Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,23 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen-Image
+pipeline_tag: text-to-image
+tags: [text-to-image, mflux, qwen, qwen-image, quantized, osaurus]
+---
+
+![Osaurus](osaurus-x-banner.png)
+
+# Qwen-Image · mflux · 8-bit
+
+Official **OsaurusAI** 8-bit [mflux](https://github.com/filipstrand/mflux) build of [Qwen-Image](https://huggingface.co/Qwen/Qwen-Image) (Qwen, Apache-2.0), quantized by Osaurus with mflux 0.18. High-quality text-to-image (strong text rendering) for Apple Silicon.
+
+## Usage
+```bash
+mflux-generate-qwen --model OsaurusAI/Qwen-Image-mflux-8bit \
+  --prompt "a small red cube on a white table" --steps 20
+```
+Or load in [Osaurus](https://osaurus.ai).
+
+## Provenance
+- Base: [Qwen/Qwen-Image](https://huggingface.co/Qwen/Qwen-Image) © Qwen — Apache-2.0
+- Quantization: Osaurus · mflux 0.18 · 8-bit · eric@osaurus.ai

text_encoder/0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96ce966c660e1349bc5ba63412c313c1c4b8c50ecda9bb03fe7a848c511a957a
+size 2080974775

text_encoder/1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea395d17455264f9ca8e190a607ade851e8e932cc2dee193bb72831277a846b
+size 2136050841

text_encoder/2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056244185bdf6f7b2740f56151fdd3b44378ae40db87850a6db26479d4025c3e
+size 2059005337

text_encoder/3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d49848b27c508b6010784934d75cc15d355a79669432313b729e91e9767950b
+size 2136050889

text_encoder/4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011e81551bbedb065c33a15c9c6def4cdcdf4e13d17292b879593170fbb0f1fe
+size 2059005367

text_encoder/5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56678abf1770845e35f46a0a0691d4c3c9a149ea91bed538251161f3393fb25f
+size 2136050889

text_encoder/6.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f900818d34e352c61d46255dd9e604577b4ed435c9d70720a5642277550f56
+size 1534150412

text_encoder/model.safetensors.index.json

@@ -0,0 +1,375 @@
+{
+  "metadata": {
+    "quantization_level": "8",
+    "mflux_version": "0.18.0"
+  },
+  "weight_map": {
+    "encoder.embed_tokens.weight": "0.safetensors",
+    "encoder.layers.0.input_layernorm.weight": "0.safetensors",
+    "encoder.layers.0.self_attn.q_proj.weight": "0.safetensors",
+    "encoder.layers.0.self_attn.q_proj.bias": "0.safetensors",
+    "encoder.layers.0.self_attn.k_proj.weight": "0.safetensors",
+    "encoder.layers.0.self_attn.k_proj.bias": "0.safetensors",
+    "encoder.layers.0.self_attn.v_proj.weight": "0.safetensors",
+    "encoder.layers.0.self_attn.v_proj.bias": "0.safetensors",
+    "encoder.layers.0.self_attn.o_proj.weight": "0.safetensors",
+    "encoder.layers.0.self_attn.rotary_emb.inv_freq": "0.safetensors",
+    "encoder.layers.0.post_attention_layernorm.weight": "0.safetensors",
+    "encoder.layers.0.mlp.gate_proj.weight": "0.safetensors",
+    "encoder.layers.0.mlp.up_proj.weight": "0.safetensors",
+    "encoder.layers.0.mlp.down_proj.weight": "0.safetensors",
+    "encoder.layers.1.input_layernorm.weight": "0.safetensors",
+    "encoder.layers.1.self_attn.q_proj.weight": "0.safetensors",
+    "encoder.layers.1.self_attn.q_proj.bias": "0.safetensors",
+    "encoder.layers.1.self_attn.k_proj.weight": "0.safetensors",
+    "encoder.layers.1.self_attn.k_proj.bias": "0.safetensors",
+    "encoder.layers.1.self_attn.v_proj.weight": "0.safetensors",
+    "encoder.layers.1.self_attn.v_proj.bias": "0.safetensors",
+    "encoder.layers.1.self_attn.o_proj.weight": "0.safetensors",
+    "encoder.layers.1.self_attn.rotary_emb.inv_freq": "0.safetensors",
+    "encoder.layers.1.post_attention_layernorm.weight": "0.safetensors",
+    "encoder.layers.1.mlp.gate_proj.weight": "0.safetensors",
+    "encoder.layers.1.mlp.up_proj.weight": "0.safetensors",
+    "encoder.layers.1.mlp.down_proj.weight": "0.safetensors",
+    "encoder.layers.2.input_layernorm.weight": "0.safetensors",
+    "encoder.layers.2.self_attn.q_proj.weight": "0.safetensors",
+    "encoder.layers.2.self_attn.q_proj.bias": "0.safetensors",
+    "encoder.layers.2.self_attn.k_proj.weight": "0.safetensors",
+    "encoder.layers.2.self_attn.k_proj.bias": "0.safetensors",
+    "encoder.layers.2.self_attn.v_proj.weight": "0.safetensors",
+    "encoder.layers.2.self_attn.v_proj.bias": "0.safetensors",
+    "encoder.layers.2.self_attn.o_proj.weight": "0.safetensors",
+    "encoder.layers.2.self_attn.rotary_emb.inv_freq": "0.safetensors",
+    "encoder.layers.2.post_attention_layernorm.weight": "0.safetensors",
+    "encoder.layers.2.mlp.gate_proj.weight": "1.safetensors",
+    "encoder.layers.2.mlp.up_proj.weight": "1.safetensors",
+    "encoder.layers.2.mlp.down_proj.weight": "1.safetensors",
+    "encoder.layers.3.input_layernorm.weight": "1.safetensors",
+    "encoder.layers.3.self_attn.q_proj.weight": "1.safetensors",
+    "encoder.layers.3.self_attn.q_proj.bias": "1.safetensors",
+    "encoder.layers.3.self_attn.k_proj.weight": "1.safetensors",
+    "encoder.layers.3.self_attn.k_proj.bias": "1.safetensors",
+    "encoder.layers.3.self_attn.v_proj.weight": "1.safetensors",
+    "encoder.layers.3.self_attn.v_proj.bias": "1.safetensors",
+    "encoder.layers.3.self_attn.o_proj.weight": "1.safetensors",
+    "encoder.layers.3.self_attn.rotary_emb.inv_freq": "1.safetensors",
+    "encoder.layers.3.post_attention_layernorm.weight": "1.safetensors",
+    "encoder.layers.3.mlp.gate_proj.weight": "1.safetensors",
+    "encoder.layers.3.mlp.up_proj.weight": "1.safetensors",
+    "encoder.layers.3.mlp.down_proj.weight": "1.safetensors",
+    "encoder.layers.4.input_layernorm.weight": "1.safetensors",
+    "encoder.layers.4.self_attn.q_proj.weight": "1.safetensors",
+    "encoder.layers.4.self_attn.q_proj.bias": "1.safetensors",
+    "encoder.layers.4.self_attn.k_proj.weight": "1.safetensors",
+    "encoder.layers.4.self_attn.k_proj.bias": "1.safetensors",
+    "encoder.layers.4.self_attn.v_proj.weight": "1.safetensors",
+    "encoder.layers.4.self_attn.v_proj.bias": "1.safetensors",
+    "encoder.layers.4.self_attn.o_proj.weight": "1.safetensors",
+    "encoder.layers.4.self_attn.rotary_emb.inv_freq": "1.safetensors",
+    "encoder.layers.4.post_attention_layernorm.weight": "1.safetensors",
+    "encoder.layers.4.mlp.gate_proj.weight": "1.safetensors",
+    "encoder.layers.4.mlp.up_proj.weight": "1.safetensors",
+    "encoder.layers.4.mlp.down_proj.weight": "1.safetensors",
+    "encoder.layers.5.input_layernorm.weight": "1.safetensors",
+    "encoder.layers.5.self_attn.q_proj.weight": "1.safetensors",
+    "encoder.layers.5.self_attn.q_proj.bias": "1.safetensors",
+    "encoder.layers.5.self_attn.k_proj.weight": "1.safetensors",
+    "encoder.layers.5.self_attn.k_proj.bias": "1.safetensors",
+    "encoder.layers.5.self_attn.v_proj.weight": "1.safetensors",
+    "encoder.layers.5.self_attn.v_proj.bias": "1.safetensors",
+    "encoder.layers.5.self_attn.o_proj.weight": "1.safetensors",
+    "encoder.layers.5.self_attn.rotary_emb.inv_freq": "1.safetensors",
+    "encoder.layers.5.post_attention_layernorm.weight": "1.safetensors",
+    "encoder.layers.5.mlp.gate_proj.weight": "1.safetensors",
+    "encoder.layers.5.mlp.up_proj.weight": "1.safetensors",
+    "encoder.layers.5.mlp.down_proj.weight": "1.safetensors",
+    "encoder.layers.6.input_layernorm.weight": "1.safetensors",
+    "encoder.layers.6.self_attn.q_proj.weight": "1.safetensors",
+    "encoder.layers.6.self_attn.q_proj.bias": "1.safetensors",
+    "encoder.layers.6.self_attn.k_proj.weight": "1.safetensors",
+    "encoder.layers.6.self_attn.k_proj.bias": "1.safetensors",
+    "encoder.layers.6.self_attn.v_proj.weight": "1.safetensors",
+    "encoder.layers.6.self_attn.v_proj.bias": "1.safetensors",
+    "encoder.layers.6.self_attn.o_proj.weight": "1.safetensors",
+    "encoder.layers.6.self_attn.rotary_emb.inv_freq": "1.safetensors",
+    "encoder.layers.6.post_attention_layernorm.weight": "1.safetensors",
+    "encoder.layers.6.mlp.gate_proj.weight": "1.safetensors",
+    "encoder.layers.6.mlp.up_proj.weight": "1.safetensors",
+    "encoder.layers.6.mlp.down_proj.weight": "2.safetensors",
+    "encoder.layers.7.input_layernorm.weight": "2.safetensors",
+    "encoder.layers.7.self_attn.q_proj.weight": "2.safetensors",
+    "encoder.layers.7.self_attn.q_proj.bias": "2.safetensors",
+    "encoder.layers.7.self_attn.k_proj.weight": "2.safetensors",
+    "encoder.layers.7.self_attn.k_proj.bias": "2.safetensors",
+    "encoder.layers.7.self_attn.v_proj.weight": "2.safetensors",
+    "encoder.layers.7.self_attn.v_proj.bias": "2.safetensors",
+    "encoder.layers.7.self_attn.o_proj.weight": "2.safetensors",
+    "encoder.layers.7.self_attn.rotary_emb.inv_freq": "2.safetensors",
+    "encoder.layers.7.post_attention_layernorm.weight": "2.safetensors",
+    "encoder.layers.7.mlp.gate_proj.weight": "2.safetensors",
+    "encoder.layers.7.mlp.up_proj.weight": "2.safetensors",
+    "encoder.layers.7.mlp.down_proj.weight": "2.safetensors",
+    "encoder.layers.8.input_layernorm.weight": "2.safetensors",
+    "encoder.layers.8.self_attn.q_proj.weight": "2.safetensors",
+    "encoder.layers.8.self_attn.q_proj.bias": "2.safetensors",
+    "encoder.layers.8.self_attn.k_proj.weight": "2.safetensors",
+    "encoder.layers.8.self_attn.k_proj.bias": "2.safetensors",
+    "encoder.layers.8.self_attn.v_proj.weight": "2.safetensors",
+    "encoder.layers.8.self_attn.v_proj.bias": "2.safetensors",
+    "encoder.layers.8.self_attn.o_proj.weight": "2.safetensors",
+    "encoder.layers.8.self_attn.rotary_emb.inv_freq": "2.safetensors",
+    "encoder.layers.8.post_attention_layernorm.weight": "2.safetensors",
+    "encoder.layers.8.mlp.gate_proj.weight": "2.safetensors",
+    "encoder.layers.8.mlp.up_proj.weight": "2.safetensors",
+    "encoder.layers.8.mlp.down_proj.weight": "2.safetensors",
+    "encoder.layers.9.input_layernorm.weight": "2.safetensors",
+    "encoder.layers.9.self_attn.q_proj.weight": "2.safetensors",
+    "encoder.layers.9.self_attn.q_proj.bias": "2.safetensors",
+    "encoder.layers.9.self_attn.k_proj.weight": "2.safetensors",
+    "encoder.layers.9.self_attn.k_proj.bias": "2.safetensors",
+    "encoder.layers.9.self_attn.v_proj.weight": "2.safetensors",
+    "encoder.layers.9.self_attn.v_proj.bias": "2.safetensors",
+    "encoder.layers.9.self_attn.o_proj.weight": "2.safetensors",
+    "encoder.layers.9.self_attn.rotary_emb.inv_freq": "2.safetensors",
+    "encoder.layers.9.post_attention_layernorm.weight": "2.safetensors",
+    "encoder.layers.9.mlp.gate_proj.weight": "2.safetensors",
+    "encoder.layers.9.mlp.up_proj.weight": "2.safetensors",
+    "encoder.layers.9.mlp.down_proj.weight": "2.safetensors",
+    "encoder.layers.10.input_layernorm.weight": "2.safetensors",
+    "encoder.layers.10.self_attn.q_proj.weight": "2.safetensors",
+    "encoder.layers.10.self_attn.q_proj.bias": "2.safetensors",
+    "encoder.layers.10.self_attn.k_proj.weight": "2.safetensors",
+    "encoder.layers.10.self_attn.k_proj.bias": "2.safetensors",
+    "encoder.layers.10.self_attn.v_proj.weight": "2.safetensors",
+    "encoder.layers.10.self_attn.v_proj.bias": "2.safetensors",
+    "encoder.layers.10.self_attn.o_proj.weight": "2.safetensors",
+    "encoder.layers.10.self_attn.rotary_emb.inv_freq": "2.safetensors",
+    "encoder.layers.10.post_attention_layernorm.weight": "2.safetensors",
+    "encoder.layers.10.mlp.gate_proj.weight": "2.safetensors",
+    "encoder.layers.10.mlp.up_proj.weight": "2.safetensors",
+    "encoder.layers.10.mlp.down_proj.weight": "2.safetensors",
+    "encoder.layers.11.input_layernorm.weight": "2.safetensors",
+    "encoder.layers.11.self_attn.q_proj.weight": "2.safetensors",
+    "encoder.layers.11.self_attn.q_proj.bias": "2.safetensors",
+    "encoder.layers.11.self_attn.k_proj.weight": "2.safetensors",
+    "encoder.layers.11.self_attn.k_proj.bias": "2.safetensors",
+    "encoder.layers.11.self_attn.v_proj.weight": "2.safetensors",
+    "encoder.layers.11.self_attn.v_proj.bias": "2.safetensors",
+    "encoder.layers.11.self_attn.o_proj.weight": "2.safetensors",
+    "encoder.layers.11.self_attn.rotary_emb.inv_freq": "2.safetensors",
+    "encoder.layers.11.post_attention_layernorm.weight": "2.safetensors",
+    "encoder.layers.11.mlp.gate_proj.weight": "3.safetensors",
+    "encoder.layers.11.mlp.up_proj.weight": "3.safetensors",
+    "encoder.layers.11.mlp.down_proj.weight": "3.safetensors",
+    "encoder.layers.12.input_layernorm.weight": "3.safetensors",
+    "encoder.layers.12.self_attn.q_proj.weight": "3.safetensors",
+    "encoder.layers.12.self_attn.q_proj.bias": "3.safetensors",
+    "encoder.layers.12.self_attn.k_proj.weight": "3.safetensors",
+    "encoder.layers.12.self_attn.k_proj.bias": "3.safetensors",
+    "encoder.layers.12.self_attn.v_proj.weight": "3.safetensors",
+    "encoder.layers.12.self_attn.v_proj.bias": "3.safetensors",
+    "encoder.layers.12.self_attn.o_proj.weight": "3.safetensors",
+    "encoder.layers.12.self_attn.rotary_emb.inv_freq": "3.safetensors",
+    "encoder.layers.12.post_attention_layernorm.weight": "3.safetensors",
+    "encoder.layers.12.mlp.gate_proj.weight": "3.safetensors",
+    "encoder.layers.12.mlp.up_proj.weight": "3.safetensors",
+    "encoder.layers.12.mlp.down_proj.weight": "3.safetensors",
+    "encoder.layers.13.input_layernorm.weight": "3.safetensors",
+    "encoder.layers.13.self_attn.q_proj.weight": "3.safetensors",
+    "encoder.layers.13.self_attn.q_proj.bias": "3.safetensors",
+    "encoder.layers.13.self_attn.k_proj.weight": "3.safetensors",
+    "encoder.layers.13.self_attn.k_proj.bias": "3.safetensors",
+    "encoder.layers.13.self_attn.v_proj.weight": "3.safetensors",
+    "encoder.layers.13.self_attn.v_proj.bias": "3.safetensors",
+    "encoder.layers.13.self_attn.o_proj.weight": "3.safetensors",
+    "encoder.layers.13.self_attn.rotary_emb.inv_freq": "3.safetensors",
+    "encoder.layers.13.post_attention_layernorm.weight": "3.safetensors",
+    "encoder.layers.13.mlp.gate_proj.weight": "3.safetensors",
+    "encoder.layers.13.mlp.up_proj.weight": "3.safetensors",
+    "encoder.layers.13.mlp.down_proj.weight": "3.safetensors",
+    "encoder.layers.14.input_layernorm.weight": "3.safetensors",
+    "encoder.layers.14.self_attn.q_proj.weight": "3.safetensors",
+    "encoder.layers.14.self_attn.q_proj.bias": "3.safetensors",
+    "encoder.layers.14.self_attn.k_proj.weight": "3.safetensors",
+    "encoder.layers.14.self_attn.k_proj.bias": "3.safetensors",
+    "encoder.layers.14.self_attn.v_proj.weight": "3.safetensors",
+    "encoder.layers.14.self_attn.v_proj.bias": "3.safetensors",
+    "encoder.layers.14.self_attn.o_proj.weight": "3.safetensors",
+    "encoder.layers.14.self_attn.rotary_emb.inv_freq": "3.safetensors",
+    "encoder.layers.14.post_attention_layernorm.weight": "3.safetensors",
+    "encoder.layers.14.mlp.gate_proj.weight": "3.safetensors",
+    "encoder.layers.14.mlp.up_proj.weight": "3.safetensors",
+    "encoder.layers.14.mlp.down_proj.weight": "3.safetensors",
+    "encoder.layers.15.input_layernorm.weight": "3.safetensors",
+    "encoder.layers.15.self_attn.q_proj.weight": "3.safetensors",
+    "encoder.layers.15.self_attn.q_proj.bias": "3.safetensors",
+    "encoder.layers.15.self_attn.k_proj.weight": "3.safetensors",
+    "encoder.layers.15.self_attn.k_proj.bias": "3.safetensors",
+    "encoder.layers.15.self_attn.v_proj.weight": "3.safetensors",
+    "encoder.layers.15.self_attn.v_proj.bias": "3.safetensors",
+    "encoder.layers.15.self_attn.o_proj.weight": "3.safetensors",
+    "encoder.layers.15.self_attn.rotary_emb.inv_freq": "3.safetensors",
+    "encoder.layers.15.post_attention_layernorm.weight": "3.safetensors",
+    "encoder.layers.15.mlp.gate_proj.weight": "3.safetensors",
+    "encoder.layers.15.mlp.up_proj.weight": "3.safetensors",
+    "encoder.layers.15.mlp.down_proj.weight": "4.safetensors",
+    "encoder.layers.16.input_layernorm.weight": "4.safetensors",
+    "encoder.layers.16.self_attn.q_proj.weight": "4.safetensors",
+    "encoder.layers.16.self_attn.q_proj.bias": "4.safetensors",
+    "encoder.layers.16.self_attn.k_proj.weight": "4.safetensors",
+    "encoder.layers.16.self_attn.k_proj.bias": "4.safetensors",
+    "encoder.layers.16.self_attn.v_proj.weight": "4.safetensors",
+    "encoder.layers.16.self_attn.v_proj.bias": "4.safetensors",
+    "encoder.layers.16.self_attn.o_proj.weight": "4.safetensors",
+    "encoder.layers.16.self_attn.rotary_emb.inv_freq": "4.safetensors",
+    "encoder.layers.16.post_attention_layernorm.weight": "4.safetensors",
+    "encoder.layers.16.mlp.gate_proj.weight": "4.safetensors",
+    "encoder.layers.16.mlp.up_proj.weight": "4.safetensors",
+    "encoder.layers.16.mlp.down_proj.weight": "4.safetensors",
+    "encoder.layers.17.input_layernorm.weight": "4.safetensors",
+    "encoder.layers.17.self_attn.q_proj.weight": "4.safetensors",
+    "encoder.layers.17.self_attn.q_proj.bias": "4.safetensors",
+    "encoder.layers.17.self_attn.k_proj.weight": "4.safetensors",
+    "encoder.layers.17.self_attn.k_proj.bias": "4.safetensors",
+    "encoder.layers.17.self_attn.v_proj.weight": "4.safetensors",
+    "encoder.layers.17.self_attn.v_proj.bias": "4.safetensors",
+    "encoder.layers.17.self_attn.o_proj.weight": "4.safetensors",
+    "encoder.layers.17.self_attn.rotary_emb.inv_freq": "4.safetensors",
+    "encoder.layers.17.post_attention_layernorm.weight": "4.safetensors",
+    "encoder.layers.17.mlp.gate_proj.weight": "4.safetensors",
+    "encoder.layers.17.mlp.up_proj.weight": "4.safetensors",
+    "encoder.layers.17.mlp.down_proj.weight": "4.safetensors",
+    "encoder.layers.18.input_layernorm.weight": "4.safetensors",
+    "encoder.layers.18.self_attn.q_proj.weight": "4.safetensors",
+    "encoder.layers.18.self_attn.q_proj.bias": "4.safetensors",
+    "encoder.layers.18.self_attn.k_proj.weight": "4.safetensors",
+    "encoder.layers.18.self_attn.k_proj.bias": "4.safetensors",
+    "encoder.layers.18.self_attn.v_proj.weight": "4.safetensors",
+    "encoder.layers.18.self_attn.v_proj.bias": "4.safetensors",
+    "encoder.layers.18.self_attn.o_proj.weight": "4.safetensors",
+    "encoder.layers.18.self_attn.rotary_emb.inv_freq": "4.safetensors",
+    "encoder.layers.18.post_attention_layernorm.weight": "4.safetensors",
+    "encoder.layers.18.mlp.gate_proj.weight": "4.safetensors",
+    "encoder.layers.18.mlp.up_proj.weight": "4.safetensors",
+    "encoder.layers.18.mlp.down_proj.weight": "4.safetensors",
+    "encoder.layers.19.input_layernorm.weight": "4.safetensors",
+    "encoder.layers.19.self_attn.q_proj.weight": "4.safetensors",
+    "encoder.layers.19.self_attn.q_proj.bias": "4.safetensors",
+    "encoder.layers.19.self_attn.k_proj.weight": "4.safetensors",
+    "encoder.layers.19.self_attn.k_proj.bias": "4.safetensors",
+    "encoder.layers.19.self_attn.v_proj.weight": "4.safetensors",
+    "encoder.layers.19.self_attn.v_proj.bias": "4.safetensors",
+    "encoder.layers.19.self_attn.o_proj.weight": "4.safetensors",
+    "encoder.layers.19.self_attn.rotary_emb.inv_freq": "4.safetensors",
+    "encoder.layers.19.post_attention_layernorm.weight": "4.safetensors",
+    "encoder.layers.19.mlp.gate_proj.weight": "4.safetensors",
+    "encoder.layers.19.mlp.up_proj.weight": "4.safetensors",
+    "encoder.layers.19.mlp.down_proj.weight": "4.safetensors",
+    "encoder.layers.20.input_layernorm.weight": "4.safetensors",
+    "encoder.layers.20.self_attn.q_proj.weight": "4.safetensors",
+    "encoder.layers.20.self_attn.q_proj.bias": "4.safetensors",
+    "encoder.layers.20.self_attn.k_proj.weight": "4.safetensors",
+    "encoder.layers.20.self_attn.k_proj.bias": "4.safetensors",
+    "encoder.layers.20.self_attn.v_proj.weight": "4.safetensors",
+    "encoder.layers.20.self_attn.v_proj.bias": "4.safetensors",
+    "encoder.layers.20.self_attn.o_proj.weight": "4.safetensors",
+    "encoder.layers.20.self_attn.rotary_emb.inv_freq": "4.safetensors",
+    "encoder.layers.20.post_attention_layernorm.weight": "4.safetensors",
+    "encoder.layers.20.mlp.gate_proj.weight": "5.safetensors",
+    "encoder.layers.20.mlp.up_proj.weight": "5.safetensors",
+    "encoder.layers.20.mlp.down_proj.weight": "5.safetensors",
+    "encoder.layers.21.input_layernorm.weight": "5.safetensors",
+    "encoder.layers.21.self_attn.q_proj.weight": "5.safetensors",
+    "encoder.layers.21.self_attn.q_proj.bias": "5.safetensors",
+    "encoder.layers.21.self_attn.k_proj.weight": "5.safetensors",
+    "encoder.layers.21.self_attn.k_proj.bias": "5.safetensors",
+    "encoder.layers.21.self_attn.v_proj.weight": "5.safetensors",
+    "encoder.layers.21.self_attn.v_proj.bias": "5.safetensors",
+    "encoder.layers.21.self_attn.o_proj.weight": "5.safetensors",
+    "encoder.layers.21.self_attn.rotary_emb.inv_freq": "5.safetensors",
+    "encoder.layers.21.post_attention_layernorm.weight": "5.safetensors",
+    "encoder.layers.21.mlp.gate_proj.weight": "5.safetensors",
+    "encoder.layers.21.mlp.up_proj.weight": "5.safetensors",
+    "encoder.layers.21.mlp.down_proj.weight": "5.safetensors",
+    "encoder.layers.22.input_layernorm.weight": "5.safetensors",
+    "encoder.layers.22.self_attn.q_proj.weight": "5.safetensors",
+    "encoder.layers.22.self_attn.q_proj.bias": "5.safetensors",
+    "encoder.layers.22.self_attn.k_proj.weight": "5.safetensors",
+    "encoder.layers.22.self_attn.k_proj.bias": "5.safetensors",
+    "encoder.layers.22.self_attn.v_proj.weight": "5.safetensors",
+    "encoder.layers.22.self_attn.v_proj.bias": "5.safetensors",
+    "encoder.layers.22.self_attn.o_proj.weight": "5.safetensors",
+    "encoder.layers.22.self_attn.rotary_emb.inv_freq": "5.safetensors",
+    "encoder.layers.22.post_attention_layernorm.weight": "5.safetensors",
+    "encoder.layers.22.mlp.gate_proj.weight": "5.safetensors",
+    "encoder.layers.22.mlp.up_proj.weight": "5.safetensors",
+    "encoder.layers.22.mlp.down_proj.weight": "5.safetensors",
+    "encoder.layers.23.input_layernorm.weight": "5.safetensors",
+    "encoder.layers.23.self_attn.q_proj.weight": "5.safetensors",
+    "encoder.layers.23.self_attn.q_proj.bias": "5.safetensors",
+    "encoder.layers.23.self_attn.k_proj.weight": "5.safetensors",
+    "encoder.layers.23.self_attn.k_proj.bias": "5.safetensors",
+    "encoder.layers.23.self_attn.v_proj.weight": "5.safetensors",
+    "encoder.layers.23.self_attn.v_proj.bias": "5.safetensors",
+    "encoder.layers.23.self_attn.o_proj.weight": "5.safetensors",
+    "encoder.layers.23.self_attn.rotary_emb.inv_freq": "5.safetensors",
+    "encoder.layers.23.post_attention_layernorm.weight": "5.safetensors",
+    "encoder.layers.23.mlp.gate_proj.weight": "5.safetensors",
+    "encoder.layers.23.mlp.up_proj.weight": "5.safetensors",
+    "encoder.layers.23.mlp.down_proj.weight": "5.safetensors",
+    "encoder.layers.24.input_layernorm.weight": "5.safetensors",
+    "encoder.layers.24.self_attn.q_proj.weight": "5.safetensors",
+    "encoder.layers.24.self_attn.q_proj.bias": "5.safetensors",
+    "encoder.layers.24.self_attn.k_proj.weight": "5.safetensors",
+    "encoder.layers.24.self_attn.k_proj.bias": "5.safetensors",
+    "encoder.layers.24.self_attn.v_proj.weight": "5.safetensors",
+    "encoder.layers.24.self_attn.v_proj.bias": "5.safetensors",
+    "encoder.layers.24.self_attn.o_proj.weight": "5.safetensors",
+    "encoder.layers.24.self_attn.rotary_emb.inv_freq": "5.safetensors",
+    "encoder.layers.24.post_attention_layernorm.weight": "5.safetensors",
+    "encoder.layers.24.mlp.gate_proj.weight": "5.safetensors",
+    "encoder.layers.24.mlp.up_proj.weight": "5.safetensors",
+    "encoder.layers.24.mlp.down_proj.weight": "6.safetensors",
+    "encoder.layers.25.input_layernorm.weight": "6.safetensors",
+    "encoder.layers.25.self_attn.q_proj.weight": "6.safetensors",
+    "encoder.layers.25.self_attn.q_proj.bias": "6.safetensors",
+    "encoder.layers.25.self_attn.k_proj.weight": "6.safetensors",
+    "encoder.layers.25.self_attn.k_proj.bias": "6.safetensors",
+    "encoder.layers.25.self_attn.v_proj.weight": "6.safetensors",
+    "encoder.layers.25.self_attn.v_proj.bias": "6.safetensors",
+    "encoder.layers.25.self_attn.o_proj.weight": "6.safetensors",
+    "encoder.layers.25.self_attn.rotary_emb.inv_freq": "6.safetensors",
+    "encoder.layers.25.post_attention_layernorm.weight": "6.safetensors",
+    "encoder.layers.25.mlp.gate_proj.weight": "6.safetensors",
+    "encoder.layers.25.mlp.up_proj.weight": "6.safetensors",
+    "encoder.layers.25.mlp.down_proj.weight": "6.safetensors",
+    "encoder.layers.26.input_layernorm.weight": "6.safetensors",
+    "encoder.layers.26.self_attn.q_proj.weight": "6.safetensors",
+    "encoder.layers.26.self_attn.q_proj.bias": "6.safetensors",
+    "encoder.layers.26.self_attn.k_proj.weight": "6.safetensors",
+    "encoder.layers.26.self_attn.k_proj.bias": "6.safetensors",
+    "encoder.layers.26.self_attn.v_proj.weight": "6.safetensors",
+    "encoder.layers.26.self_attn.v_proj.bias": "6.safetensors",
+    "encoder.layers.26.self_attn.o_proj.weight": "6.safetensors",
+    "encoder.layers.26.self_attn.rotary_emb.inv_freq": "6.safetensors",
+    "encoder.layers.26.post_attention_layernorm.weight": "6.safetensors",
+    "encoder.layers.26.mlp.gate_proj.weight": "6.safetensors",
+    "encoder.layers.26.mlp.up_proj.weight": "6.safetensors",
+    "encoder.layers.26.mlp.down_proj.weight": "6.safetensors",
+    "encoder.layers.27.input_layernorm.weight": "6.safetensors",
+    "encoder.layers.27.self_attn.q_proj.weight": "6.safetensors",
+    "encoder.layers.27.self_attn.q_proj.bias": "6.safetensors",
+    "encoder.layers.27.self_attn.k_proj.weight": "6.safetensors",
+    "encoder.layers.27.self_attn.k_proj.bias": "6.safetensors",
+    "encoder.layers.27.self_attn.v_proj.weight": "6.safetensors",
+    "encoder.layers.27.self_attn.v_proj.bias": "6.safetensors",
+    "encoder.layers.27.self_attn.o_proj.weight": "6.safetensors",
+    "encoder.layers.27.self_attn.rotary_emb.inv_freq": "6.safetensors",
+    "encoder.layers.27.post_attention_layernorm.weight": "6.safetensors",
+    "encoder.layers.27.mlp.gate_proj.weight": "6.safetensors",
+    "encoder.layers.27.mlp.up_proj.weight": "6.safetensors",
+    "encoder.layers.27.mlp.down_proj.weight": "6.safetensors",
+    "encoder.norm.weight": "6.safetensors",
+    "encoder.rotary_emb.inv_freq": "6.safetensors"
+  }
+}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444a80c37c7f34f485c050cf374595a0cb7d88735459cf0505fd204453c33178
+size 11417006

tokenizer/tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

transformer/0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f066462bf3d6f647ce48443db49c9f695777affa001f6b7b68bc59e82572d8b8
+size 2147291992

transformer/1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0498fc1358e51103f53c9448698c039e5683b2960bb742a21d4934c87da53b
+size 2129238946

transformer/10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04c56884f8596b4bdcafa58041cf7ad9287704fd2bf7d8d62ac462c675181b21
+size 381428288

transformer/2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddffef2ff7f3b40c79dbe550800c9f49506c219dc9d0a0d4b514b7b41bc93fc5
+size 2106788646

transformer/3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e16e32a09ead1e22c8c0bf0c098823c142b101246cf8b15ea4f9a60af5f62f7d
+size 2126873381

transformer/4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4011f4acb940f07138a90cea6d9b261333c4a8f1ba6ffd731378685239c30a
+size 2126854960

transformer/5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cfa6f69c7d75f879da0747e0f0dc8c008c4fbb4adca9c5447621b7715665a71
+size 2146920787

transformer/6.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c4d7f2d7b864460a5cd60cc2778bf07e741091a6a2504186394993958c2b82
+size 2146919411

transformer/7.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a732fffb464451d91f1b21cd30826e561e1af4f3b874838afb7b8b15239b01de
+size 2146920895

transformer/8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4c506aa98dc8061a00760567b9b0aac97bd18d01d5d7e65b75cddffdb6f2d9
+size 2146920883

transformer/9.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c97e4156e019fa442561a424571b7b7955252246c3bfa93c5ab722fa2086c2f
+size 2106788772

vae/0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a9f85b4c9632303684c05227f0b85e3a476f315ee018b11d8bfb08202e858f
+size 253586147

vae/model.safetensors.index.json

@@ -0,0 +1,200 @@
+{
+  "metadata": {
+    "quantization_level": "8",
+    "mflux_version": "0.18.0"
+  },
+  "weight_map": {
+    "decoder.conv_in.conv3d.weight": "0.safetensors",
+    "decoder.conv_in.conv3d.bias": "0.safetensors",
+    "decoder.mid_block.attentions.0.norm.weight": "0.safetensors",
+    "decoder.mid_block.attentions.0.to_qkv.weight": "0.safetensors",
+    "decoder.mid_block.attentions.0.to_qkv.bias": "0.safetensors",
+    "decoder.mid_block.attentions.0.proj.weight": "0.safetensors",
+    "decoder.mid_block.attentions.0.proj.bias": "0.safetensors",
+    "decoder.mid_block.resnets.0.norm1.weight": "0.safetensors",
+    "decoder.mid_block.resnets.0.conv1.conv3d.weight": "0.safetensors",
+    "decoder.mid_block.resnets.0.conv1.conv3d.bias": "0.safetensors",
+    "decoder.mid_block.resnets.0.norm2.weight": "0.safetensors",
+    "decoder.mid_block.resnets.0.conv2.conv3d.weight": "0.safetensors",
+    "decoder.mid_block.resnets.0.conv2.conv3d.bias": "0.safetensors",
+    "decoder.mid_block.resnets.1.norm1.weight": "0.safetensors",
+    "decoder.mid_block.resnets.1.conv1.conv3d.weight": "0.safetensors",
+    "decoder.mid_block.resnets.1.conv1.conv3d.bias": "0.safetensors",
+    "decoder.mid_block.resnets.1.norm2.weight": "0.safetensors",
+    "decoder.mid_block.resnets.1.conv2.conv3d.weight": "0.safetensors",
+    "decoder.mid_block.resnets.1.conv2.conv3d.bias": "0.safetensors",
+    "decoder.up_block0.resnets.0.norm1.weight": "0.safetensors",
+    "decoder.up_block0.resnets.0.conv1.conv3d.weight": "0.safetensors",
+    "decoder.up_block0.resnets.0.conv1.conv3d.bias": "0.safetensors",
+    "decoder.up_block0.resnets.0.norm2.weight": "0.safetensors",
+    "decoder.up_block0.resnets.0.conv2.conv3d.weight": "0.safetensors",
+    "decoder.up_block0.resnets.0.conv2.conv3d.bias": "0.safetensors",
+    "decoder.up_block0.resnets.1.norm1.weight": "0.safetensors",
+    "decoder.up_block0.resnets.1.conv1.conv3d.weight": "0.safetensors",
+    "decoder.up_block0.resnets.1.conv1.conv3d.bias": "0.safetensors",
+    "decoder.up_block0.resnets.1.norm2.weight": "0.safetensors",
+    "decoder.up_block0.resnets.1.conv2.conv3d.weight": "0.safetensors",
+    "decoder.up_block0.resnets.1.conv2.conv3d.bias": "0.safetensors",
+    "decoder.up_block0.resnets.2.norm1.weight": "0.safetensors",
+    "decoder.up_block0.resnets.2.conv1.conv3d.weight": "0.safetensors",
+    "decoder.up_block0.resnets.2.conv1.conv3d.bias": "0.safetensors",
+    "decoder.up_block0.resnets.2.norm2.weight": "0.safetensors",
+    "decoder.up_block0.resnets.2.conv2.conv3d.weight": "0.safetensors",
+    "decoder.up_block0.resnets.2.conv2.conv3d.bias": "0.safetensors",
+    "decoder.up_block0.upsamplers.0.time_conv.conv3d.weight": "0.safetensors",
+    "decoder.up_block0.upsamplers.0.time_conv.conv3d.bias": "0.safetensors",
+    "decoder.up_block0.upsamplers.0.resample_conv.weight": "0.safetensors",
+    "decoder.up_block0.upsamplers.0.resample_conv.bias": "0.safetensors",
+    "decoder.up_block1.resnets.0.norm1.weight": "0.safetensors",
+    "decoder.up_block1.resnets.0.conv1.conv3d.weight": "0.safetensors",
+    "decoder.up_block1.resnets.0.conv1.conv3d.bias": "0.safetensors",
+    "decoder.up_block1.resnets.0.norm2.weight": "0.safetensors",
+    "decoder.up_block1.resnets.0.conv2.conv3d.weight": "0.safetensors",
+    "decoder.up_block1.resnets.0.conv2.conv3d.bias": "0.safetensors",
+    "decoder.up_block1.resnets.0.skip_conv.conv3d.weight": "0.safetensors",
+    "decoder.up_block1.resnets.0.skip_conv.conv3d.bias": "0.safetensors",
+    "decoder.up_block1.resnets.1.norm1.weight": "0.safetensors",
+    "decoder.up_block1.resnets.1.conv1.conv3d.weight": "0.safetensors",
+    "decoder.up_block1.resnets.1.conv1.conv3d.bias": "0.safetensors",
+    "decoder.up_block1.resnets.1.norm2.weight": "0.safetensors",
+    "decoder.up_block1.resnets.1.conv2.conv3d.weight": "0.safetensors",
+    "decoder.up_block1.resnets.1.conv2.conv3d.bias": "0.safetensors",
+    "decoder.up_block1.resnets.2.norm1.weight": "0.safetensors",
+    "decoder.up_block1.resnets.2.conv1.conv3d.weight": "0.safetensors",
+    "decoder.up_block1.resnets.2.conv1.conv3d.bias": "0.safetensors",
+    "decoder.up_block1.resnets.2.norm2.weight": "0.safetensors",
+    "decoder.up_block1.resnets.2.conv2.conv3d.weight": "0.safetensors",
+    "decoder.up_block1.resnets.2.conv2.conv3d.bias": "0.safetensors",
+    "decoder.up_block1.upsamplers.0.time_conv.conv3d.weight": "0.safetensors",
+    "decoder.up_block1.upsamplers.0.time_conv.conv3d.bias": "0.safetensors",
+    "decoder.up_block1.upsamplers.0.resample_conv.weight": "0.safetensors",
+    "decoder.up_block1.upsamplers.0.resample_conv.bias": "0.safetensors",
+    "decoder.up_block2.resnets.0.norm1.weight": "0.safetensors",
+    "decoder.up_block2.resnets.0.conv1.conv3d.weight": "0.safetensors",
+    "decoder.up_block2.resnets.0.conv1.conv3d.bias": "0.safetensors",
+    "decoder.up_block2.resnets.0.norm2.weight": "0.safetensors",
+    "decoder.up_block2.resnets.0.conv2.conv3d.weight": "0.safetensors",
+    "decoder.up_block2.resnets.0.conv2.conv3d.bias": "0.safetensors",
+    "decoder.up_block2.resnets.1.norm1.weight": "0.safetensors",
+    "decoder.up_block2.resnets.1.conv1.conv3d.weight": "0.safetensors",
+    "decoder.up_block2.resnets.1.conv1.conv3d.bias": "0.safetensors",
+    "decoder.up_block2.resnets.1.norm2.weight": "0.safetensors",
+    "decoder.up_block2.resnets.1.conv2.conv3d.weight": "0.safetensors",
+    "decoder.up_block2.resnets.1.conv2.conv3d.bias": "0.safetensors",
+    "decoder.up_block2.resnets.2.norm1.weight": "0.safetensors",
+    "decoder.up_block2.resnets.2.conv1.conv3d.weight": "0.safetensors",
+    "decoder.up_block2.resnets.2.conv1.conv3d.bias": "0.safetensors",
+    "decoder.up_block2.resnets.2.norm2.weight": "0.safetensors",
+    "decoder.up_block2.resnets.2.conv2.conv3d.weight": "0.safetensors",
+    "decoder.up_block2.resnets.2.conv2.conv3d.bias": "0.safetensors",
+    "decoder.up_block2.upsamplers.0.resample_conv.weight": "0.safetensors",
+    "decoder.up_block2.upsamplers.0.resample_conv.bias": "0.safetensors",
+    "decoder.up_block3.resnets.0.norm1.weight": "0.safetensors",
+    "decoder.up_block3.resnets.0.conv1.conv3d.weight": "0.safetensors",
+    "decoder.up_block3.resnets.0.conv1.conv3d.bias": "0.safetensors",
+    "decoder.up_block3.resnets.0.norm2.weight": "0.safetensors",
+    "decoder.up_block3.resnets.0.conv2.conv3d.weight": "0.safetensors",
+    "decoder.up_block3.resnets.0.conv2.conv3d.bias": "0.safetensors",
+    "decoder.up_block3.resnets.1.norm1.weight": "0.safetensors",
+    "decoder.up_block3.resnets.1.conv1.conv3d.weight": "0.safetensors",
+    "decoder.up_block3.resnets.1.conv1.conv3d.bias": "0.safetensors",
+    "decoder.up_block3.resnets.1.norm2.weight": "0.safetensors",
+    "decoder.up_block3.resnets.1.conv2.conv3d.weight": "0.safetensors",
+    "decoder.up_block3.resnets.1.conv2.conv3d.bias": "0.safetensors",
+    "decoder.up_block3.resnets.2.norm1.weight": "0.safetensors",
+    "decoder.up_block3.resnets.2.conv1.conv3d.weight": "0.safetensors",
+    "decoder.up_block3.resnets.2.conv1.conv3d.bias": "0.safetensors",
+    "decoder.up_block3.resnets.2.norm2.weight": "0.safetensors",
+    "decoder.up_block3.resnets.2.conv2.conv3d.weight": "0.safetensors",
+    "decoder.up_block3.resnets.2.conv2.conv3d.bias": "0.safetensors",
+    "decoder.norm_out.weight": "0.safetensors",
+    "decoder.conv_out.conv3d.weight": "0.safetensors",
+    "decoder.conv_out.conv3d.bias": "0.safetensors",
+    "encoder.conv_in.conv3d.weight": "0.safetensors",
+    "encoder.conv_in.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv1.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv1.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv2.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv2.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv1.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv1.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv2.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv2.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.0.downsamplers.0.resample_conv.weight": "0.safetensors",
+    "encoder.down_blocks.0.downsamplers.0.resample_conv.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv1.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv1.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv2.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv2.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.skip_conv.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.skip_conv.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv1.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv1.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv2.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv2.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.1.downsamplers.0.resample_conv.weight": "0.safetensors",
+    "encoder.down_blocks.1.downsamplers.0.resample_conv.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv1.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv1.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv2.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv2.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.skip_conv.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.skip_conv.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv1.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv1.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv2.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv2.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.2.downsamplers.0.time_conv.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.2.downsamplers.0.time_conv.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.2.downsamplers.0.resample_conv.weight": "0.safetensors",
+    "encoder.down_blocks.2.downsamplers.0.resample_conv.bias": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv1.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv1.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv2.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv2.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv1.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv1.conv3d.bias": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv2.conv3d.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv2.conv3d.bias": "0.safetensors",
+    "encoder.mid_block.attentions.0.norm.weight": "0.safetensors",
+    "encoder.mid_block.attentions.0.to_qkv.weight": "0.safetensors",
+    "encoder.mid_block.attentions.0.to_qkv.bias": "0.safetensors",
+    "encoder.mid_block.attentions.0.proj.weight": "0.safetensors",
+    "encoder.mid_block.attentions.0.proj.bias": "0.safetensors",
+    "encoder.mid_block.resnets.0.norm1.weight": "0.safetensors",
+    "encoder.mid_block.resnets.0.conv1.conv3d.weight": "0.safetensors",
+    "encoder.mid_block.resnets.0.conv1.conv3d.bias": "0.safetensors",
+    "encoder.mid_block.resnets.0.norm2.weight": "0.safetensors",
+    "encoder.mid_block.resnets.0.conv2.conv3d.weight": "0.safetensors",
+    "encoder.mid_block.resnets.0.conv2.conv3d.bias": "0.safetensors",
+    "encoder.mid_block.resnets.1.norm1.weight": "0.safetensors",
+    "encoder.mid_block.resnets.1.conv1.conv3d.weight": "0.safetensors",
+    "encoder.mid_block.resnets.1.conv1.conv3d.bias": "0.safetensors",
+    "encoder.mid_block.resnets.1.norm2.weight": "0.safetensors",
+    "encoder.mid_block.resnets.1.conv2.conv3d.weight": "0.safetensors",
+    "encoder.mid_block.resnets.1.conv2.conv3d.bias": "0.safetensors",
+    "encoder.norm_out.weight": "0.safetensors",
+    "encoder.conv_out.conv3d.weight": "0.safetensors",
+    "encoder.conv_out.conv3d.bias": "0.safetensors",
+    "post_quant_conv.conv3d.weight": "0.safetensors",
+    "post_quant_conv.conv3d.bias": "0.safetensors",
+    "quant_conv.conv3d.weight": "0.safetensors",
+    "quant_conv.conv3d.bias": "0.safetensors"
+  }
+}