kimi000 commited on
Commit
e632326
·
verified ·
1 Parent(s): b1af34b

Add files using upload-large-folder tool

Browse files
Files changed (43) hide show
  1. .gitattributes +2 -0
  2. LICENSE.md +176 -0
  3. README.md +21 -0
  4. artifact_checksums.sha256 +41 -0
  5. demo.py +37 -0
  6. export_manifest.json +24 -0
  7. model_index.json +26 -0
  8. pipeline.py +27 -0
  9. scheduler/scheduler_config.json +18 -0
  10. smoke_512.png +3 -0
  11. text_encoder/config.json +68 -0
  12. text_encoder/generation_config.json +13 -0
  13. text_encoder/model-00001-of-00009.safetensors +3 -0
  14. text_encoder/model-00002-of-00009.safetensors +3 -0
  15. text_encoder/model-00003-of-00009.safetensors +3 -0
  16. text_encoder/model-00004-of-00009.safetensors +3 -0
  17. text_encoder/model-00005-of-00009.safetensors +3 -0
  18. text_encoder/model-00006-of-00009.safetensors +3 -0
  19. text_encoder/model-00007-of-00009.safetensors +3 -0
  20. text_encoder/model-00008-of-00009.safetensors +3 -0
  21. text_encoder/model-00009-of-00009.safetensors +3 -0
  22. text_encoder/model.safetensors.index.json +406 -0
  23. tokenizer/added_tokens.json +28 -0
  24. tokenizer/chat_template.jinja +89 -0
  25. tokenizer/merges.txt +0 -0
  26. tokenizer/special_tokens_map.json +31 -0
  27. tokenizer/tokenizer.json +3 -0
  28. tokenizer/tokenizer_config.json +239 -0
  29. tokenizer/vocab.json +0 -0
  30. transformer/config.json +24 -0
  31. transformer/diffusion_pytorch_model-00001-of-00009.safetensors +3 -0
  32. transformer/diffusion_pytorch_model-00002-of-00009.safetensors +3 -0
  33. transformer/diffusion_pytorch_model-00003-of-00009.safetensors +3 -0
  34. transformer/diffusion_pytorch_model-00004-of-00009.safetensors +3 -0
  35. transformer/diffusion_pytorch_model-00005-of-00009.safetensors +3 -0
  36. transformer/diffusion_pytorch_model-00006-of-00009.safetensors +3 -0
  37. transformer/diffusion_pytorch_model-00007-of-00009.safetensors +3 -0
  38. transformer/diffusion_pytorch_model-00008-of-00009.safetensors +3 -0
  39. transformer/diffusion_pytorch_model-00009-of-00009.safetensors +3 -0
  40. transformer/diffusion_pytorch_model.safetensors.index.json +176 -0
  41. vae/config.json +41 -0
  42. vae/diffusion_pytorch_model.safetensors +3 -0
  43. verification.json +18 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ smoke_512.png filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
LICENSE.md ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: black-forest-labs/FLUX.2-klein-base-4B
4
+ pipeline_tag: text-to-image
5
+ ---
6
+
7
+ # FLUX.2 Klein Base 4B AlphaGRPO checkpoint
8
+
9
+ This is a complete native Diffusers `Flux2KleinPipeline`. The EMA LoRA is
10
+ already merged into the transformer, so FAR and PEFT are not required for
11
+ inference.
12
+
13
+ Source experiment: `flux2_klein_base_4b_diffusionnft_alphagrpo_dvreward_alphagrpo20k_512px_20step_cfg4_16prompts_group14_7train_1dvreward_tp1_2node_nrt`
14
+
15
+ Source checkpoint: `step_600.pt`
16
+
17
+ Training profile: 512px, 20 rollout steps, CFG 4, AlphaGRPO DVReward.
18
+
19
+ ```bash
20
+ python demo.py --prompt "A red cube beside a blue glass sphere."
21
+ ```
artifact_checksums.sha256 ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ca02bc51900ab07789d1b70283329e7137f5af98f5161c23a1c81fc38a4af1fe LICENSE.md
2
+ b22eeabd66cb2e2bf78bd64b56dbe246b525ecd865bd48a35c35025c64f9fcfb README.md
3
+ 6e0cf32396382f34dab2345de02028cb9d3cdfd5d0e3bca65bab448acd7a8bc6 demo.py
4
+ fb32d65cf042de042bd14d7193d32e2d5023650081b3d478d2e509e400019dcd export_manifest.json
5
+ 0a39848175a01876c25ab7dcccb1f12b8ad5257687b0da4d690e2a80b26bb679 model_index.json
6
+ 41bc00fbd6370b7c2341c0e2de7efc17a9b4d63dcfb48fcab82b665bfd2aa17f pipeline.py
7
+ 5d5af7e00dad78642b2bd51ddad2ba0f2758dbef9fb441a3dbee5ceb2fbcb8e3 scheduler/scheduler_config.json
8
+ 1e70ee416ac074a4439b09472e89b5ad63f056abea86080a46abebf43e0aeb4f smoke_512.png
9
+ 5ef8ab0396a0e7bdca392bba52df1a67f097411ba67e359a63e9d059304cea4e text_encoder/config.json
10
+ 19d9395705449004ddebeeaf62841338a48cc8df85cddb1ca0b2c60396d95c96 text_encoder/generation_config.json
11
+ 57f8f125f877b5a94aa3264a03cd78a2b40c45331c851df4b42501813c98ba96 text_encoder/model-00001-of-00009.safetensors
12
+ b8dfce452c2ac782f536802eb830ce6adcda720b158afcb53fa45630b89a38b1 text_encoder/model-00002-of-00009.safetensors
13
+ 3eef84c4a964fdb059775c2515d91e3c8ab15fd65b46693f04b79aaa601adce6 text_encoder/model-00003-of-00009.safetensors
14
+ 969d70f61b9fcbd22ff93ed75dfa653115b78c36c293e85bdde85e2a30b856fe text_encoder/model-00004-of-00009.safetensors
15
+ d38ca8dca7de1cfce04f1551688b795b56f3e83c058a49a54f9e4ef070f580d9 text_encoder/model-00005-of-00009.safetensors
16
+ 3b124ab247c998e318620edf110a2b49f7289b4c344b56398f177cc16987a254 text_encoder/model-00006-of-00009.safetensors
17
+ 04a7a53a1c3a36aa6422ecd624d6b34b02c1cb27477c2ca66945aa6895ecdbd1 text_encoder/model-00007-of-00009.safetensors
18
+ 2a0e1f11748d3be73963261f19d368c7ca07c4d3392d2484122cb2e41e585ab7 text_encoder/model-00008-of-00009.safetensors
19
+ 54c5f906afe14357fb5a3db62944d7287163c4e332e7328196dab88b5237ef97 text_encoder/model-00009-of-00009.safetensors
20
+ 3413d0b85ca60ad69d033c826ddc12e185515a6e0783c83df0dfba9c3b0d657e text_encoder/model.safetensors.index.json
21
+ c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680 tokenizer/added_tokens.json
22
+ a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8 tokenizer/chat_template.jinja
23
+ 8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 tokenizer/merges.txt
24
+ 76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd tokenizer/special_tokens_map.json
25
+ aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 tokenizer/tokenizer.json
26
+ 443bfa629eb16387a12edbf92a76f6a6f10b2af3b53d87ba1550adfcf45f7fa0 tokenizer/tokenizer_config.json
27
+ ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 tokenizer/vocab.json
28
+ 95b5c882d3b652878bdf3447def1102f14957c4d672e4ec759ce6f5d6311affe transformer/config.json
29
+ f8c73adb3c6db244cce0ee39412c35eb61064ed119b38c5d674af2318c9bf8ad transformer/diffusion_pytorch_model-00001-of-00009.safetensors
30
+ eab60aad3cbee69725cc83b4533d1a0bc51b64525ab155f8ed51c5ca417722e8 transformer/diffusion_pytorch_model-00002-of-00009.safetensors
31
+ 76434abcdb649a32085d7c4688ffc26011179638d190a35200d39bed827dbddb transformer/diffusion_pytorch_model-00003-of-00009.safetensors
32
+ 124655f6b9123035e51d772d0f7926a18bfa8a21f59b2f53eb5fae97348b6a4e transformer/diffusion_pytorch_model-00004-of-00009.safetensors
33
+ d38a3063aded27a8e99295ad5974745cf82fa6a739ad4b82b77e5a7d1aad83c0 transformer/diffusion_pytorch_model-00005-of-00009.safetensors
34
+ a6f6278a75e3a265f2d720864962ab5258e9d4e37e3326963e8f766bd21b304a transformer/diffusion_pytorch_model-00006-of-00009.safetensors
35
+ 43b8c334c65ba82ea39ead2573afe7510159a47383b735ffedda474b214c4445 transformer/diffusion_pytorch_model-00007-of-00009.safetensors
36
+ 21be2c99eecd6b888d3f87fa4d7adc00573681db25e53d27fc43b2a3d72842d3 transformer/diffusion_pytorch_model-00008-of-00009.safetensors
37
+ 392c55726afb7db6643737d0dc63119068e86187550d4c34bc18e0fe8378732e transformer/diffusion_pytorch_model-00009-of-00009.safetensors
38
+ f2964d3cce66b54f2f1d82dcb6a7e097ed5ff9ab4aa523c89fb74b0571d38f04 transformer/diffusion_pytorch_model.safetensors.index.json
39
+ 190b52240604c890f8086c5c9c15356fe85bae26a2ce5e2cc7fcd5b1a46fec9b vae/config.json
40
+ ca70d2202afe6415bdbcb8793ba8cd99fd159cfe6192381504d6c4d3036e0f04 vae/diffusion_pytorch_model.safetensors
41
+ 0b209bbd0ee18a35c1acccc5f1a6c56250454b72963a45289688b483a3385102 verification.json
demo.py ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+ from __future__ import annotations
3
+
4
+ import argparse
5
+ from pathlib import Path
6
+
7
+ from pipeline import generate, load_pipeline
8
+
9
+
10
+ def main():
11
+ parser = argparse.ArgumentParser()
12
+ parser.add_argument("--model", default=str(Path(__file__).resolve().parent))
13
+ parser.add_argument("--prompt", required=True)
14
+ parser.add_argument("--output", default="output.png")
15
+ parser.add_argument("--height", type=int, default=512)
16
+ parser.add_argument("--width", type=int, default=512)
17
+ parser.add_argument("--steps", type=int, default=20)
18
+ parser.add_argument("--cfg", type=float, default=4.0)
19
+ parser.add_argument("--seed", type=int, default=0)
20
+ args = parser.parse_args()
21
+
22
+ pipe = load_pipeline(args.model)
23
+ image = generate(
24
+ pipe,
25
+ args.prompt,
26
+ height=args.height,
27
+ width=args.width,
28
+ steps=args.steps,
29
+ cfg=args.cfg,
30
+ seed=args.seed,
31
+ )
32
+ image.save(args.output)
33
+ print(args.output)
34
+
35
+
36
+ if __name__ == "__main__":
37
+ main()
export_manifest.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model": "/lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/hcai/workspace/code/.cache/huggingface/hub/models--black-forest-labs--FLUX.2-klein-base-4B/snapshots/a3b4f4849157f664bdbc776fd7453c2783562f4d",
3
+ "checkpoint": "/lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/hcai/workspace/code/junyiwu/FAR-Anyflow1.5/experiments/flux2_klein_base_4b_diffusionnft_alphagrpo_dvreward_alphagrpo20k_512px_20step_cfg4_16prompts_group14_7train_1dvreward_tp1_2node_nrt/models/step_600.pt",
4
+ "checkpoint_sha256": "7aee299d4aab3a878b59ef68f9d533bbcbd646ddeea79d40d0b4392eaeceaac6",
5
+ "diffusers_version": "0.39.0",
6
+ "dtype": "bfloat16",
7
+ "format": "diffusers-flux2-klein-pipeline",
8
+ "global_step": 600,
9
+ "lora_alpha": 64.0,
10
+ "lora_rank": 32,
11
+ "native_pipeline_class": "diffusers.Flux2KleinPipeline",
12
+ "native_transformer_class": "diffusers.Flux2Transformer2DModel",
13
+ "parameters": 3875544576,
14
+ "scheduler": {
15
+ "num_train_timesteps": 1000,
16
+ "stochastic_sampling": false,
17
+ "use_dynamic_shifting": true
18
+ },
19
+ "source_experiment": "flux2_klein_base_4b_diffusionnft_alphagrpo_dvreward_alphagrpo20k_512px_20step_cfg4_16prompts_group14_7train_1dvreward_tp1_2node_nrt",
20
+ "source_revision": "a3b4f4849157f664bdbc776fd7453c2783562f4d",
21
+ "tensor_keys": 169,
22
+ "torch_version": "2.9.1+cu128",
23
+ "weight": "ema"
24
+ }
model_index.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Flux2KleinPipeline",
3
+ "_diffusers_version": "0.39.0",
4
+ "_name_or_path": "/lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/hcai/workspace/code/.cache/huggingface/hub/models--black-forest-labs--FLUX.2-klein-base-4B/snapshots/a3b4f4849157f664bdbc776fd7453c2783562f4d",
5
+ "is_distilled": false,
6
+ "scheduler": [
7
+ "diffusers",
8
+ "FlowMatchEulerDiscreteScheduler"
9
+ ],
10
+ "text_encoder": [
11
+ "transformers",
12
+ "Qwen3ForCausalLM"
13
+ ],
14
+ "tokenizer": [
15
+ "transformers",
16
+ "Qwen2TokenizerFast"
17
+ ],
18
+ "transformer": [
19
+ "diffusers",
20
+ "Flux2Transformer2DModel"
21
+ ],
22
+ "vae": [
23
+ "diffusers",
24
+ "AutoencoderKLFlux2"
25
+ ]
26
+ }
pipeline.py ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """Inference helpers for the native Diffusers FLUX.2 Klein pipeline."""
2
+
3
+ from __future__ import annotations
4
+
5
+ import torch
6
+ from diffusers import Flux2KleinPipeline
7
+
8
+
9
+ def load_pipeline(model_path, device="cuda", dtype=torch.bfloat16):
10
+ pipe = Flux2KleinPipeline.from_pretrained(
11
+ model_path,
12
+ torch_dtype=dtype,
13
+ local_files_only=True,
14
+ )
15
+ return pipe.to(device)
16
+
17
+
18
+ def generate(pipe, prompt, *, height=512, width=512, steps=20, cfg=4.0, seed=0):
19
+ generator = torch.Generator(device=pipe.device).manual_seed(seed)
20
+ return pipe(
21
+ prompt=prompt,
22
+ height=height,
23
+ width=width,
24
+ num_inference_steps=steps,
25
+ guidance_scale=cfg,
26
+ generator=generator,
27
+ ).images[0]
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.39.0",
4
+ "base_image_seq_len": 256,
5
+ "base_shift": 0.5,
6
+ "invert_sigmas": false,
7
+ "max_image_seq_len": 4096,
8
+ "max_shift": 1.15,
9
+ "num_train_timesteps": 1000,
10
+ "shift": 3.0,
11
+ "shift_terminal": null,
12
+ "stochastic_sampling": false,
13
+ "time_shift_type": "exponential",
14
+ "use_beta_sigmas": false,
15
+ "use_dynamic_shifting": true,
16
+ "use_exponential_sigmas": false,
17
+ "use_karras_sigmas": false
18
+ }
smoke_512.png ADDED

Git LFS Details

  • SHA256: 1e70ee416ac074a4439b09472e89b5ad63f056abea86080a46abebf43e0aeb4f
  • Pointer size: 131 Bytes
  • Size of remote file: 377 kB
text_encoder/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2560,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 9728,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 40960,
54
+ "max_window_layers": 36,
55
+ "model_type": "qwen3",
56
+ "num_attention_heads": 32,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": null,
61
+ "rope_theta": 1000000,
62
+ "sliding_window": null,
63
+ "tie_word_embeddings": true,
64
+ "transformers_version": "4.57.3",
65
+ "use_cache": true,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 151936
68
+ }
text_encoder/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.3"
13
+ }
text_encoder/model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f8f125f877b5a94aa3264a03cd78a2b40c45331c851df4b42501813c98ba96
3
+ size 979775328
text_encoder/model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8dfce452c2ac782f536802eb830ce6adcda720b158afcb53fa45630b89a38b1
3
+ size 959496440
text_encoder/model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eef84c4a964fdb059775c2515d91e3c8ab15fd65b46693f04b79aaa601adce6
3
+ size 959506912
text_encoder/model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:969d70f61b9fcbd22ff93ed75dfa653115b78c36c293e85bdde85e2a30b856fe
3
+ size 959506952
text_encoder/model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d38ca8dca7de1cfce04f1551688b795b56f3e83c058a49a54f9e4ef070f580d9
3
+ size 988342064
text_encoder/model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b124ab247c998e318620edf110a2b49f7289b4c344b56398f177cc16987a254
3
+ size 998828440
text_encoder/model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04a7a53a1c3a36aa6422ecd624d6b34b02c1cb27477c2ca66945aa6895ecdbd1
3
+ size 988342792
text_encoder/model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0e1f11748d3be73963261f19d368c7ca07c4d3392d2484122cb2e41e585ab7
3
+ size 959496488
text_encoder/model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c5f906afe14357fb5a3db62944d7287163c4e332e7328196dab88b5237ef97
3
+ size 251686048
text_encoder/model.safetensors.index.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4022468096,
4
+ "total_size": 8044936192
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
13
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00009.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
16
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00009.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
24
+ "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
27
+ "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
35
+ "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
38
+ "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
46
+ "model.layers.11.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
49
+ "model.layers.11.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
57
+ "model.layers.12.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
60
+ "model.layers.12.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
68
+ "model.layers.13.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
71
+ "model.layers.13.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
79
+ "model.layers.14.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
82
+ "model.layers.14.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
90
+ "model.layers.15.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
93
+ "model.layers.15.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
101
+ "model.layers.16.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
104
+ "model.layers.16.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00005-of-00009.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
112
+ "model.layers.17.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
115
+ "model.layers.17.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
123
+ "model.layers.18.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
126
+ "model.layers.18.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
134
+ "model.layers.19.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
137
+ "model.layers.19.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
145
+ "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
148
+ "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
156
+ "model.layers.20.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
159
+ "model.layers.20.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00006-of-00009.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
167
+ "model.layers.21.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
170
+ "model.layers.21.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
178
+ "model.layers.22.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
181
+ "model.layers.22.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
189
+ "model.layers.23.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
192
+ "model.layers.23.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00009.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
200
+ "model.layers.24.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
203
+ "model.layers.24.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00007-of-00009.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
211
+ "model.layers.25.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
214
+ "model.layers.25.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
222
+ "model.layers.26.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
225
+ "model.layers.26.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
233
+ "model.layers.27.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
236
+ "model.layers.27.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
239
+ "model.layers.28.input_layernorm.weight": "model-00007-of-00009.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
241
+ "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
242
+ "model.layers.28.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
243
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
244
+ "model.layers.28.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
247
+ "model.layers.28.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
250
+ "model.layers.29.input_layernorm.weight": "model-00007-of-00009.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
252
+ "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
253
+ "model.layers.29.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
254
+ "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
255
+ "model.layers.29.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
258
+ "model.layers.29.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
266
+ "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
269
+ "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
272
+ "model.layers.30.input_layernorm.weight": "model-00008-of-00009.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
274
+ "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
275
+ "model.layers.30.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
276
+ "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
277
+ "model.layers.30.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
280
+ "model.layers.30.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
283
+ "model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
285
+ "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
286
+ "model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
287
+ "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
288
+ "model.layers.31.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
291
+ "model.layers.31.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
294
+ "model.layers.32.input_layernorm.weight": "model-00008-of-00009.safetensors",
295
+ "model.layers.32.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
296
+ "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
297
+ "model.layers.32.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
298
+ "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
299
+ "model.layers.32.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
300
+ "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
301
+ "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
302
+ "model.layers.32.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
305
+ "model.layers.33.input_layernorm.weight": "model-00008-of-00009.safetensors",
306
+ "model.layers.33.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
307
+ "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
308
+ "model.layers.33.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
309
+ "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
310
+ "model.layers.33.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
311
+ "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
312
+ "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
313
+ "model.layers.33.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
316
+ "model.layers.34.input_layernorm.weight": "model-00009-of-00009.safetensors",
317
+ "model.layers.34.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
318
+ "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
319
+ "model.layers.34.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
320
+ "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
321
+ "model.layers.34.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
322
+ "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
323
+ "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
324
+ "model.layers.34.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
327
+ "model.layers.35.input_layernorm.weight": "model-00009-of-00009.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
329
+ "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
330
+ "model.layers.35.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
331
+ "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
332
+ "model.layers.35.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
333
+ "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
334
+ "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
335
+ "model.layers.35.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
338
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
339
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
340
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
341
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
342
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
343
+ "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
344
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
345
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
346
+ "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
347
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
348
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
349
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
350
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
351
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
352
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
353
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
354
+ "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
355
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
356
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
357
+ "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
358
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
359
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
360
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
361
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
362
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
363
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
364
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
365
+ "model.layers.6.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
366
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
367
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
368
+ "model.layers.6.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
369
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
370
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
371
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
372
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
373
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
374
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
375
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
376
+ "model.layers.7.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
377
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
378
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
379
+ "model.layers.7.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
380
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
381
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
382
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors",
383
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
384
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
385
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
386
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
387
+ "model.layers.8.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
388
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
389
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
390
+ "model.layers.8.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
391
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
392
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
393
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors",
394
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
395
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
396
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
397
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
398
+ "model.layers.9.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
399
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
400
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
401
+ "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
402
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
403
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
404
+ "model.norm.weight": "model-00009-of-00009.safetensors"
405
+ }
406
+ }
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
transformer/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Flux2Transformer2DModel",
3
+ "_diffusers_version": "0.39.0",
4
+ "_name_or_path": "/lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/hcai/workspace/code/.cache/huggingface/hub/models--black-forest-labs--FLUX.2-klein-base-4B/snapshots/a3b4f4849157f664bdbc776fd7453c2783562f4d",
5
+ "attention_head_dim": 128,
6
+ "axes_dims_rope": [
7
+ 32,
8
+ 32,
9
+ 32,
10
+ 32
11
+ ],
12
+ "eps": 1e-06,
13
+ "guidance_embeds": false,
14
+ "in_channels": 128,
15
+ "joint_attention_dim": 7680,
16
+ "mlp_ratio": 3.0,
17
+ "num_attention_heads": 24,
18
+ "num_layers": 5,
19
+ "num_single_layers": 20,
20
+ "out_channels": null,
21
+ "patch_size": 1,
22
+ "rope_theta": 2000,
23
+ "timestep_guidance_channels": 256
24
+ }
transformer/diffusion_pytorch_model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c73adb3c6db244cce0ee39412c35eb61064ed119b38c5d674af2318c9bf8ad
3
+ size 993269776
transformer/diffusion_pytorch_model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab60aad3cbee69725cc83b4533d1a0bc51b64525ab155f8ed51c5ca417722e8
3
+ size 981472976
transformer/diffusion_pytorch_model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76434abcdb649a32085d7c4688ffc26011179638d190a35200d39bed827dbddb
3
+ size 830475616
transformer/diffusion_pytorch_model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124655f6b9123035e51d772d0f7926a18bfa8a21f59b2f53eb5fae97348b6a4e
3
+ size 981471160
transformer/diffusion_pytorch_model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d38a3063aded27a8e99295ad5974745cf82fa6a739ad4b82b77e5a7d1aad83c0
3
+ size 981471160
transformer/diffusion_pytorch_model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6f6278a75e3a265f2d720864962ab5258e9d4e37e3326963e8f766bd21b304a
3
+ size 981471168
transformer/diffusion_pytorch_model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b8c334c65ba82ea39ead2573afe7510159a47383b735ffedda474b214c4445
3
+ size 981471176
transformer/diffusion_pytorch_model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21be2c99eecd6b888d3f87fa4d7adc00573681db25e53d27fc43b2a3d72842d3
3
+ size 981471176
transformer/diffusion_pytorch_model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392c55726afb7db6643737d0dc63119068e86187550d4c34bc18e0fe8378732e
3
+ size 38535392
transformer/diffusion_pytorch_model.safetensors.index.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7751089152
4
+ },
5
+ "weight_map": {
6
+ "context_embedder.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
7
+ "double_stream_modulation_img.linear.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
8
+ "double_stream_modulation_txt.linear.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
9
+ "norm_out.linear.weight": "diffusion_pytorch_model-00009-of-00009.safetensors",
10
+ "proj_out.weight": "diffusion_pytorch_model-00009-of-00009.safetensors",
11
+ "single_stream_modulation.linear.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
12
+ "single_transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
13
+ "single_transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
14
+ "single_transformer_blocks.0.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
15
+ "single_transformer_blocks.0.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
16
+ "single_transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
17
+ "single_transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
18
+ "single_transformer_blocks.1.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
19
+ "single_transformer_blocks.1.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
20
+ "single_transformer_blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
21
+ "single_transformer_blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
22
+ "single_transformer_blocks.10.attn.to_out.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
23
+ "single_transformer_blocks.10.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
24
+ "single_transformer_blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
25
+ "single_transformer_blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
26
+ "single_transformer_blocks.11.attn.to_out.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
27
+ "single_transformer_blocks.11.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
28
+ "single_transformer_blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
29
+ "single_transformer_blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
30
+ "single_transformer_blocks.12.attn.to_out.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
31
+ "single_transformer_blocks.12.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
32
+ "single_transformer_blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
33
+ "single_transformer_blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
34
+ "single_transformer_blocks.13.attn.to_out.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
35
+ "single_transformer_blocks.13.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
36
+ "single_transformer_blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
37
+ "single_transformer_blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
38
+ "single_transformer_blocks.14.attn.to_out.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
39
+ "single_transformer_blocks.14.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
40
+ "single_transformer_blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
41
+ "single_transformer_blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
42
+ "single_transformer_blocks.15.attn.to_out.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
43
+ "single_transformer_blocks.15.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00007-of-00009.safetensors",
44
+ "single_transformer_blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
45
+ "single_transformer_blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
46
+ "single_transformer_blocks.16.attn.to_out.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
47
+ "single_transformer_blocks.16.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
48
+ "single_transformer_blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
49
+ "single_transformer_blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
50
+ "single_transformer_blocks.17.attn.to_out.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
51
+ "single_transformer_blocks.17.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
52
+ "single_transformer_blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
53
+ "single_transformer_blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
54
+ "single_transformer_blocks.18.attn.to_out.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
55
+ "single_transformer_blocks.18.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
56
+ "single_transformer_blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
57
+ "single_transformer_blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
58
+ "single_transformer_blocks.19.attn.to_out.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
59
+ "single_transformer_blocks.19.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00008-of-00009.safetensors",
60
+ "single_transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
61
+ "single_transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
62
+ "single_transformer_blocks.2.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
63
+ "single_transformer_blocks.2.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
64
+ "single_transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
65
+ "single_transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
66
+ "single_transformer_blocks.3.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
67
+ "single_transformer_blocks.3.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00004-of-00009.safetensors",
68
+ "single_transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
69
+ "single_transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
70
+ "single_transformer_blocks.4.attn.to_out.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
71
+ "single_transformer_blocks.4.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
72
+ "single_transformer_blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
73
+ "single_transformer_blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
74
+ "single_transformer_blocks.5.attn.to_out.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
75
+ "single_transformer_blocks.5.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
76
+ "single_transformer_blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
77
+ "single_transformer_blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
78
+ "single_transformer_blocks.6.attn.to_out.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
79
+ "single_transformer_blocks.6.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
80
+ "single_transformer_blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
81
+ "single_transformer_blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
82
+ "single_transformer_blocks.7.attn.to_out.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
83
+ "single_transformer_blocks.7.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00005-of-00009.safetensors",
84
+ "single_transformer_blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
85
+ "single_transformer_blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
86
+ "single_transformer_blocks.8.attn.to_out.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
87
+ "single_transformer_blocks.8.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
88
+ "single_transformer_blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
89
+ "single_transformer_blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
90
+ "single_transformer_blocks.9.attn.to_out.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
91
+ "single_transformer_blocks.9.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00006-of-00009.safetensors",
92
+ "time_guidance_embed.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
93
+ "time_guidance_embed.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
94
+ "transformer_blocks.0.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
95
+ "transformer_blocks.0.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
96
+ "transformer_blocks.0.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
97
+ "transformer_blocks.0.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
98
+ "transformer_blocks.0.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
99
+ "transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
100
+ "transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
101
+ "transformer_blocks.0.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
102
+ "transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
103
+ "transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
104
+ "transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
105
+ "transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
106
+ "transformer_blocks.0.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
107
+ "transformer_blocks.0.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
108
+ "transformer_blocks.0.ff_context.linear_in.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
109
+ "transformer_blocks.0.ff_context.linear_out.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
110
+ "transformer_blocks.1.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
111
+ "transformer_blocks.1.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
112
+ "transformer_blocks.1.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
113
+ "transformer_blocks.1.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
114
+ "transformer_blocks.1.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
115
+ "transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
116
+ "transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
117
+ "transformer_blocks.1.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
118
+ "transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
119
+ "transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
120
+ "transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
121
+ "transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00009.safetensors",
122
+ "transformer_blocks.1.ff.linear_in.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
123
+ "transformer_blocks.1.ff.linear_out.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
124
+ "transformer_blocks.1.ff_context.linear_in.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
125
+ "transformer_blocks.1.ff_context.linear_out.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
126
+ "transformer_blocks.2.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
127
+ "transformer_blocks.2.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
128
+ "transformer_blocks.2.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
129
+ "transformer_blocks.2.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
130
+ "transformer_blocks.2.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
131
+ "transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
132
+ "transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
133
+ "transformer_blocks.2.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
134
+ "transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
135
+ "transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
136
+ "transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
137
+ "transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
138
+ "transformer_blocks.2.ff.linear_in.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
139
+ "transformer_blocks.2.ff.linear_out.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
140
+ "transformer_blocks.2.ff_context.linear_in.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
141
+ "transformer_blocks.2.ff_context.linear_out.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
142
+ "transformer_blocks.3.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
143
+ "transformer_blocks.3.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
144
+ "transformer_blocks.3.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
145
+ "transformer_blocks.3.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
146
+ "transformer_blocks.3.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
147
+ "transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
148
+ "transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
149
+ "transformer_blocks.3.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
150
+ "transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
151
+ "transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
152
+ "transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
153
+ "transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00009.safetensors",
154
+ "transformer_blocks.3.ff.linear_in.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
155
+ "transformer_blocks.3.ff.linear_out.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
156
+ "transformer_blocks.3.ff_context.linear_in.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
157
+ "transformer_blocks.3.ff_context.linear_out.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
158
+ "transformer_blocks.4.attn.add_k_proj.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
159
+ "transformer_blocks.4.attn.add_q_proj.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
160
+ "transformer_blocks.4.attn.add_v_proj.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
161
+ "transformer_blocks.4.attn.norm_added_k.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
162
+ "transformer_blocks.4.attn.norm_added_q.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
163
+ "transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
164
+ "transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
165
+ "transformer_blocks.4.attn.to_add_out.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
166
+ "transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
167
+ "transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
168
+ "transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
169
+ "transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
170
+ "transformer_blocks.4.ff.linear_in.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
171
+ "transformer_blocks.4.ff.linear_out.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
172
+ "transformer_blocks.4.ff_context.linear_in.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
173
+ "transformer_blocks.4.ff_context.linear_out.weight": "diffusion_pytorch_model-00003-of-00009.safetensors",
174
+ "x_embedder.weight": "diffusion_pytorch_model-00001-of-00009.safetensors"
175
+ }
176
+ }
vae/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLFlux2",
3
+ "_diffusers_version": "0.39.0",
4
+ "_name_or_path": "/lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/hcai/workspace/code/.cache/huggingface/hub/models--black-forest-labs--FLUX.2-klein-base-4B/snapshots/a3b4f4849157f664bdbc776fd7453c2783562f4d/vae",
5
+ "act_fn": "silu",
6
+ "batch_norm_eps": 0.0001,
7
+ "batch_norm_momentum": 0.1,
8
+ "block_out_channels": [
9
+ 128,
10
+ 256,
11
+ 512,
12
+ 512
13
+ ],
14
+ "decoder_block_out_channels": null,
15
+ "down_block_types": [
16
+ "DownEncoderBlock2D",
17
+ "DownEncoderBlock2D",
18
+ "DownEncoderBlock2D",
19
+ "DownEncoderBlock2D"
20
+ ],
21
+ "force_upcast": true,
22
+ "in_channels": 3,
23
+ "latent_channels": 32,
24
+ "layers_per_block": 2,
25
+ "mid_block_add_attention": true,
26
+ "norm_num_groups": 32,
27
+ "out_channels": 3,
28
+ "patch_size": [
29
+ 2,
30
+ 2
31
+ ],
32
+ "sample_size": 1024,
33
+ "up_block_types": [
34
+ "UpDecoderBlock2D",
35
+ "UpDecoderBlock2D",
36
+ "UpDecoderBlock2D",
37
+ "UpDecoderBlock2D"
38
+ ],
39
+ "use_post_quant_conv": true,
40
+ "use_quant_conv": true
41
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca70d2202afe6415bdbcb8793ba8cd99fd159cfe6192381504d6c4d3036e0f04
3
+ size 168120878
verification.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "global_step": 600,
3
+ "offline_reload": true,
4
+ "scheduler": {
5
+ "num_train_timesteps": 1000,
6
+ "stochastic_sampling": false,
7
+ "use_dynamic_shifting": true
8
+ },
9
+ "smoke_guidance_scale": 4.0,
10
+ "smoke_image": "smoke_512.png",
11
+ "smoke_image_size": [
12
+ 512,
13
+ 512
14
+ ],
15
+ "smoke_seed": 0,
16
+ "smoke_steps": 4,
17
+ "strict_transformer_load": true
18
+ }