - ko
+  - de
+  - fr
+  - yue
+pipeline_tag: image-to-video
+tags:
+  - text-to-video
+  - image-text-to-video
+  - text-to-audio
+  - text-to-audio-video
+  - image-to-audio-video
+  - image-text-to-audio-video
+  - multimodal
+---
+
+<div align="center">
+
+# daVinci-MagiHuman
+
+### Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model
+
+This repository contains the weights for **daVinci-MagiHuman**, introduced in the [paper](https://huggingface.co/papers/2603.21986).
+
+<p align="center Visitor">
+  <a href="https://plms.ai">SII-GAIR</a> &nbsp;&amp;&nbsp; <a href="https://sand.ai">Sand.ai</a>
+</p>
+
+[![GitHub](https://img.shields.io/badge/GitHub-Repo-black?logo=github)](https://github.com/GAIR-NLP/daVinci-MagiHuman)
+[![Paper](https://img.shields.io/badge/Paper-PDF-red)](https://arxiv.org/abs/2603.21986)
+[![Demo](https://img.shields.io/badge/%F0%9F%A4%97%20Demo-HuggingFace-orange)](https://huggingface.co/spaces/SII-GAIR/daVinci-MagiHuman)
+[![Models](https://img.shields.io/badge/%F0%9F%A4%97%20Models-HuggingFace-yellow)](https://huggingface.co/GAIR/daVinci-MagiHuman)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Python](https://img.shields.io/badge/Python-3.12%2B-blue.svg)](https://www.python.org/)
+[![PyTorch](https://img.shields.io/badge/PyTorch-2.9%2B-ee4c2c.svg)](https://pytorch.org/)
+
+</div>
+
+## Highlights
+
+- **Single-Stream Transformer** — A unified 15B-parameter, 40-layer Transformer that jointly processes text, video, and audio via self-attention only. No cross-attention, no multi-stream complexity.
+- **Exceptional Human-Centric Quality** — Expressive facial performance, natural speech-expression coordination, realistic body motion, and accurate audio-video synchronization.
+- **Multilingual** — Supports Chinese (Mandarin & Cantonese), English, Japanese, Korean, German, and French.
+- **Blazing Fast Inference** — Generates a 5-second 256p video in **2 seconds** and a 5-second 1080p video in **38 seconds** on a single H100 GPU.
+- **State-of-the-Art Results** — Achieves **80.0%** win rate vs Ovi 1.1 and **60.9%** vs LTX 2.3 in pairwise human evaluation over 2,000 comparisons.
+- **Fully Open Source** — We release the complete model stack: base model, distilled model, super-resolution model, and inference code.
+
+## Architecture
+
+<div align="center">
+<img src="architecture.png" width="90%">
+</div>
+
+daVinci-MagiHuman uses a single-stream Transformer that takes text tokens, a reference image latent, and noisy video and audio tokens as input, and jointly denoises the video and audio within a unified token sequence.
+
+Key design choices:
+
+| Component | Description |
+|---|---|
+| **Sandwich Architecture** | First and last 4 layers use modality-specific projections; middle 32 layers share parameters across modalities |
+| **Timestep-Free Denoising** | No explicit timestep embeddings — the model infers the denoising state directly from input latents |
+| **Per-Head Gating** | Learned scalar gates with sigmoid activation on each attention head for training stability |
+| **Unified Conditioning** | Denoising and reference signals handled through a minimal unified interface — no dedicated conditioning branches |
+
+## Performance
+
+### Quantitative Quality Benchmark
+
+| Model | Visual Quality ↑ | Text Alignment ↑ | Physical Consistency ↑ | WER ↓ |
+|---|:---:|:---:|:---:|:---:|
+| OVI 1.1 | 4.73 | 4.10 | 4.41 | 40.45% |
+| LTX 2.3 | 4.76 | 4.12 | **4.56** | 19.23% |
+| **daVinci-MagiHuman** | **4.80** | **4.18** | 4.52 | **14.60%** |
+
+### Human Evaluation (2,000 Pairwise Comparisons)
+
+| Matchup | daVinci-MagiHuman Win | Tie | Opponent Win |
+|---|:---:|:---:|:---:|
+| vs Ovi 1.1 | **80.0%** | 8.2% | 11.8% |
+| vs LTX 2.3 | **60.9%** | 17.2% | 21.9% |
+
+### Inference Speed (5-second video)
+
+| Resolution | Base (s) | Super-Res (s) | Decode (s) | **Total (s)** |
+|---|:---:|:---:|:---:|:---:|
+| 256p | 1.6 | — | 0.4 | **2.0** |
+| 540p | 1.6 | 5.1 | 1.3 | **8.0** |
+| 1080p | 1.6 | 31.0 | 5.8 | **38.4** |
+
+## Efficient Inference Techniques
+
+- **Latent-Space Super-Resolution** — Two-stage pipeline: generate at low resolution, then refine in latent space (not pixel space), avoiding an extra VAE decode-encode round trip.
+- **Turbo VAE Decoder** — A lightweight re-trained decoder that substantially reduces decoding overhead.
+- **Full-Graph Compilation** — [MagiCompiler](https://github.com/SandAI-org/MagiCompiler) fuses operators across Transformer layers for ~1.2x speedup.
+- **Distillation** — DMD-2 distillation enables generation with only 8 denoising steps (no CFG), without sacrificing quality.
+
+## Getting Started
+
+### Option 1: Docker (Recommended)
+
+```bash
+# Pull the MagiCompiler Docker image
+docker pull sandai/magi-compiler:latest
+
+# Launch container
+docker run -it --gpus all \
+  -v /path/to/models:/models \
+  sandai/magi-compiler:latest bash
+
+# Install MagiCompiler
+git clone https://github.com/SandAI-org/MagiCompiler
+cd MagiCompiler
+pip install -e . --no-build-isolation --config-settings editable_mode=compat
+cd ..
+
+# Clone daVinci-MagiHuman
+git clone https://github.com/GAIR-NLP/daVinci-MagiHuman
+cd daVinci-MagiHuman
+```
+
+### Option 2: Conda
+
+```bash
+# Create environment
+conda create -n davinci python=3.12
+conda activate davinci
+
+# Install PyTorch
+pip install torch==2.9.0 torchvision==0.24.0 torchaudio==2.9.0
+
+# Install Flash Attention (Hopper)
+git clone https://github.com/Dao-AILab/flash-attention
+cd flash-attention/hopper && python setup.py install && cd ../..
+
+# Install MagiCompiler
+git clone https://github.com/SandAI-org/MagiCompiler
+cd MagiCompiler
+pip install -e . --no-build-isolation --config-settings editable_mode=compat
+cd ..
+
+# Clone and install daVinci-MagiHuman
+git clone https://github.com/GAIR-NLP/daVinci-MagiHuman
+cd daVinci-MagiHuman
+pip install -r requirements.txt
+```
+
+### Download Model Checkpoints
+
+Download the complete model stack from [HuggingFace](https://huggingface.co/GAIR/daVinci-MagiHuman) and update the paths in the config files under `example/`.
+
+## Usage
+
+Before running, update the checkpoint paths in the config files (`example/*/config.json`) to point to your local model directory.
+
+**Base Model (256p)**
+```bash
+bash example/base/run.sh
+```
+
+**Distilled Model (256p, 8 steps, no CFG)**
+```bash
+bash example/distill/run.sh
+```
+
+**Super-Resolution to 540p**
+```bash
+bash example/sr_540p/run.sh
+```
+
+**Super-Resolution to 1080p**
+```bash
+bash example/sr_1080p/run.sh
+```
+
+## Acknowledgements
+
+We thank the open-source community, and in particular [Wan2.2](https://github.com/Wan-Video/Wan2.2) and [Turbo-VAED](https://github.com/hustvl/Turbo-VAED), for their valuable contributions.
+
+## License
+
+This project is released under the [Apache License 2.0](https://opensource.org/licenses/Apache-2.0).
+
+## Citation
+
+```bibtex
+@misc{davinci-magihuman-2026,
+  title   = {Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model},
+  author  = {SII-GAIR and Sand.ai},
+  year    = {2026},
+  url     = {https://github.com/GAIR-NLP/daVinci-MagiHuman}
+}
+```

base/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a960919effe1ca65d3d4d3939feee4af3d272b3acc155da432551741fc769c73
+size 4798025672

base/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa22eb2f724ea69c367694acd232258693637a1bf9cd03a561608f10c32dafa
+size 4777051960

base/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5b6feb177f6cf71906ed05a256bfe8f0cd8a4b2a67414d99fe5bd4578801d2
+size 4998672920

base/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb7d5cdb61d0636045afb83e13b9bd8b6a6289046c1b448918cca56928c35ab
+size 4737735064

base/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652b2e12b9cc8686b04264d34945f32e659769ad1eb243121eacf7bf15c15d55
+size 4971519728

base/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c194b6f0b53ab17ba235808f4d40ab1172c7f89655eb547173f701e1763773ec
+size 4554972288

base/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e9dddc6c00dd173977e47637787392ad48e7478c5e397dbd6489b33bbe5d63c
+size 1804067488

base/model.safetensors.index.json

@@ -0,0 +1,338 @@
+{
+  "metadata": {
+    "total_size": 30642008128
+  },
+  "weight_map": {
+    "adapter.audio_embedder.bias": "model-00001-of-00007.safetensors",
+    "adapter.audio_embedder.weight": "model-00004-of-00007.safetensors",
+    "adapter.rope.bands": "model-00006-of-00007.safetensors",
+    "adapter.text_embedder.bias": "model-00001-of-00007.safetensors",
+    "adapter.text_embedder.weight": "model-00001-of-00007.safetensors",
+    "adapter.video_embedder.bias": "model-00002-of-00007.safetensors",
+    "adapter.video_embedder.weight": "model-00005-of-00007.safetensors",
+    "block.layers.0.attention.k_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.0.attention.linear_proj.weight": "model-00007-of-00007.safetensors",
+    "block.layers.0.attention.linear_qkv.weight": "model-00002-of-00007.safetensors",
+    "block.layers.0.attention.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.0.attention.q_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.0.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.0.mlp.pre_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.0.mlp.up_gate_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.1.attention.k_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.1.attention.linear_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.1.attention.linear_qkv.weight": "model-00005-of-00007.safetensors",
+    "block.layers.1.attention.pre_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.1.attention.q_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.1.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.1.mlp.pre_norm.weight": "model-00007-of-00007.safetensors",
+    "block.layers.1.mlp.up_gate_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.10.attention.k_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.10.attention.linear_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.10.attention.linear_qkv.weight": "model-00002-of-00007.safetensors",
+    "block.layers.10.attention.pre_norm.weight": "model-00007-of-00007.safetensors",
+    "block.layers.10.attention.q_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.10.mlp.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.10.mlp.up_gate_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.11.attention.k_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.11.attention.linear_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.11.attention.linear_qkv.weight": "model-00002-of-00007.safetensors",
+    "block.layers.11.attention.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.11.attention.q_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.11.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.11.mlp.pre_norm.weight": "model-00007-of-00007.safetensors",
+    "block.layers.11.mlp.up_gate_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.12.attention.k_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.12.attention.linear_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.12.attention.linear_qkv.weight": "model-00005-of-00007.safetensors",
+    "block.layers.12.attention.pre_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.12.attention.q_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.12.mlp.pre_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.12.mlp.up_gate_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.13.attention.k_norm.weight": "model-00007-of-00007.safetensors",
+    "block.layers.13.attention.linear_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.13.attention.linear_qkv.weight": "model-00004-of-00007.safetensors",
+    "block.layers.13.attention.pre_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.13.attention.q_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.13.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.13.mlp.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.13.mlp.up_gate_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.14.attention.k_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.14.attention.linear_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.14.attention.linear_qkv.weight": "model-00005-of-00007.safetensors",
+    "block.layers.14.attention.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.14.attention.q_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.14.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "block.layers.14.mlp.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.14.mlp.up_gate_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.15.attention.k_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.15.attention.linear_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.15.attention.linear_qkv.weight": "model-00005-of-00007.safetensors",
+    "block.layers.15.attention.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.15.attention.q_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.15.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.15.mlp.pre_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.15.mlp.up_gate_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.16.attention.k_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.16.attention.linear_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.16.attention.linear_qkv.weight": "model-00003-of-00007.safetensors",
+    "block.layers.16.attention.pre_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.16.attention.q_norm.weight": "model-00007-of-00007.safetensors",
+    "block.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.16.mlp.pre_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.16.mlp.up_gate_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.17.attention.k_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.17.attention.linear_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.17.attention.linear_qkv.weight": "model-00001-of-00007.safetensors",
+    "block.layers.17.attention.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.17.attention.q_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.17.mlp.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.17.mlp.up_gate_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.18.attention.k_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.18.attention.linear_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.18.attention.linear_qkv.weight": "model-00005-of-00007.safetensors",
+    "block.layers.18.attention.pre_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.18.attention.q_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.18.mlp.pre_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.18.mlp.up_gate_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.19.attention.k_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.19.attention.linear_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.19.attention.linear_qkv.weight": "model-00005-of-00007.safetensors",
+    "block.layers.19.attention.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.19.attention.q_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.19.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.19.mlp.pre_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.19.mlp.up_gate_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.2.attention.k_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.2.attention.linear_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.2.attention.linear_qkv.weight": "model-00004-of-00007.safetensors",
+    "block.layers.2.attention.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.2.attention.q_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.2.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.2.mlp.pre_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.2.mlp.up_gate_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.20.attention.k_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.20.attention.linear_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.20.attention.linear_qkv.weight": "model-00002-of-00007.safetensors",
+    "block.layers.20.attention.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.20.attention.q_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.20.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.20.mlp.pre_norm.weight": "model-00007-of-00007.safetensors",
+    "block.layers.20.mlp.up_gate_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.21.attention.k_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.21.attention.linear_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.21.attention.linear_qkv.weight": "model-00002-of-00007.safetensors",
+    "block.layers.21.attention.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.21.attention.q_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.21.mlp.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.21.mlp.up_gate_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.22.attention.k_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.22.attention.linear_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.22.attention.linear_qkv.weight": "model-00001-of-00007.safetensors",
+    "block.layers.22.attention.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.22.attention.q_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.22.mlp.pre_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.22.mlp.up_gate_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.23.attention.k_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.23.attention.linear_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.23.attention.linear_qkv.weight": "model-00007-of-00007.safetensors",
+    "block.layers.23.attention.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.23.attention.q_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.23.mlp.pre_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.23.mlp.up_gate_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.24.attention.k_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.24.attention.linear_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.24.attention.linear_qkv.weight": "model-00006-of-00007.safetensors",
+    "block.layers.24.attention.pre_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.24.attention.q_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.24.mlp.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.24.mlp.up_gate_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.25.attention.k_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.25.attention.linear_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.25.attention.linear_qkv.weight": "model-00001-of-00007.safetensors",
+    "block.layers.25.attention.pre_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.25.attention.q_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.25.mlp.pre_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.25.mlp.up_gate_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.26.attention.k_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.26.attention.linear_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.26.attention.linear_qkv.weight": "model-00005-of-00007.safetensors",
+    "block.layers.26.attention.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.26.attention.q_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.26.mlp.pre_norm.weight": "model-00007-of-00007.safetensors",
+    "block.layers.26.mlp.up_gate_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.27.attention.k_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.27.attention.linear_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.27.attention.linear_qkv.weight": "model-00003-of-00007.safetensors",
+    "block.layers.27.attention.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.27.attention.q_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.27.mlp.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.27.mlp.up_gate_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.28.attention.k_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.28.attention.linear_proj.weight": "model-00007-of-00007.safetensors",
+    "block.layers.28.attention.linear_qkv.weight": "model-00003-of-00007.safetensors",
+    "block.layers.28.attention.pre_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.28.attention.q_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.28.mlp.pre_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.28.mlp.up_gate_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.29.attention.k_norm.weight": "model-00007-of-00007.safetensors",
+    "block.layers.29.attention.linear_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.29.attention.linear_qkv.weight": "model-00003-of-00007.safetensors",
+    "block.layers.29.attention.pre_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.29.attention.q_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.29.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.29.mlp.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.29.mlp.up_gate_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.3.attention.k_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.3.attention.linear_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.3.attention.linear_qkv.weight": "model-00004-of-00007.safetensors",
+    "block.layers.3.attention.pre_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.3.attention.q_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.3.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "block.layers.3.mlp.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.3.mlp.up_gate_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.30.attention.k_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.30.attention.linear_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.30.attention.linear_qkv.weight": "model-00004-of-00007.safetensors",
+    "block.layers.30.attention.pre_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.30.attention.q_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.30.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.30.mlp.pre_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.30.mlp.up_gate_proj.weight": "model-00007-of-00007.safetensors",
+    "block.layers.31.attention.k_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.31.attention.linear_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.31.attention.linear_qkv.weight": "model-00001-of-00007.safetensors",
+    "block.layers.31.attention.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.31.attention.q_norm.weight": "model-00007-of-00007.safetensors",
+    "block.layers.31.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.31.mlp.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.31.mlp.up_gate_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.32.attention.k_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.32.attention.linear_proj.weight": "model-00007-of-00007.safetensors",
+    "block.layers.32.attention.linear_qkv.weight": "model-00006-of-00007.safetensors",
+    "block.layers.32.attention.pre_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.32.attention.q_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.32.mlp.pre_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.32.mlp.up_gate_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.33.attention.k_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.33.attention.linear_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.33.attention.linear_qkv.weight": "model-00006-of-00007.safetensors",
+    "block.layers.33.attention.pre_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.33.attention.q_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.33.mlp.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.33.mlp.up_gate_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.34.attention.k_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.34.attention.linear_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.34.attention.linear_qkv.weight": "model-00002-of-00007.safetensors",
+    "block.layers.34.attention.pre_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.34.attention.q_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.34.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.34.mlp.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.34.mlp.up_gate_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.35.attention.k_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.35.attention.linear_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.35.attention.linear_qkv.weight": "model-00003-of-00007.safetensors",
+    "block.layers.35.attention.pre_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.35.attention.q_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.35.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.35.mlp.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.35.mlp.up_gate_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.36.attention.k_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.36.attention.linear_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.36.attention.linear_qkv.weight": "model-00002-of-00007.safetensors",
+    "block.layers.36.attention.pre_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.36.attention.q_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.36.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "block.layers.36.mlp.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.36.mlp.up_gate_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.37.attention.k_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.37.attention.linear_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.37.attention.linear_qkv.weight": "model-00002-of-00007.safetensors",
+    "block.layers.37.attention.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.37.attention.q_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.37.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.37.mlp.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.37.mlp.up_gate_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.38.attention.k_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.38.attention.linear_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.38.attention.linear_qkv.weight": "model-00006-of-00007.safetensors",
+    "block.layers.38.attention.pre_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.38.attention.q_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.38.mlp.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.38.mlp.up_gate_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.39.attention.k_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.39.attention.linear_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.39.attention.linear_qkv.weight": "model-00003-of-00007.safetensors",
+    "block.layers.39.attention.pre_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.39.attention.q_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.39.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.39.mlp.pre_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.39.mlp.up_gate_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.4.attention.k_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.4.attention.linear_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.4.attention.linear_qkv.weight": "model-00001-of-00007.safetensors",
+    "block.layers.4.attention.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.4.attention.q_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.4.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.4.mlp.pre_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.4.mlp.up_gate_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.5.attention.k_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.5.attention.linear_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.5.attention.linear_qkv.weight": "model-00006-of-00007.safetensors",
+    "block.layers.5.attention.pre_norm.weight": "model-00002-of-00007.safetensors",
+    "block.layers.5.attention.q_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.5.mlp.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.5.mlp.up_gate_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.6.attention.k_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.6.attention.linear_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.6.attention.linear_qkv.weight": "model-00005-of-00007.safetensors",
+    "block.layers.6.attention.pre_norm.weight": "model-00007-of-00007.safetensors",
+    "block.layers.6.attention.q_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "block.layers.6.mlp.pre_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.6.mlp.up_gate_proj.weight": "model-00001-of-00007.safetensors",
+    "block.layers.7.attention.k_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.7.attention.linear_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.7.attention.linear_qkv.weight": "model-00004-of-00007.safetensors",
+    "block.layers.7.attention.pre_norm.weight": "model-00006-of-00007.safetensors",
+    "block.layers.7.attention.q_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.7.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "block.layers.7.mlp.pre_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.7.mlp.up_gate_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.8.attention.k_norm.weight": "model-00003-of-00007.safetensors",
+    "block.layers.8.attention.linear_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.8.attention.linear_qkv.weight": "model-00002-of-00007.safetensors",
+    "block.layers.8.attention.pre_norm.weight": "model-00004-of-00007.safetensors",
+    "block.layers.8.attention.q_norm.weight": "model-00007-of-00007.safetensors",
+    "block.layers.8.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "block.layers.8.mlp.pre_norm.weight": "model-00005-of-00007.safetensors",
+    "block.layers.8.mlp.up_gate_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.9.attention.k_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.9.attention.linear_proj.weight": "model-00004-of-00007.safetensors",
+    "block.layers.9.attention.linear_qkv.weight": "model-00003-of-00007.safetensors",
+    "block.layers.9.attention.pre_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.9.attention.q_norm.weight": "model-00001-of-00007.safetensors",
+    "block.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "block.layers.9.mlp.pre_norm.weight": "model-00007-of-00007.safetensors",
+    "block.layers.9.mlp.up_gate_proj.weight": "model-00004-of-00007.safetensors",
+    "final_linear_audio.weight": "model-00006-of-00007.safetensors",
+    "final_linear_video.weight": "model-00001-of-00007.safetensors",
+    "final_norm_audio.weight": "model-00003-of-00007.safetensors",
+    "final_norm_video.weight": "model-00002-of-00007.safetensors"
+  }
+}

config.json

@@ -0,0 +1 @@
+{}

distill/model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db62d550ae1cd3314387aaa725a2b4326d01accd102dccabfad8e3ed7b55c95
+size 4110405792

distill/model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e320703d8301f09c17af1b9e925ae28e9563d4c276bb3adee4666f1fa6694c
+size 4532432944

distill/model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e73a407ac6382c4d82c9c452bf7a8cff4745cad64b0b486b7e22eecf611abd12
+size 4784953040

distill/model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03463b72b0ddcdc6de8953262950a74cf26d3cd449ac7ea0a1c5f10d970e14c1
+size 4924382928

distill/model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd26c288a679e7d0e7a8d5ed78d77e7a614beba8eaeb385758c877024b6432ea
+size 4897310080

distill/model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c79a8869485133b6f874d0eb515569774e408adb75e3a36e8e3d59956bcf971
+size 4924382960

distill/model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bfe24e9ec13e843f32544d8439bdd49bd8c64e2b2892a21bfeca647ae2c715
+size 4897310104

distill/model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e038cb921cab2e053bbf3d214487747405796a9d70fef9a1bfd05b1b5002c37
+size 4924382960

distill/model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7634d94685b4adfd2614ad2c9bbd92941e36c25a6631dcf960fdf744d6af361
+size 4897310104

distill/model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90b02583db891ab75ac290e0a06b13fefacf0670f4773cfdec6db2d49f5af7cc
+size 4924382960