“12”

.gitattributes

@@ -1,35 +1,48 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2025 CogView Model Team @ Zhipu AI
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,137 @@
+---
+license: apache-2.0
+language:
+- zh
+- en
+base_model:
+- THUDM/glm-4-9b
+pipeline_tag: text-to-image
+library_name: diffusers
+---
+
+# CogView4-6B
+
+<p style="text-align: center;">
+  <div align="center">
+  <img src=https://github.com/THUDM/CogView4/raw/main/resources/logo.svg width="50%"/>
+  </div>
+  <p align="center">
+  <a href="https://huggingface.co/spaces/THUDM-HF-SPACE/CogView4">🤗 Space | </a> 
+  <a href="https://github.com/THUDM/CogView4">🌐 Github </a> | 
+  <a href="https://arxiv.org/pdf/2403.05121">📜 arxiv </a>
+</p>
+
+![img](https://raw.githubusercontent.com/THUDM/CogView4/refs/heads/main/resources/showcase.png)
+
+## Inference Requirements and Model Introduction
+
++ Resolution: Width and height must be between `512px` and `2048px`, divisible by `32`, and ensure the maximum number of pixels does not exceed `2^21` px.
++ Precision: BF16 / FP32 (FP16 is not supported as it will cause overflow resulting in completely black images)
+
+Using `BF16` precision with `batchsize=4` for testing, the memory usage is shown in the table below:
+
+| Resolution   | enable_model_cpu_offload OFF | enable_model_cpu_offload ON | enable_model_cpu_offload ON </br> Text Encoder 4bit | 
+|--------------|------------------------------|-----------------------------|----------------------------------------------------|
+| 512 * 512    | 33GB                         | 20GB                        | 13G                                                |
+| 1280 * 720   | 35GB                         | 20GB                        | 13G                                                |
+| 1024 * 1024  | 35GB                         | 20GB                        | 13G                                                |
+| 1920 * 1280  | 39GB                         | 20GB                        | 14G                                                |
+| 2048 * 2048  | 43GB                         | 21GB                        | 14G                                                |
+
+## Quick Start
+
+First, ensure you install the `diffusers` library from source.
+
+```shell
+pip install git+https://github.com/huggingface/diffusers.git
+cd diffusers
+pip install -e .
+```
+
+Then, run the following code:
+
+```python
+from diffusers import CogView4Pipeline
+pipe = CogView4Pipeline.from_pretrained("THUDM/CogView4-6B", torch_dtype=torch.bfloat16)
+
+# Open it for reduce GPU memory usage
+pipe.enable_model_cpu_offload()
+pipe.vae.enable_slicing()
+pipe.vae.enable_tiling()
+
+prompt = "A vibrant cherry red sports car sits proudly under the gleaming sun, its polished exterior smooth and flawless, casting a mirror-like reflection. The car features a low, aerodynamic body, angular headlights that gaze forward like predatory eyes, and a set of black, high-gloss racing rims that contrast starkly with the red. A subtle hint of chrome embellishes the grille and exhaust, while the tinted windows suggest a luxurious and private interior. The scene conveys a sense of speed and elegance, the car appearing as if it's about to burst into a sprint along a coastal road, with the ocean's azure waves crashing in the background."
+image = pipe(
+    prompt=prompt,
+    guidance_scale=3.5,
+    num_images_per_prompt=1,
+    num_inference_steps=50,
+    width=1024,
+    height=1024,
+).images[0]
+
+image.save("cogview4.png")
+```
+
+## Model Performance
+
+We've tested on multiple benchmarks and achieved the following scores:
+
+### dpg_bench
+
+| model | overall | global | entity | attribute | relation | other |
+|-------|---------|--------|--------|-----------|----------|-------|
+| sdxl | 74.65 | 83.27 | 82.43 | 80.91 | 86.76 | 80.41 |
+| pixart-alpha | 71.11 | 74.97 | 79.32 | 78.60 | 82.57 | 76.96 |
+| sd3-medium | 84.08 | 87.90 | **91.01** | 88.83 | 80.70 | 88.68 |
+| dalle-3 | 83.50 | **90.97** | 89.61 | 88.39 | 90.58 | 89.83 |
+| flux.1-dev | 83.79 | 85.80 | 86.79 | 89.98 | 90.04 | **89.90** |
+| **cogview4** | **85.13** | 83.85 | 90.35 | **91.17** | **91.14** | 87.29 |
+
+
+### Geneval
+
+| model | overall | single | two | counting | colors | position | Color attribution |
+|-------|---------|--------|-----|----------|--------|----------|------------------|
+| sdxl | 0.55 | 0.98 | 0.74 | 0.39 | 0.85 | 0.15 | 0.23 |
+| pixart-alpha | 0.48 | 0.98 | 0.50 | 0.44 | 0.80 | 0.08 | 0.07 |
+| sd3-meidum | **0.74** | **0.99** | **0.94** | **0.72** | **0.89** | 0.33 | **0.60** |
+| dall-e 3 | 0.67 | 0.96 | 0.87 | 0.47 | 0.83 | 0.43 | 0.45 |
+| flux.1-dev | 0.66 | 0.98 | 0.79 | 0.73 | 0.77 | 0.22 | 0.45 |
+| **cogview4** | 0.73 | **0.99** | 0.86 | 0.66 | 0.79 | **0.48** | 0.58 |
+
+### t2i_compbench
+
+| model | color | shape | texture | 2d-spatial | 3d-spatial | numeracy | Non-spatial clip | complex 3-in-1 |
+|-------|-------|-------|---------|------------|------------|----------|-----------------|---------------|
+| sdxl | 0.5879 | 0.4687 | 0.5299 | 0.2133 | 0.3566 | 0.4988 | 0.3119 | 0.3237 |
+| pixart-alpha | 0.6690 | 0.4927 | 0.6477 | 0.2064 | 0.3901 | 0.5058 | **0.3197** | 0.3433 |
+| sd3-medium | **0.8132** | 0.5885 | **0.7334** | **0.3200** | **0.4084** | 0.6174 | 0.3140 | 0.3771 |
+| dall-e 3 | 0.7785 | **0.6205** | 0.7036 | 0.2865 | 0.3744 | 0.5880 | 0.3003 | **0.3773** |
+| flux.1-dev | 0.7572 | 0.5066 | 0.6300 | 0.2700 | 0.3992 | 0.6165 | 0.3065 | 0.3628 |
+| **cogview4** | 0.7786 | 0.5880 | 0.6983 | 0.3075 | 0.3708 | **0.6626** | 0.3056 | 0.3869 |
+
+
+## Chinese Text Accuracy Evaluation
+
+| model | Precision | Recall | F1 Score | pick@4 |
+|-------|-----------|--------|----------|--------|
+| kolors | 0.6094 | 0.1886 | 0.2880 | 0.1633 |
+| **cogview4** | **0.6969** | **0.5532** | **0.6168** | **0.3265** |
+
+
+## Citation
+
+🌟 If you find our work helpful, please consider citing our paper and leaving valuable stars
+
+```
+@article{zheng2024cogview3,
+  title={Cogview3: Finer and faster text-to-image generation via relay diffusion},
+  author={Zheng, Wendi and Teng, Jiayan and Yang, Zhuoyi and Wang, Weihan and Chen, Jidong and Gu, Xiaotao and Dong, Yuxiao and Ding, Ming and Tang, Jie},
+  journal={arXiv preprint arXiv:2403.05121},
+  year={2024}
+}
+```
+
+## License
+
+This model is released under the [Apache 2.0 License](LICENSE).

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "CogView4Pipeline",
+  "_diffusers_version": "0.33.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "GlmModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "PreTrainedTokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "CogView4Transformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,17 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.33.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.25,
+  "invert_sigmas": false,
+  "max_image_seq_len": 4096,
+  "max_shift": 0.75,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": null,
+  "time_shift_type": "linear",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": true,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/share/home/zyx/Models/glm-4-9b-hf",
+  "architectures": [
+    "GlmModel"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 13696,
+  "max_position_embeddings": 8192,
+  "model_type": "glm",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1.5625e-07,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": true,
+  "vocab_size": 151552
+}

text_encoder/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d33a01dba14c62a0d5c471aba9f57902a1d6155080b2cf07e1360b9600fa60a8
+size 4984132960

text_encoder/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2913605db189102456ad417a4c38903fb038b9e9fb2a96c95e2de56da224667
+size 4895074376

text_encoder/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81bd5307c4f6175c7b080abad40eb869fafa263ff13c8550d6928330ae749a6
+size 4895074392

text_encoder/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:224b322bd87949a50d36adea784bb4d7203b219023b1efec1ee4fd5a7ad05056
+size 2784155192

text_encoder/model.safetensors.index.json

@@ -0,0 +1,449 @@
+{
+  "metadata": {
+    "total_size": 17558388736
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.33.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.34.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.34.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.34.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.34.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.35.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.35.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.35.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.35.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.36.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.36.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.36.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.36.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.37.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.37.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.37.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.37.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.38.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.38.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.38.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.38.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.39.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.39.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.39.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.39.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a7269d6daa6328de533def0082ff9d3a825bb89036cbcc665c324f941f67fbf
+size 19967863

tokenizer/tokenizer_config.json

@@ -0,0 +1,151 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_chatglm.ChatGLM4Tokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

transformer/config.json

@@ -0,0 +1,19 @@
+{
+  "_class_name": "CogView4Transformer2DModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "attention_head_dim": 128,
+  "condition_dim": 256,
+  "in_channels": 16,
+  "num_attention_heads": 32,
+  "num_layers": 28,
+  "out_channels": 16,
+  "patch_size": 2,
+  "pos_embed_max_size": 128,
+  "rope_axes_dim": [
+    256,
+    256
+  ],
+  "sample_size": 128,
+  "text_embed_dim": 4096,
+  "time_embed_dim": 512
+}

transformer/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe197664340943dd4b1ec30af012a4e136bdfd80c53e6520378928e084de8b0d
+size 4891433328

transformer/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63bc1152f337fb89ae9cfca5cb0d11451c5b456a345db9b008a14f129916beeb
+size 4984743304

transformer/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f196554fd09958d69e1491ed9a7d63a5a29384dbb73848d819285dd5124b478
+size 2862106776

transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,415 @@
+{
+  "metadata": {
+    "total_size": 12738236544
+  },
+  "weight_map": {
+    "norm_out.linear.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "norm_out.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "patch_embed.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "patch_embed.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "patch_embed.text_proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "patch_embed.text_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "proj_out.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "time_condition_embed.condition_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_condition_embed.condition_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_condition_embed.condition_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_condition_embed.condition_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_condition_embed.timestep_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_condition_embed.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_condition_embed.timestep_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_condition_embed.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.10.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.10.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.11.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.11.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.12.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.13.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.14.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.15.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.16.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.17.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.18.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.19.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.2.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.2.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.20.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.20.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.ff.net.2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.21.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.21.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "transformer_blocks.22.attn1.to_k.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn1.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn1.to_out.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn1.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn1.to_q.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn1.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn1.to_v.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.attn1.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.ff.net.0.proj.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.ff.net.2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.norm1.linear.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.22.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn1.to_k.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn1.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn1.to_out.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn1.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn1.to_q.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn1.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn1.to_v.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.attn1.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.ff.net.0.proj.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.ff.net.2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.norm1.linear.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.23.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn1.to_k.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn1.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn1.to_out.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn1.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn1.to_q.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn1.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn1.to_v.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.attn1.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.ff.net.0.proj.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.ff.net.2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.norm1.linear.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.24.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn1.to_k.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn1.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn1.to_out.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn1.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn1.to_q.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn1.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn1.to_v.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.attn1.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.ff.net.0.proj.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.ff.net.2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.norm1.linear.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.25.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn1.to_k.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn1.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn1.to_out.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn1.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn1.to_q.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn1.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn1.to_v.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.attn1.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.ff.net.0.proj.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.ff.net.2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.norm1.linear.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.26.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn1.to_k.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn1.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn1.to_out.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn1.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn1.to_q.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn1.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn1.to_v.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.attn1.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.ff.net.0.proj.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.ff.net.0.proj.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.ff.net.2.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.ff.net.2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.norm1.linear.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.27.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "transformer_blocks.3.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.3.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.4.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.5.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.6.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.7.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.8.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "transformer_blocks.9.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors"
+  }
+}

vae/config.json

@@ -0,0 +1,37 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.33.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    512,
+    1024,
+    1024
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 3,
+  "mid_block_add_attention": false,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 1.0,
+  "shift_factor": 0.0,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": false,
+  "use_quant_conv": false
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40aabe789e1591a3a3d8a2f598eda99f60a42275c410e7292a714b5270b97747
+size 812234342