Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,10 @@ 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
+lib/liboptimus_ths-torch2.2-cu121.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+lib/liboptimus_ths-torch2.3-cu121.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+lib/liboptimus_ths-torch2.5-cu124.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+assets/dcvae.png filter=lfs diff=lfs merge=lfs -text
+assets/dit.png filter=lfs diff=lfs merge=lfs -text
+assets/dpo_pipeline.png filter=lfs diff=lfs merge=lfs -text
+assets/model_architecture.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,173 @@
----
-license: mit
----
+---
+license: mit
+library_name: diffusers
+pipeline_tag: text-to-video
+---
+
+<p align="center">
+  <img src="assets/logo.png"  height=100>
+</p>
+<div align="center">
+  <a href="https://yuewen.cn/videos"><img src="https://img.shields.io/static/v1?label=Step-Video&message=Web&color=green"></a> &ensp;
+  <a href="https://arxiv.org/abs/2502.10248"><img src="https://img.shields.io/static/v1?label=Tech Report&message=Arxiv&color=red"></a> &ensp;
+  <a href="https://x.com/StepFun_ai"><img src="https://img.shields.io/static/v1?label=X.com&message=Web&color=blue"></a> &ensp;
+</div>
+
+<div align="center">
+  <a href="https://huggingface.co/stepfun-ai/stepvideo-t2v"><img src="https://img.shields.io/static/v1?label=Step-Video-T2V&message=HuggingFace&color=yellow"></a> &ensp;
+  <a href="https://huggingface.co/stepfun-ai/stepvideo-t2v-turbo"><img src="https://img.shields.io/static/v1?label=Step-Video-T2V-Turbo&message=HuggingFace&color=yellow"></a> &ensp;
+  <a href="https://github.com/stepfun-ai/Step-Video-T2V"><img src="https://img.shields.io/static/v1?label=Code&message=Github&color=black"></a> &ensp;
+</div>
+
+## 🔥🔥🔥 News!!
+* Feb 17, 2025: 👋 We release the inference code and model weights of Step-Video-T2V. [Download](https://huggingface.co/stepfun-ai/stepvideo-t2v)
+* Feb 17, 2025: 👋 We release the inference code and model weights of Step-Video-T2V-Turbo. [Download](https://huggingface.co/stepfun-ai/stepvideo-t2v-turbo)
+* Feb 17, 2025: 🎉 We have made our technical report available as open source. [Read](https://arxiv.org/abs/2502.10248)
+
+## Video Demos
+
+<table border="0" style="width: 100%; text-align: center; margin-top: 1px;">
+  <tr>
+    <td><video src="https://github.com/user-attachments/assets/9274b351-595d-41fb-aba3-f58e6e91603a" width="100%" controls autoplay loop muted></video></td>
+    <td><video src="https://github.com/user-attachments/assets/2f6b3ad5-e93b-436b-98bc-4701182d8652" width="100%" controls autoplay loop muted></video></td>
+    <td><video src="https://github.com/user-attachments/assets/67d20ee7-ad78-4b8f-80f6-3fdb00fb52d8" width="100%" controls autoplay loop muted></video></td>
+  </tr>
+  <tr>
+    <td><video src="https://github.com/user-attachments/assets/9abce409-105d-4a8a-ad13-104a98cc8a0b" width="100%" controls autoplay loop muted></video></td>
+    <td><video src="https://github.com/user-attachments/assets/8d1e1a47-048a-49ce-85f6-9d013f2d8e89" width="100%" controls autoplay loop muted></video></td>
+    <td><video src="https://github.com/user-attachments/assets/32cf4bd1-ec1f-4f77-a488-cd0284aa81bb" width="100%" controls autoplay loop muted></video></td>
+  </tr>
+  <tr>
+    <td><video src="https://github.com/user-attachments/assets/f95a7a49-032a-44ea-a10f-553d4e5d21c6" width="100%" controls autoplay loop muted></video></td>
+    <td><video src="https://github.com/user-attachments/assets/3534072e-87d9-4128-a87f-28fcb5d951e0" width="100%" controls autoplay loop muted></video></td>
+    <td><video src="https://github.com/user-attachments/assets/6d893dad-556d-4527-a882-666cba3d10e9" width="100%" controls autoplay loop muted></video></td>
+  </tr>
+
+</table>
+
+## Table of Contents
+
+1. [Introduction](#1-introduction)
+2. [Model Summary](#2-model-summary)
+3. [Model Download](#3-model-download)
+4. [Model Usage](#4-model-usage)
+5. [Benchmark](#5-benchmark)
+6. [Online Engine](#6-online-engine)
+7. [Citation](#7-citation)
+8. [Acknowledgement](#8-ackownledgement)
+
+## 1. Introduction
+We present **Step-Video-T2V**, a state-of-the-art (SoTA) text-to-video pre-trained model with 30 billion parameters and the capability to generate videos up to 204 frames. To enhance both training and inference efficiency, we propose a deep compression VAE for videos, achieving 16x16 spatial and 8x temporal compression ratios. Direct Preference Optimization (DPO) is applied in the final stage to further enhance the visual quality of the generated videos. Step-Video-T2V's performance is evaluated on a novel video generation benchmark, **Step-Video-T2V-Eval**, demonstrating its SoTA text-to-video quality compared to both open-source and commercial engines.
+
+## 2. Model Summary
+In Step-Video-T2V, videos are represented by a high-compression Video-VAE, achieving 16x16 spatial and 8x temporal compression ratios. User prompts are encoded using two bilingual pre-trained text encoders to handle both English and Chinese. A DiT with 3D full attention is trained using Flow Matching and is employed to denoise input noise into latent frames, with text embeddings and timesteps serving as conditioning factors. To further enhance the visual quality of the generated videos, a video-based DPO approach is applied, which effectively reduces artifacts and ensures smoother, more realistic video outputs.
+
+<p align="center">
+  <img width="80%" src="assets/model_architecture.png">
+</p>
+
+### 2.1. Video-VAE
+A deep compression Variational Autoencoder (VideoVAE) is designed for video generation tasks, achieving 16x16 spatial and 8x temporal compression ratios while maintaining exceptional video reconstruction quality. This compression not only accelerates training and inference but also aligns with the diffusion process's preference for condensed representations.
+
+<p align="center">
+  <img width="70%" src="assets/dcvae.png">
+</p>
+
+### 2.2. DiT w/ 3D Full Attention
+Step-Video-T2V is built on the DiT architecture, which has 48 layers, each containing 48 attention heads, with each head’s dimension set to 128. AdaLN-Single is leveraged to incorporate the timestep condition, while QK-Norm in the self-attention mechanism is introduced to ensure training stability. Additionally, 3D RoPE is employed, playing a critical role in handling sequences of varying video lengths and resolutions.
+
+<p align="center">
+  <img width="80%" src="assets/dit.png">
+</p>
+
+### 2.3. Video-DPO
+In Step-Video-T2V, we incorporate human feedback through Direct Preference Optimization (DPO) to further enhance the visual quality of the generated videos. DPO leverages human preference data to fine-tune the model, ensuring that the generated content aligns more closely with human expectations. The overall DPO pipeline is shown below, highlighting its critical role in improving both the consistency and quality of the video generation process.
+
+<p align="center">
+  <img width="100%" src="assets/dpo_pipeline.png">
+</p>
+
+
+
+## 3. Model Download
+| Models   | 🤗Huggingface    |  🤖Modelscope |
+|:-------:|:-------:|:-------:|
+| Step-Video-T2V | [download](https://huggingface.co/stepfun-ai/stepvideo-t2v) | [download](https://www.modelscope.cn/models/stepfun-ai/stepvideo-t2v)
+| Step-Video-T2V-Turbo (Inference Step Distillation) | [download](https://huggingface.co/stepfun-ai/stepvideo-t2v-turbo) | [download](https://www.modelscope.cn/models/stepfun-ai/stepvideo-t2v-turbo)
+
+
+## 4. Model Usage
+### 📜 4.1  Requirements
+
+The following table shows the requirements for running Step-Video-T2V model (batch size = 1, w/o cfg distillation) to generate videos:
+
+|     Model    |  height/width/frame |  Peak GPU Memory | 50 steps w flash-attn | 50 steps w/o flash-attn |
+|:------------:|:------------:|:------------:|:------------:|:------------:|
+| Step-Video-T2V   |        544px992px204f      |  77.64 GB | 743 s | 1232 s |
+| Step-Video-T2V   |        544px992px136f      |  72.48 GB | 408 s | 605 s |
+
+* An NVIDIA GPU with CUDA support is required. 
+  * The model is tested on four GPUs.
+  * **Recommended**: We recommend to use GPUs with 80GB of memory for better generation quality.
+* Tested operating system: Linux
+* The self-attention in text-encoder (step_llm) only supports CUDA capabilities sm_80 sm_86 and sm_90
+
+### 🔧 4.2 Dependencies and Installation
+- Python >= 3.10.0 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html))
+- [PyTorch >= 2.3-cu121](https://pytorch.org/)
+- [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads)
+- [FFmpeg](https://www.ffmpeg.org/) 
+```bash
+git clone https://github.com/stepfun-ai/Step-Video-T2V.git
+conda create -n stepvideo python=3.10
+conda activate stepvideo
+
+cd Step-Video-T2V
+pip install -e .
+pip install flash-attn --no-build-isolation  ## flash-attn is optional
+```
+
+###  🚀 4.3 Inference Scripts
+- We employed a decoupling strategy for the text encoder, VAE decoding, and DiT to optimize GPU resource utilization by DiT. As a result, a dedicated GPU is needed to handle the API services for the text encoder's embeddings and VAE decoding.
+```bash
+python api/call_remote_server.py --model_dir where_you_download_dir &  ## We assume you have more than 4 GPUs available. This command will return the URL for both the caption API and the VAE API. Please use the returned URL in the following command.
+
+parallel=4  # or parallel=8
+url='127.0.0.1'
+model_dir=where_you_download_dir
+
+torchrun --nproc_per_node $parallel run_parallel.py --model_dir $model_dir --vae_url $url --caption_url $url  --ulysses_degree $parallel --prompt "一名宇航员在月球上发现一块石碑，上面印有“stepfun”字样，闪闪发光" --infer_steps 50  --cfg_scale 9.0 --time_shift 13.0
+```
+
+###  🚀 4.4 Best-of-Practice Inference settings
+Step-Video-T2V exhibits robust performance in inference settings, consistently generating high-fidelity and dynamic videos. However, our experiments reveal that variations in inference hyperparameters can have a substantial effect on the trade-off between video fidelity and dynamics. To achieve optimal results, we recommend the following best practices for tuning inference parameters:
+
+| Models   | infer_steps   | cfg_scale  | time_shift | num_frames |
+|:-------:|:-------:|:-------:|:-------:|:-------:|
+| Step-Video-T2V | 30-50 | 9.0 |  13.0 | 204
+| Step-Video-T2V-Turbo (Inference Step Distillation) | 10-15 | 5.0 | 17.0 | 204 |
+
+
+## 5. Benchmark
+We are releasing [Step-Video-T2V Eval](https://github.com/stepfun-ai/Step-Video-T2V/blob/main/benchmark/Step-Video-T2V-Eval) as a new benchmark, featuring 128 Chinese prompts sourced from real users. This benchmark is designed to evaluate the quality of generated videos across 11 distinct categories: Sports, Food, Scenery, Animals, Festivals, Combination Concepts, Surreal, People, 3D Animation, Cinematography, and Style.
+
+## 6. Online Engine
+The online version of Step-Video-T2V is available on [跃问视频](https://yuewen.cn/videos), where you can also explore some impressive examples.
+
+## 7. Citation
+```
+@misc{ma2025stepvideot2vtechnicalreportpractice,
+      title={Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model}, 
+      author={Guoqing Ma and Haoyang Huang and Kun Yan and Liangyu Chen and Nan Duan and Shengming Yin and Changyi Wan and Ranchen Ming and Xiaoniu Song and Xing Chen and Yu Zhou and Deshan Sun and Deyu Zhou and Jian Zhou and Kaijun Tan and Kang An and Mei Chen and Wei Ji and Qiling Wu and Wen Sun and Xin Han and Yanan Wei and Zheng Ge and Aojie Li and Bin Wang and Bizhu Huang and Bo Wang and Brian Li and Changxing Miao and Chen Xu and Chenfei Wu and Chenguang Yu and Dapeng Shi and Dingyuan Hu and Enle Liu and Gang Yu and Ge Yang and Guanzhe Huang and Gulin Yan and Haiyang Feng and Hao Nie and Haonan Jia and Hanpeng Hu and Hanqi Chen and Haolong Yan and Heng Wang and Hongcheng Guo and Huilin Xiong and Huixin Xiong and Jiahao Gong and Jianchang Wu and Jiaoren Wu and Jie Wu and Jie Yang and Jiashuai Liu and Jiashuo Li and Jingyang Zhang and Junjing Guo and Junzhe Lin and Kaixiang Li and Lei Liu and Lei Xia and Liang Zhao and Liguo Tan and Liwen Huang and Liying Shi and Ming Li and Mingliang Li and Muhua Cheng and Na Wang and Qiaohui Chen and Qinglin He and Qiuyan Liang and Quan Sun and Ran Sun and Rui Wang and Shaoliang Pang and Shiliang Yang and Sitong Liu and Siqi Liu and Shuli Gao and Tiancheng Cao and Tianyu Wang and Weipeng Ming and Wenqing He and Xu Zhao and Xuelin Zhang and Xianfang Zeng and Xiaojia Liu and Xuan Yang and Yaqi Dai and Yanbo Yu and Yang Li and Yineng Deng and Yingming Wang and Yilei Wang and Yuanwei Lu and Yu Chen and Yu Luo and Yuchu Luo and Yuhe Yin and Yuheng Feng and Yuxiang Yang and Zecheng Tang and Zekai Zhang and Zidong Yang and Binxing Jiao and Jiansheng Chen and Jing Li and Shuchang Zhou and Xiangyu Zhang and Xinhao Zhang and Yibo Zhu and Heung-Yeung Shum and Daxin Jiang},
+      year={2025},
+      eprint={2502.10248},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2502.10248}, 
+}
+```
+
+## 8. Acknowledgement
+- We would like to express our sincere thanks to the [xDiT](https://github.com/xdit-project/xDiT) team for their invaluable support and parallelization strategy. 
+- Our code will be integrated into the official repository of [Huggingface/Diffusers](https://github.com/huggingface/diffusers).
+- We thank the [FastVideo](https://github.com/hao-ai-lab/FastVideo) team for their continued collaboration and look forward to launching inference acceleration solutions together in the near future.

hunyuan_clip/clip_text_encoder/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "hfl/chinese-roberta-wwm-ext-large",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 47020
+}

hunyuan_clip/clip_text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77fd65c751513310fe575e0ef59963743f89a4955ee5c79d7468157b27e83c51
+size 3936679395

hunyuan_clip/tokenizer/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

hunyuan_clip/tokenizer/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "name_or_path": "hfl/chinese-roberta-wwm-ext",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/chenweifeng/.cache/huggingface/hub/models--hfl--chinese-roberta-wwm-ext/snapshots/5c58d0b8ec1d9014354d691c538661bf00bfdb44/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]",
+  "model_max_length": 77
+}

lib/liboptimus_ths-torch2.2-cu121.cpython-310-x86_64-linux-gnu.so

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2201371a93b103f7a5bc87dc8b9f1d781a81fc272d5a8ac8c1a82877aea98661
+size 3994424

lib/liboptimus_ths-torch2.3-cu121.cpython-310-x86_64-linux-gnu.so

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43a22318a90192fe37e167689bbfda9321b7eeb004f8cbafe671fe99204f1fe
+size 3998552

lib/liboptimus_ths-torch2.5-cu124.cpython-310-x86_64-linux-gnu.so

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab934f8ca508ec04b252674d3654628b1eea39ce7834f004a71c6fae399b9ce6
+size 4002768

model_index.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "StepVideoPipeline",
+  "_diffusers_version": "0.31.0",
+  "scheduler": [
+    "stepvideo.diffusion.scheduler",
+    "FlowMatchDiscreteScheduler"
+  ],
+  "transformer": [
+    "stepvideo.modules.model",
+    "StepVideoModel"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,8 @@
+{
+  "_class_name": "FlowMatchDiscreteScheduler",
+  "_diffusers_version": "0.31.0",
+  "device": null,
+  "num_train_timesteps": 1000,
+  "reverse": false,
+  "solver": "euler"
+}

step_llm/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/mnt/shared-storage/tenant/opensource/step_llm",
+  "allow_transformer_engine": false,
+  "architectures": [
+    "Step1Model"
+  ],
+  "attention_dropout": 0.0,
+  "attention_impl": "GQA",
+  "base_batch_size": 128,
+  "embedding_weights_in_fp32": false,
+  "ffn_hidden_size": 16896,
+  "fp32_residual_connection": false,
+  "hidden_dropout": 0.0,
+  "hidden_size": 6144,
+  "kv_channels": 128,
+  "layernorm_epsilon": 1e-05,
+  "max_position_embeddings": 16384,
+  "num_attention_groups": 8,
+  "num_attention_heads": 48,
+  "num_layers": 48,
+  "orig_vocab_size": 65536,
+  "overlap_p2p_comm": true,
+  "padded_vocab_size": 65536,
+  "params_dtype": "torch.bfloat16",
+  "seq_length": 16384,
+  "swiglu_recompute_silu_dot": true,
+  "tokens_to_generate": 512,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_flash_attn": true,
+  "virtual_pipeline_model_parallel_size": 3
+}

step_llm/model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc79bad96b5f9fdd56106864c56fdc7955627062de4d023ee99944ddac0c930
+size 4976668520

step_llm/model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2112d1a56602599f5cd9c8f3e80b47a9df5861b5a03c565fbd29f4cbc8b7acc
+size 4794241224

step_llm/model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7bd774bd5c30b51ae342ae92ae9d2706d631bf4ee817fd0997ccc1b0b651c3
+size 4794241248

step_llm/model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d9d688d310ef2098b9f219d7fd84245d13a46b969497de5c111cdd3196a86e
+size 4794241248

step_llm/model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe129667571adf93917a54839a7af52f702bd7c7e63aee34912228507d6c1dc
+size 4794241248

step_llm/model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4f01bd89d7e047de600579071e6e5e17dfff7aaf8143323ab2989ec840db26
+size 4794241248

step_llm/model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e9ba842a20b0a0fe9bc00646135b5c82cf544c6fba83aaa3630748f9c9ada9
+size 4794241248

step_llm/model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c5fd462b5422bdb8665fcb2e4c461cbdbd39f92c9b5e677f87a77044c259af
+size 4794241248

step_llm/model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d707aa08cd795a137e6b18558658e65bd9969a27a8aca34d201e3a1b1a68fa4e
+size 622879216

step_llm/model.safetensors.index.json

@@ -0,0 +1,296 @@
+{
+  "metadata": {
+    "total_size": 39159201792
+  },
+  "weight_map": {
+    "tok_embeddings.word_embeddings.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.0.attention.wo.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.0.attention.wqkv.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.0.attention_norm.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.0.feed_forward.w1.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.0.feed_forward.w2.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.0.ffn_norm.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.1.attention.wo.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.1.attention.wqkv.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.1.attention_norm.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.1.feed_forward.w1.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.1.feed_forward.w2.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.1.ffn_norm.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.10.attention.wo.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.10.attention.wqkv.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.10.attention_norm.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.10.feed_forward.w1.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.10.feed_forward.w2.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.10.ffn_norm.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.11.attention.wo.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.11.attention.wqkv.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.11.attention_norm.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.11.feed_forward.w1.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.11.feed_forward.w2.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.11.ffn_norm.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.12.attention.wo.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.12.attention.wqkv.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.12.attention_norm.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.12.feed_forward.w1.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.12.feed_forward.w2.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.12.ffn_norm.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.13.attention.wo.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.13.attention.wqkv.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.13.attention_norm.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.13.feed_forward.w1.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.13.feed_forward.w2.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.13.ffn_norm.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.14.attention.wo.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.14.attention.wqkv.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.14.attention_norm.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.14.feed_forward.w1.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.14.feed_forward.w2.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.14.ffn_norm.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.15.attention.wo.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.15.attention.wqkv.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.15.attention_norm.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.15.feed_forward.w1.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.15.feed_forward.w2.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.15.ffn_norm.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.16.attention.wo.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.16.attention.wqkv.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.16.attention_norm.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.16.feed_forward.w1.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.16.feed_forward.w2.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.16.ffn_norm.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.17.attention.wo.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.17.attention.wqkv.weight": "model-00003-of-00009.safetensors",
+    "transformer.layers.17.attention_norm.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.17.feed_forward.w1.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.17.feed_forward.w2.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.17.ffn_norm.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.18.attention.wo.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.18.attention.wqkv.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.18.attention_norm.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.18.feed_forward.w1.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.18.feed_forward.w2.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.18.ffn_norm.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.19.attention.wo.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.19.attention.wqkv.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.19.attention_norm.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.19.feed_forward.w1.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.19.feed_forward.w2.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.19.ffn_norm.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.2.attention.wo.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.2.attention.wqkv.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.2.attention_norm.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.2.feed_forward.w1.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.2.feed_forward.w2.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.2.ffn_norm.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.20.attention.wo.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.20.attention.wqkv.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.20.attention_norm.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.20.feed_forward.w1.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.20.feed_forward.w2.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.20.ffn_norm.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.21.attention.wo.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.21.attention.wqkv.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.21.attention_norm.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.21.feed_forward.w1.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.21.feed_forward.w2.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.21.ffn_norm.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.22.attention.wo.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.22.attention.wqkv.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.22.attention_norm.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.22.feed_forward.w1.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.22.feed_forward.w2.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.22.ffn_norm.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.23.attention.wo.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.23.attention.wqkv.weight": "model-00004-of-00009.safetensors",
+    "transformer.layers.23.attention_norm.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.23.feed_forward.w1.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.23.feed_forward.w2.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.23.ffn_norm.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.24.attention.wo.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.24.attention.wqkv.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.24.attention_norm.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.24.feed_forward.w1.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.24.feed_forward.w2.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.24.ffn_norm.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.25.attention.wo.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.25.attention.wqkv.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.25.attention_norm.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.25.feed_forward.w1.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.25.feed_forward.w2.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.25.ffn_norm.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.26.attention.wo.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.26.attention.wqkv.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.26.attention_norm.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.26.feed_forward.w1.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.26.feed_forward.w2.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.26.ffn_norm.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.27.attention.wo.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.27.attention.wqkv.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.27.attention_norm.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.27.feed_forward.w1.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.27.feed_forward.w2.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.27.ffn_norm.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.28.attention.wo.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.28.attention.wqkv.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.28.attention_norm.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.28.feed_forward.w1.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.28.feed_forward.w2.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.28.ffn_norm.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.29.attention.wo.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.29.attention.wqkv.weight": "model-00005-of-00009.safetensors",
+    "transformer.layers.29.attention_norm.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.29.feed_forward.w1.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.29.feed_forward.w2.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.29.ffn_norm.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.3.attention.wo.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.3.attention.wqkv.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.3.attention_norm.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.3.feed_forward.w1.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.3.feed_forward.w2.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.3.ffn_norm.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.30.attention.wo.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.30.attention.wqkv.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.30.attention_norm.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.30.feed_forward.w1.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.30.feed_forward.w2.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.30.ffn_norm.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.31.attention.wo.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.31.attention.wqkv.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.31.attention_norm.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.31.feed_forward.w1.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.31.feed_forward.w2.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.31.ffn_norm.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.32.attention.wo.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.32.attention.wqkv.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.32.attention_norm.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.32.feed_forward.w1.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.32.feed_forward.w2.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.32.ffn_norm.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.33.attention.wo.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.33.attention.wqkv.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.33.attention_norm.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.33.feed_forward.w1.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.33.feed_forward.w2.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.33.ffn_norm.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.34.attention.wo.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.34.attention.wqkv.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.34.attention_norm.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.34.feed_forward.w1.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.34.feed_forward.w2.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.34.ffn_norm.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.35.attention.wo.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.35.attention.wqkv.weight": "model-00006-of-00009.safetensors",
+    "transformer.layers.35.attention_norm.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.35.feed_forward.w1.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.35.feed_forward.w2.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.35.ffn_norm.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.36.attention.wo.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.36.attention.wqkv.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.36.attention_norm.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.36.feed_forward.w1.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.36.feed_forward.w2.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.36.ffn_norm.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.37.attention.wo.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.37.attention.wqkv.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.37.attention_norm.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.37.feed_forward.w1.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.37.feed_forward.w2.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.37.ffn_norm.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.38.attention.wo.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.38.attention.wqkv.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.38.attention_norm.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.38.feed_forward.w1.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.38.feed_forward.w2.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.38.ffn_norm.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.39.attention.wo.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.39.attention.wqkv.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.39.attention_norm.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.39.feed_forward.w1.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.39.feed_forward.w2.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.39.ffn_norm.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.4.attention.wo.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.4.attention.wqkv.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.4.attention_norm.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.4.feed_forward.w1.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.4.feed_forward.w2.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.4.ffn_norm.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.40.attention.wo.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.40.attention.wqkv.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.40.attention_norm.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.40.feed_forward.w1.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.40.feed_forward.w2.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.40.ffn_norm.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.41.attention.wo.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.41.attention.wqkv.weight": "model-00007-of-00009.safetensors",
+    "transformer.layers.41.attention_norm.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.41.feed_forward.w1.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.41.feed_forward.w2.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.41.ffn_norm.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.42.attention.wo.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.42.attention.wqkv.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.42.attention_norm.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.42.feed_forward.w1.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.42.feed_forward.w2.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.42.ffn_norm.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.43.attention.wo.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.43.attention.wqkv.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.43.attention_norm.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.43.feed_forward.w1.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.43.feed_forward.w2.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.43.ffn_norm.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.44.attention.wo.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.44.attention.wqkv.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.44.attention_norm.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.44.feed_forward.w1.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.44.feed_forward.w2.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.44.ffn_norm.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.45.attention.wo.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.45.attention.wqkv.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.45.attention_norm.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.45.feed_forward.w1.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.45.feed_forward.w2.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.45.ffn_norm.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.46.attention.wo.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.46.attention.wqkv.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.46.attention_norm.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.46.feed_forward.w1.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.46.feed_forward.w2.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.46.ffn_norm.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.47.attention.wo.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.47.attention.wqkv.weight": "model-00008-of-00009.safetensors",
+    "transformer.layers.47.attention_norm.weight": "model-00009-of-00009.safetensors",
+    "transformer.layers.47.feed_forward.w1.weight": "model-00009-of-00009.safetensors",
+    "transformer.layers.47.feed_forward.w2.weight": "model-00009-of-00009.safetensors",
+    "transformer.layers.47.ffn_norm.weight": "model-00009-of-00009.safetensors",
+    "transformer.layers.5.attention.wo.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.5.attention.wqkv.weight": "model-00001-of-00009.safetensors",
+    "transformer.layers.5.attention_norm.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.5.feed_forward.w1.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.5.feed_forward.w2.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.5.ffn_norm.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.6.attention.wo.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.6.attention.wqkv.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.6.attention_norm.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.6.feed_forward.w1.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.6.feed_forward.w2.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.6.ffn_norm.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.7.attention.wo.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.7.attention.wqkv.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.7.attention_norm.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.7.feed_forward.w1.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.7.feed_forward.w2.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.7.ffn_norm.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.8.attention.wo.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.8.attention.wqkv.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.8.attention_norm.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.8.feed_forward.w1.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.8.feed_forward.w2.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.8.ffn_norm.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.9.attention.wo.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.9.attention.wqkv.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.9.attention_norm.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.9.feed_forward.w1.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.9.feed_forward.w2.weight": "model-00002-of-00009.safetensors",
+    "transformer.layers.9.ffn_norm.weight": "model-00002-of-00009.safetensors"
+  }
+}

step_llm/step1_chat_tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae238f74162b98d3384eb1ceef143ed67f822528a6b0d6c5e351f87d7f4a651a
+size 1053360

transformer/config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "StepVideoModel",
+  "_diffusers_version": "0.31.0",
+  "attention_head_dim": 128,
+  "attention_type": "parallel",
+  "caption_channels": [
+    6144,
+    1024
+  ],
+  "dropout": 0.0,
+  "in_channels": 64,
+  "norm_elementwise_affine": false,
+  "norm_eps": 1e-06,
+  "norm_type": "ada_norm_single",
+  "num_attention_heads": 48,
+  "num_layers": 48,
+  "out_channels": 64,
+  "patch_size": 1,
+  "use_additional_conditions": true
+}

transformer/diffusion_pytorch_model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4f9537f8df1eb848fe0d80029b753be38f9936c9ee85d64104a0691ec6884fc
+size 9968406384

transformer/diffusion_pytorch_model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb37f6bfedeffe7bf6af05c101f8635a01f7d9ea518649f3da30336a0e089875
+size 9966673176

transformer/diffusion_pytorch_model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:021d2ce812b95e194d4a3367a1adccd9ec78e909bdc02067ea8a4fb7a4ccdf40
+size 9966672264

transformer/diffusion_pytorch_model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2724ddf7e417a56ef9f042bb9213de02038485ca59e226ba7e6bfe07090559
+size 9966770888

transformer/diffusion_pytorch_model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3edb2d87133a1abef3aa5f577271ef98be1c384910fc787e5ae2a639a260c889
+size 9966697872

transformer/diffusion_pytorch_model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb92dc2c29af885db5d598557416dfa1a0b26395153d737d6e13751833f1832
+size 8929280064

transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,796 @@
+{
+  "metadata": {
+    "total_size": 58764411008
+  },
+  "weight_map": {
+    "adaln_single.emb.motion_score_embedder.linear_1.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "adaln_single.emb.motion_score_embedder.linear_1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "adaln_single.emb.motion_score_embedder.linear_2.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "adaln_single.emb.motion_score_embedder.linear_2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "adaln_single.emb.timestep_embedder.linear_1.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "adaln_single.emb.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "adaln_single.emb.timestep_embedder.linear_2.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "adaln_single.emb.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "adaln_single.linear.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "adaln_single.linear.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "caption_projection.linear_1.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "caption_projection.linear_1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "caption_projection.linear_2.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "caption_projection.linear_2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "clip_projection.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "clip_projection.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "pos_embed.proj.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "pos_embed.proj.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "proj_out.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "scale_shift_table": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.attn1.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.attn1.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.attn1.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.attn1.wqkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.attn2.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.attn2.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.attn2.wkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.attn2.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.attn2.wq.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.norm1.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.norm2.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.0.scale_shift_table": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.attn1.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.attn1.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.attn1.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.attn1.wqkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.attn2.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.attn2.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.attn2.wkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.attn2.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.attn2.wq.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.norm1.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.norm2.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.1.scale_shift_table": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.10.attn1.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.attn1.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.attn1.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.attn1.wqkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.attn2.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.attn2.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.attn2.wkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.attn2.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.attn2.wq.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.norm1.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.norm2.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.10.scale_shift_table": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.attn1.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.attn1.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.attn1.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.attn1.wqkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.attn2.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.attn2.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.attn2.wkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.attn2.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.attn2.wq.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.norm1.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.norm2.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.11.scale_shift_table": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.attn1.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.attn1.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.attn1.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.attn1.wqkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.attn2.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.attn2.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.attn2.wkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.attn2.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.attn2.wq.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.norm1.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.norm2.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.12.scale_shift_table": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.attn1.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.attn1.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.attn1.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.attn1.wqkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.attn2.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.attn2.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.attn2.wkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.attn2.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.attn2.wq.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.norm1.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.norm2.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.13.scale_shift_table": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.attn1.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.attn1.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.attn1.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.attn1.wqkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.attn2.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.attn2.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.attn2.wkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.attn2.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.attn2.wq.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.norm1.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.norm2.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.14.scale_shift_table": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.attn1.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.attn1.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.attn1.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.attn1.wqkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.attn2.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.attn2.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.attn2.wkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.attn2.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.attn2.wq.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.norm1.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.norm2.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.15.scale_shift_table": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.attn1.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.attn1.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.attn1.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.attn1.wqkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.attn2.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.attn2.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.attn2.wkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.attn2.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.attn2.wq.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.16.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.16.norm1.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.norm2.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.16.scale_shift_table": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.17.attn1.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.attn1.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.attn1.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.attn1.wqkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.attn2.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.attn2.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.attn2.wkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.attn2.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.attn2.wq.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.norm1.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.norm2.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.17.scale_shift_table": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.attn1.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.attn1.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.attn1.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.attn1.wqkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.attn2.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.attn2.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.attn2.wkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.attn2.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.attn2.wq.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.norm1.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.norm2.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.18.scale_shift_table": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.attn1.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.attn1.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.attn1.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.attn1.wqkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.attn2.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.attn2.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.attn2.wkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.attn2.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.attn2.wq.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.norm1.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.norm2.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.19.scale_shift_table": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.2.attn1.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.attn1.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.attn1.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.attn1.wqkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.attn2.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.attn2.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.attn2.wkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.attn2.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.attn2.wq.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.norm1.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.norm2.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.2.scale_shift_table": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.20.attn1.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.attn1.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.attn1.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.attn1.wqkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.attn2.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.attn2.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.attn2.wkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.attn2.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.attn2.wq.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.norm1.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.norm2.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.20.scale_shift_table": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.attn1.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.attn1.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.attn1.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.attn1.wqkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.attn2.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.attn2.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.attn2.wkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.attn2.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.attn2.wq.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.norm1.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.norm2.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.21.scale_shift_table": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.attn1.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.attn1.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.attn1.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.attn1.wqkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.attn2.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.attn2.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.attn2.wkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.attn2.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.attn2.wq.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.norm1.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.norm2.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.22.scale_shift_table": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.attn1.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.attn1.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.attn1.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.attn1.wqkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.attn2.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.attn2.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.attn2.wkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.attn2.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.attn2.wq.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.norm1.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.norm2.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.23.scale_shift_table": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.attn1.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.attn1.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.attn1.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.attn1.wqkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.attn2.k_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.attn2.q_norm.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.attn2.wkv.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.attn2.wo.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.attn2.wq.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.24.norm1.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.norm1.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.norm2.bias": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.norm2.weight": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.24.scale_shift_table": "diffusion_pytorch_model-00003-of-00006.safetensors",
+    "transformer_blocks.25.attn1.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.attn1.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.attn1.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.attn1.wqkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.attn2.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.attn2.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.attn2.wkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.attn2.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.attn2.wq.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.norm1.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.norm2.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.25.scale_shift_table": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.attn1.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.attn1.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.attn1.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.attn1.wqkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.attn2.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.attn2.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.attn2.wkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.attn2.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.attn2.wq.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.norm1.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.norm2.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.26.scale_shift_table": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.attn1.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.attn1.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.attn1.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.attn1.wqkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.attn2.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.attn2.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.attn2.wkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.attn2.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.attn2.wq.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.norm1.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.norm2.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.27.scale_shift_table": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.attn1.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.attn1.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.attn1.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.attn1.wqkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.attn2.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.attn2.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.attn2.wkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.attn2.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.attn2.wq.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.norm1.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.norm2.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.28.scale_shift_table": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.attn1.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.attn1.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.attn1.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.attn1.wqkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.attn2.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.attn2.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.attn2.wkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.attn2.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.attn2.wq.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.norm1.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.norm2.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.29.scale_shift_table": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.3.attn1.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.attn1.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.attn1.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.attn1.wqkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.attn2.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.attn2.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.attn2.wkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.attn2.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.attn2.wq.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.norm1.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.norm2.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.3.scale_shift_table": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.30.attn1.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.attn1.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.attn1.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.attn1.wqkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.attn2.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.attn2.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.attn2.wkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.attn2.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.attn2.wq.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.norm1.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.norm2.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.30.scale_shift_table": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.attn1.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.attn1.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.attn1.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.attn1.wqkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.attn2.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.attn2.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.attn2.wkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.attn2.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.attn2.wq.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.norm1.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.norm2.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.31.scale_shift_table": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.attn1.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.attn1.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.attn1.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.attn1.wqkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.attn2.k_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.attn2.q_norm.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.attn2.wkv.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.attn2.wo.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.attn2.wq.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.ff.net.0.proj.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.ff.net.2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.norm1.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.norm2.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.norm2.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.32.scale_shift_table": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.33.attn1.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.attn1.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.attn1.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.attn1.wqkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.attn2.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.attn2.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.attn2.wkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.attn2.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.attn2.wq.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.norm1.bias": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.33.norm1.weight": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.33.norm2.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.33.scale_shift_table": "diffusion_pytorch_model-00004-of-00006.safetensors",
+    "transformer_blocks.34.attn1.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.attn1.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.attn1.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.attn1.wqkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.attn2.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.attn2.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.attn2.wkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.attn2.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.attn2.wq.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.norm1.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.norm2.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.34.scale_shift_table": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.attn1.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.attn1.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.attn1.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.attn1.wqkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.attn2.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.attn2.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.attn2.wkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.attn2.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.attn2.wq.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.norm1.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.norm2.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.35.scale_shift_table": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.attn1.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.attn1.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.attn1.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.attn1.wqkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.attn2.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.attn2.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.attn2.wkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.attn2.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.attn2.wq.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.norm1.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.norm2.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.36.scale_shift_table": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.attn1.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.attn1.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.attn1.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.attn1.wqkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.attn2.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.attn2.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.attn2.wkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.attn2.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.attn2.wq.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.norm1.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.norm2.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.37.scale_shift_table": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.attn1.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.attn1.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.attn1.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.attn1.wqkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.attn2.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.attn2.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.attn2.wkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.attn2.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.attn2.wq.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.norm1.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.norm2.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.38.scale_shift_table": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.attn1.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.attn1.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.attn1.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.attn1.wqkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.attn2.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.attn2.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.attn2.wkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.attn2.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.attn2.wq.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.norm1.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.norm2.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.39.scale_shift_table": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.4.attn1.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.attn1.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.attn1.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.attn1.wqkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.attn2.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.attn2.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.attn2.wkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.attn2.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.attn2.wq.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.norm1.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.norm2.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.4.scale_shift_table": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.40.attn1.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.attn1.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.attn1.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.attn1.wqkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.attn2.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.attn2.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.attn2.wkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.attn2.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.attn2.wq.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.ff.net.0.proj.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.ff.net.2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.norm1.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.norm2.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.40.scale_shift_table": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.41.attn1.k_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.41.attn1.q_norm.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.41.attn1.wo.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.41.attn1.wqkv.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.41.attn2.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.41.attn2.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.41.attn2.wkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.41.attn2.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.41.attn2.wq.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.41.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.41.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.41.norm1.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.41.norm1.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.41.norm2.bias": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.41.norm2.weight": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.41.scale_shift_table": "diffusion_pytorch_model-00005-of-00006.safetensors",
+    "transformer_blocks.42.attn1.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.attn1.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.attn1.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.attn1.wqkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.attn2.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.attn2.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.attn2.wkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.attn2.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.attn2.wq.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.norm1.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.norm1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.norm2.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.norm2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.42.scale_shift_table": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.attn1.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.attn1.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.attn1.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.attn1.wqkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.attn2.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.attn2.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.attn2.wkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.attn2.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.attn2.wq.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.norm1.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.norm1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.norm2.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.norm2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.43.scale_shift_table": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.attn1.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.attn1.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.attn1.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.attn1.wqkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.attn2.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.attn2.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.attn2.wkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.attn2.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.attn2.wq.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.norm1.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.norm1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.norm2.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.norm2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.44.scale_shift_table": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.attn1.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.attn1.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.attn1.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.attn1.wqkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.attn2.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.attn2.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.attn2.wkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.attn2.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.attn2.wq.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.norm1.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.norm1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.norm2.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.norm2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.45.scale_shift_table": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.attn1.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.attn1.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.attn1.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.attn1.wqkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.attn2.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.attn2.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.attn2.wkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.attn2.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.attn2.wq.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.norm1.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.norm1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.norm2.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.norm2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.46.scale_shift_table": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.attn1.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.attn1.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.attn1.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.attn1.wqkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.attn2.k_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.attn2.q_norm.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.attn2.wkv.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.attn2.wo.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.attn2.wq.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.ff.net.0.proj.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.ff.net.2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.norm1.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.norm1.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.norm2.bias": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.norm2.weight": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.47.scale_shift_table": "diffusion_pytorch_model-00006-of-00006.safetensors",
+    "transformer_blocks.5.attn1.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.attn1.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.attn1.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.attn1.wqkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.attn2.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.attn2.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.attn2.wkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.attn2.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.attn2.wq.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.norm1.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.norm2.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.5.scale_shift_table": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.attn1.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.attn1.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.attn1.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.attn1.wqkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.attn2.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.attn2.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.attn2.wkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.attn2.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.attn2.wq.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.norm1.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.norm2.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.6.scale_shift_table": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.attn1.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.attn1.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.attn1.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.attn1.wqkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.attn2.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.attn2.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.attn2.wkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.attn2.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.attn2.wq.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.norm1.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.norm2.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.7.scale_shift_table": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.8.attn1.k_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.8.attn1.q_norm.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.8.attn1.wo.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.8.attn1.wqkv.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.8.attn2.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.8.attn2.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.8.attn2.wkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.8.attn2.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.8.attn2.wq.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.8.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.8.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.8.norm1.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.8.norm1.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.8.norm2.bias": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.8.norm2.weight": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.8.scale_shift_table": "diffusion_pytorch_model-00001-of-00006.safetensors",
+    "transformer_blocks.9.attn1.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.attn1.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.attn1.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.attn1.wqkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.attn2.k_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.attn2.q_norm.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.attn2.wkv.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.attn2.wo.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.attn2.wq.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.norm1.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.norm1.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.norm2.bias": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.norm2.weight": "diffusion_pytorch_model-00002-of-00006.safetensors",
+    "transformer_blocks.9.scale_shift_table": "diffusion_pytorch_model-00002-of-00006.safetensors"
+  }
+}

vae/vae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb2747d01c482844712e2660a723c76d8f9f7031d85411a4eb74a5566daa88f
+size 1035340564

vae/vae_v2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8fa89118d7f615c4383e5820e060355ce8ebcd8865eca3f7797cb808b974cd
+size 1995304052