cocktailpeanut commited on
Commit
75b047c
1 Parent(s): 9c0050b

Upload folder using huggingface_hub

Browse files
Files changed (46) hide show
  1. .DS_Store +0 -0
  2. .gitattributes +1 -0
  3. LICENSE.md +51 -0
  4. README.md +244 -0
  5. SD3.5L_Turbo_example_workflow.json +688 -0
  6. mmdit.png +0 -0
  7. model_index.json +40 -0
  8. scheduler/scheduler_config.json +6 -0
  9. sd3.5_large_turbo.safetensors +3 -0
  10. sd3.5_large_turbo_demo.png +3 -0
  11. text_encoder/config.json +24 -0
  12. text_encoder/model.fp16.safetensors +3 -0
  13. text_encoder/model.safetensors +3 -0
  14. text_encoder_2/config.json +24 -0
  15. text_encoder_2/model.fp16.safetensors +3 -0
  16. text_encoder_2/model.safetensors +3 -0
  17. text_encoder_3/config.json +31 -0
  18. text_encoder_3/model-00001-of-00002.safetensors +3 -0
  19. text_encoder_3/model-00002-of-00002.safetensors +3 -0
  20. text_encoder_3/model.fp16-00001-of-00002.safetensors +3 -0
  21. text_encoder_3/model.fp16-00002-of-00002.safetensors +3 -0
  22. text_encoder_3/model.safetensors.index.fp16.json +226 -0
  23. text_encoder_3/model.safetensors.index.json +226 -0
  24. text_encoders/README.md +11 -0
  25. text_encoders/clip_g.safetensors +3 -0
  26. text_encoders/clip_l.safetensors +3 -0
  27. text_encoders/t5xxl_fp16.safetensors +3 -0
  28. text_encoders/t5xxl_fp8_e4m3fn.safetensors +3 -0
  29. tokenizer/merges.txt +0 -0
  30. tokenizer/special_tokens_map.json +30 -0
  31. tokenizer/tokenizer_config.json +30 -0
  32. tokenizer/vocab.json +0 -0
  33. tokenizer_2/merges.txt +0 -0
  34. tokenizer_2/special_tokens_map.json +30 -0
  35. tokenizer_2/tokenizer_config.json +38 -0
  36. tokenizer_2/vocab.json +0 -0
  37. tokenizer_3/special_tokens_map.json +125 -0
  38. tokenizer_3/spiece.model +3 -0
  39. tokenizer_3/tokenizer.json +0 -0
  40. tokenizer_3/tokenizer_config.json +940 -0
  41. transformer/config.json +16 -0
  42. transformer/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  43. transformer/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  44. transformer/diffusion_pytorch_model.safetensors.index.json +0 -0
  45. vae/config.json +38 -0
  46. vae/diffusion_pytorch_model.safetensors +3 -0
.DS_Store ADDED
Binary file (6.15 kB). View file
 
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ sd3.5_large_turbo_demo.png filter=lfs diff=lfs merge=lfs -text
LICENSE.md ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ STABILITY AI COMMUNITY LICENSE AGREEMENT
2
+ Last Updated: July 5, 2024
3
+
4
+
5
+ I. INTRODUCTION
6
+
7
+ This Agreement applies to any individual person or entity ("You", "Your" or "Licensee") that uses or distributes any portion or element of the Stability AI Materials or Derivative Works thereof for any Research & Non-Commercial or Commercial purpose. Capitalized terms not otherwise defined herein are defined in Section V below.
8
+
9
+
10
+ This Agreement is intended to allow research, non-commercial, and limited commercial uses of the Models free of charge. In order to ensure that certain limited commercial uses of the Models continue to be allowed, this Agreement preserves free access to the Models for people or organizations generating annual revenue of less than US $1,000,000 (or local currency equivalent).
11
+
12
+
13
+ By clicking "I Accept" or by using or distributing or using any portion or element of the Stability Materials or Derivative Works, You agree that You have read, understood and are bound by the terms of this Agreement. If You are acting on behalf of a company, organization or other entity, then "You" includes you and that entity, and You agree that You: (i) are an authorized representative of such entity with the authority to bind such entity to this Agreement, and (ii) You agree to the terms of this Agreement on that entity's behalf.
14
+
15
+ II. RESEARCH & NON-COMMERCIAL USE LICENSE
16
+
17
+ Subject to the terms of this Agreement, Stability AI grants You a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable and royalty-free limited license under Stability AI's intellectual property or other rights owned by Stability AI embodied in the Stability AI Materials to use, reproduce, distribute, and create Derivative Works of, and make modifications to, the Stability AI Materials for any Research or Non-Commercial Purpose. "Research Purpose" means academic or scientific advancement, and in each case, is not primarily intended for commercial advantage or monetary compensation to You or others. "Non-Commercial Purpose" means any purpose other than a Research Purpose that is not primarily intended for commercial advantage or monetary compensation to You or others, such as personal use (i.e., hobbyist) or evaluation and testing.
18
+
19
+ III. COMMERCIAL USE LICENSE
20
+
21
+ Subject to the terms of this Agreement (including the remainder of this Section III), Stability AI grants You a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable and royalty-free limited license under Stability AI's intellectual property or other rights owned by Stability AI embodied in the Stability AI Materials to use, reproduce, distribute, and create Derivative Works of, and make modifications to, the Stability AI Materials for any Commercial Purpose. "Commercial Purpose" means any purpose other than a Research Purpose or Non-Commercial Purpose that is primarily intended for commercial advantage or monetary compensation to You or others, including but not limited to, (i) creating, modifying, or distributing Your product or service, including via a hosted service or application programming interface, and (ii) for Your business's or organization's internal operations.
22
+ If You are using or distributing the Stability AI Materials for a Commercial Purpose, You must register with Stability AI at (https://stability.ai/community-license). If at any time You or Your Affiliate(s), either individually or in aggregate, generate more than USD $1,000,000 in annual revenue (or the equivalent thereof in Your local currency), regardless of whether that revenue is generated directly or indirectly from the Stability AI Materials or Derivative Works, any licenses granted to You under this Agreement shall terminate as of such date. You must request a license from Stability AI at (https://stability.ai/enterprise) , which Stability AI may grant to You in its sole discretion. If you receive Stability AI Materials, or any Derivative Works thereof, from a Licensee as part of an integrated end user product, then Section III of this Agreement will not apply to you.
23
+
24
+ IV. GENERAL TERMS
25
+
26
+ Your Research, Non-Commercial, and Commercial License(s) under this Agreement are subject to the following terms.
27
+ a. Distribution & Attribution. If You distribute or make available the Stability AI Materials or a Derivative Work to a third party, or a product or service that uses any portion of them, You shall: (i) provide a copy of this Agreement to that third party, (ii) retain the following attribution notice within a "Notice" text file distributed as a part of such copies: "This Stability AI Model is licensed under the Stability AI Community License, Copyright © Stability AI Ltd. All Rights Reserved", and (iii) prominently display "Powered by Stability AI" on a related website, user interface, blogpost, about page, or product documentation. If You create a Derivative Work, You may add your own attribution notice(s) to the "Notice" text file included with that Derivative Work, provided that You clearly indicate which attributions apply to the Stability AI Materials and state in the "Notice" text file that You changed the Stability AI Materials and how it was modified.
28
+ b. Use Restrictions. Your use of the Stability AI Materials and Derivative Works, including any output or results of the Stability AI Materials or Derivative Works, must comply with applicable laws and regulations (including Trade Control Laws and equivalent regulations) and adhere to the Documentation and Stability AI's AUP, which is hereby incorporated by reference. Furthermore, You will not use the Stability AI Materials or Derivative Works, or any output or results of the Stability AI Materials or Derivative Works, to create or improve any foundational generative AI model (excluding the Models or Derivative Works).
29
+ c. Intellectual Property.
30
+ (i) Trademark License. No trademark licenses are granted under this Agreement, and in connection with the Stability AI Materials or Derivative Works, You may not use any name or mark owned by or associated with Stability AI or any of its Affiliates, except as required under Section IV(a) herein.
31
+ (ii) Ownership of Derivative Works. As between You and Stability AI, You are the owner of Derivative Works You create, subject to Stability AI's ownership of the Stability AI Materials and any Derivative Works made by or for Stability AI.
32
+ (iii) Ownership of Outputs. As between You and Stability AI, You own any outputs generated from the Models or Derivative Works to the extent permitted by applicable law.
33
+ (iv) Disputes. If You or Your Affiliate(s) institute litigation or other proceedings against Stability AI (including a cross-claim or counterclaim in a lawsuit) alleging that the Stability AI Materials, Derivative Works or associated outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by You, then any licenses granted to You under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Stability AI from and against any claim by any third party arising out of or related to Your use or distribution of the Stability AI Materials or Derivative Works in violation of this Agreement.
34
+ (v) Feedback. From time to time, You may provide Stability AI with verbal and/or written suggestions, comments or other feedback related to Stability AI's existing or prospective technology, products or services (collectively, "Feedback"). You are not obligated to provide Stability AI with Feedback, but to the extent that You do, You hereby grant Stability AI a perpetual, irrevocable, royalty-free, fully-paid, sub-licensable, transferable, non-exclusive, worldwide right and license to exploit the Feedback in any manner without restriction. Your Feedback is provided "AS IS" and You make no warranties whatsoever about any Feedback.
35
+ d. Disclaimer Of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE STABILITY AI MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OR LAWFULNESS OF USING OR REDISTRIBUTING THE STABILITY AI MATERIALS, DERIVATIVE WORKS OR ANY OUTPUT OR RESULTS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE STABILITY AI MATERIALS, DERIVATIVE WORKS AND ANY OUTPUT AND RESULTS.
36
+ e. Limitation Of Liability. IN NO EVENT WILL STABILITY AI OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY DIRECT, INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF STABILITY AI OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
37
+ f. Term And Termination. The term of this Agreement will commence upon Your acceptance of this Agreement or access to the Stability AI Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Stability AI may terminate this Agreement if You are in breach of any term or condition of this Agreement. Upon termination of this Agreement, You shall delete and cease use of any Stability AI Materials or Derivative Works. Section IV(d), (e), and (g) shall survive the termination of this Agreement.
38
+ g. Governing Law. This Agreement will be governed by and constructed in accordance with the laws of the United States and the State of California without regard to choice of law principles, and the UN Convention on Contracts for International Sale of Goods does not apply to this Agreement.
39
+
40
+ V. DEFINITIONS
41
+
42
+ "Affiliate(s)" means any entity that directly or indirectly controls, is controlled by, or is under common control with the subject entity; for purposes of this definition, "control" means direct or indirect ownership or control of more than 50% of the voting interests of the subject entity.
43
+ "Agreement" means this Stability AI Community License Agreement.
44
+ "AUP" means the Stability AI Acceptable Use Policy available at https://stability.ai/use-policy, as may be updated from time to time.
45
+ "Derivative Work(s)" means (a) any derivative work of the Stability AI Materials as recognized by U.S. copyright laws and (b) any modifications to a Model, and any other model created which is based on or derived from the Model or the Model's output, including"fine tune" and "low-rank adaptation" models derived from a Model or a Model's output, but do not include the output of any Model.
46
+ "Documentation" means any specifications, manuals, documentation, and other written information provided by Stability AI related to the Software or Models.
47
+ "Model(s)" means, collectively, Stability AI's proprietary models and algorithms, including machine-learning models, trained model weights and other elements of the foregoing listed on Stability's Core Models Webpage available at, https://stability.ai/core-models, as may be updated from time to time.
48
+ "Stability AI" or "we" means Stability AI Ltd. and its Affiliates.
49
+ "Software" means Stability AI's proprietary software made available under this Agreement now or in the future.
50
+ "Stability AI Materials" means, collectively, Stability's proprietary Models, Software and Documentation (and any portion or combination thereof) made available under this Agreement.
51
+ "Trade Control Laws" means any applicable U.S. and non-U.S. export control and trade sanctions laws and regulations.
README.md ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: stabilityai-ai-community
4
+ license_link: LICENSE.md
5
+ tags:
6
+ - text-to-image
7
+ - stable-diffusion
8
+ - diffusers
9
+ inference: true
10
+ extra_gated_prompt: >-
11
+ By clicking "Agree", you agree to the [License
12
+ Agreement](https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo/blob/main/LICENSE.md)
13
+ and acknowledge Stability AI's [Privacy
14
+ Policy](https://stability.ai/privacy-policy).
15
+ extra_gated_fields:
16
+ Name: text
17
+ Email: text
18
+ Country: country
19
+ Organization or Affiliation: text
20
+ Receive email updates and promotions on Stability AI products, services, and research?:
21
+ type: select
22
+ options:
23
+ - 'Yes'
24
+ - 'No'
25
+ What do you intend to use the model for?:
26
+ type: select
27
+ options:
28
+ - Research
29
+ - Personal use
30
+ - Creative Professional
31
+ - Startup
32
+ - Enterprise
33
+ I agree to the License Agreement and acknowledge Stability AI's Privacy Policy: checkbox
34
+
35
+ language:
36
+ - en
37
+ pipeline_tag: text-to-image
38
+ ---
39
+
40
+ # Stable Diffusion 3.5 Large Turbo
41
+ ![3.5 Large Turbo Demo Image](sd3.5_large_turbo_demo.png)
42
+
43
+ ## Model
44
+
45
+ ![MMDiT](mmdit.png)
46
+
47
+
48
+ [Stable Diffusion 3.5 Large Turbo](https://stability.ai/news/introducing-stable-diffusion-3-5) is a Multimodal Diffusion Transformer (MMDiT) text-to-image model with [Adversarial Diffusion Distillation (ADD)](https://stability.ai/research/adversarial-diffusion-distillation) that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency, with a focus on fewer inference steps.
49
+
50
+ Please note: This model is released under the [Stability Community License](https://stability.ai/community-license-agreement). Visit [Stability AI](https://stability.ai/license) to learn or [contact us](https://stability.ai/enterprise) for commercial licensing details.
51
+
52
+
53
+ ### Model Description
54
+
55
+ - **Developed by:** Stability AI
56
+ - **Model type:** MMDiT text-to-image generative model
57
+ - **Model Description:** This model generates images based on text prompts. It is an ADD-distilled [Multimodal Diffusion Transformer](https://arxiv.org/abs/2403.03206) that use three fixed, pretrained text encoders, and with QK-normalization.
58
+
59
+ ### License
60
+
61
+ - **Community License:** Free for research, non-commercial, and commercial use for organizations or individuals with less than $1M in total annual revenue. More details can be found in the [Community License Agreement](https://stability.ai/community-license-agreement). Read more at https://stability.ai/license.
62
+ - **For individuals and organizations with annual revenue above $1M**: Please [contact us](https://stability.ai/enterprise) to get an Enterprise License.
63
+
64
+ ### Model Sources
65
+
66
+ For local or self-hosted use, we recommend [ComfyUI](https://github.com/comfyanonymous/ComfyUI) for node-based UI inference, or [diffusers](https://github.com/huggingface/diffusers) or [GitHub](https://github.com/Stability-AI/sd3.5) for programmatic use.
67
+
68
+ - **ComfyUI:** [Github](https://github.com/comfyanonymous/ComfyUI), [Example Workflow](https://comfyanonymous.github.io/ComfyUI_examples/sd3/)
69
+
70
+ - **Huggingface Space:** [Space](https://huggingface.co/spaces/stabilityai/stable-diffusion-3.5-large-turbo)
71
+
72
+ - **Diffusers**: [See below](#using-with-diffusers).
73
+
74
+ - **GitHub**: [GitHub](https://github.com/Stability-AI/sd3.5).
75
+
76
+ - **API Endpoints:**
77
+ - [Stability AI API](https://platform.stability.ai/docs/api-reference#tag/Generate/paths/~1v2beta~1stable-image~1generate~1sd3/post)
78
+ - [Deepinfra](https://deepinfra.com/stabilityai/sd3.5)
79
+
80
+
81
+
82
+ ### Implementation Details
83
+
84
+ - **QK Normalization:** Implements the QK normalization technique to improve training Stability.
85
+
86
+ - **Adversarial Diffusion Distillation (ADD)** (see the [technical report](https://stability.ai/research/adversarial-diffusion-distillation)), which allows sampling with 4 steps at high image quality.
87
+
88
+ - **Text Encoders:**
89
+ - CLIPs: [OpenCLIP-ViT/G](https://github.com/mlfoundations/open_clip), [CLIP-ViT/L](https://github.com/openai/CLIP/tree/main), context length 77 tokens
90
+ - T5: [T5-xxl](https://huggingface.co/google/t5-v1_1-xxl), context length 77/256 tokens at different stages of training
91
+
92
+ - **Training Data and Strategy:**
93
+
94
+ This model was trained on a wide variety of data, including synthetic data and filtered publicly available data.
95
+
96
+ For more technical details of the original MMDiT architecture, please refer to the [Research paper](https://stability.ai/news/stable-diffusion-3-research-paper).
97
+
98
+
99
+ ### Model Performance
100
+
101
+ See [blog](https://stability.ai/news/introducing-stable-diffusion-3-5) for our study about comparative performance in prompt adherence and aesthetic quality.
102
+
103
+
104
+ ## File Structure
105
+
106
+ Click here to access the [Files and versions tab](https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo/tree/main)
107
+
108
+ ```│
109
+ ├── text_encoders/ (text_encoder/text_encoder_1/text_encoder_2 are for diffusers)
110
+ │ ├── README.md
111
+ │ ├── clip_g.safetensors
112
+ │ ├── clip_l.safetensors
113
+ │ ├── t5xxl_fp16.safetensors
114
+ │ └── t5xxl_fp8_e4m3fn.safetensors
115
+
116
+ ├── README.md
117
+ ├── LICENSE
118
+ ├── sd3_large_turbo.safetensors
119
+ ├── SD3.5L_Turbo_example_workflow.json
120
+ └── sd3_large_turbo_demo.png
121
+
122
+ ** File structure below is for diffusers integration**
123
+ ├── scheduler/
124
+ ├── text_encoder/
125
+ ├── text_encoder_2/
126
+ ├── text_encoder_3/
127
+ ├── tokenizer/
128
+ ├── tokenizer_2/
129
+ ├── tokenizer_3/
130
+ ├── transformer/
131
+ ├── vae/
132
+ └── model_index.json
133
+
134
+ ```
135
+
136
+ ## Using with Diffusers
137
+ Upgrade to the latest version of the [🧨 diffusers library](https://github.com/huggingface/diffusers)
138
+ ```
139
+ pip install -U diffusers
140
+ ```
141
+
142
+ and then you can run
143
+ ```py
144
+ import torch
145
+ from diffusers import StableDiffusion3Pipeline
146
+
147
+ pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large-turbo", torch_dtype=torch.bfloat16)
148
+ pipe = pipe.to("cuda")
149
+
150
+ image = pipe(
151
+ "A capybara holding a sign that reads Hello Fast World",
152
+ num_inference_steps=4,
153
+ guidance_scale=0.0,
154
+ ).images[0]
155
+ image.save("capybara.png")
156
+ ```
157
+
158
+ ### Quantizing the model with diffusers
159
+
160
+ Reduce your VRAM usage and have the model fit on low VRAM GPUs
161
+
162
+ ```
163
+ pip install bitsandbytes
164
+ ```
165
+
166
+ ```py
167
+ from diffusers import BitsAndBytesConfig, SD3Transformer2DModel
168
+ from diffusers import StableDiffusion3Pipeline
169
+ import torch
170
+
171
+ model_id = "stabilityai/stable-diffusion-3.5-large-turbo"
172
+
173
+ nf4_config = BitsAndBytesConfig(
174
+ load_in_4bit=True,
175
+ bnb_4bit_quant_type="nf4",
176
+ bnb_4bit_compute_dtype=torch.bfloat16
177
+ )
178
+ model_nf4 = SD3Transformer2DModel.from_pretrained(
179
+ model_id,
180
+ subfolder="transformer",
181
+ quantization_config=nf4_config,
182
+ torch_dtype=torch.bfloat16
183
+ )
184
+
185
+ t5_nf4 = T5EncoderModel.from_pretrained("diffusers/t5-nf4", torch_dtype=torch.bfloat16)
186
+
187
+ pipeline = StableDiffusion3Pipeline.from_pretrained(
188
+ model_id,
189
+ transformer=model_nf4,
190
+ text_encoder_3=t5_nf4,
191
+ torch_dtype=torch.bfloat16
192
+ )
193
+ pipeline.enable_model_cpu_offload()
194
+
195
+ prompt = "A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus, basking in a river of melted butter amidst a breakfast-themed landscape. It features the distinctive, bulky body shape of a hippo. However, instead of the usual grey skin, the creature's body resembles a golden-brown, crispy waffle fresh off the griddle. The skin is textured with the familiar grid pattern of a waffle, each square filled with a glistening sheen of syrup. The environment combines the natural habitat of a hippo with elements of a breakfast table setting, a river of warm, melted butter, with oversized utensils or plates peeking out from the lush, pancake-like foliage in the background, a towering pepper mill standing in for a tree. As the sun rises in this fantastical world, it casts a warm, buttery glow over the scene. The creature, content in its butter river, lets out a yawn. Nearby, a flock of birds take flight"
196
+
197
+ image = pipeline(
198
+ prompt=prompt,
199
+ num_inference_steps=4,
200
+ guidance_scale=0.0,
201
+ max_sequence_length=512,
202
+ ).images[0]
203
+ image.save("whimsical.png")
204
+ ```
205
+
206
+ ## Uses
207
+
208
+ ### Intended Uses
209
+
210
+ Intended uses include the following:
211
+ * Generation of artworks and use in design and other artistic processes.
212
+ * Applications in educational or creative tools.
213
+ * Research on generative models, including understanding the limitations of generative models.
214
+
215
+ All uses of the model must be in accordance with our [Acceptable Use Policy](https://stability.ai/use-policy).
216
+
217
+ ### Out-of-Scope Uses
218
+
219
+ The model was not trained to be factual or true representations of people or events. As such, using the model to generate such content is out-of-scope of the abilities of this model.
220
+
221
+ ## Safety
222
+
223
+ As part of our safety-by-design and responsible AI deployment approach, we take deliberate measures to ensure Integrity starts at the early stages of development. We implement safety measures throughout the development of our models. We have implemented safety mitigations that are intended to reduce the risk of certain harms, however we recommend that developers conduct their own testing and apply additional mitigations based on their specific use cases.
224
+ For more about our approach to Safety, please visit our [Safety page](https://stability.ai/safety).
225
+
226
+ ### Integrity Evaluation
227
+
228
+ Our integrity evaluation methods include structured evaluations and red-teaming testing for certain harms. Testing was conducted primarily in English and may not cover all possible harms.
229
+
230
+ ### Risks identified and mitigations:
231
+
232
+ * Harmful content: We have used filtered data sets when training our models and implemented safeguards that attempt to strike the right balance between usefulness and preventing harm. However, this does not guarantee that all possible harmful content has been removed. TAll developers and deployers should exercise caution and implement content safety guardrails based on their specific product policies and application use cases.
233
+ * Misuse: Technical limitations and developer and end-user education can help mitigate against malicious applications of models. All users are required to adhere to our [Acceptable Use Policy](https://stability.ai/use-policy), including when applying fine-tuning and prompt engineering mechanisms. Please reference the Stability AI Acceptable Use Policy for information on violative uses of our products.
234
+ * Privacy violations: Developers and deployers are encouraged to adhere to privacy regulations with techniques that respect data privacy.
235
+
236
+ ## Contact
237
+
238
+ Please report any issues with the model or contact us:
239
+
240
+ * Safety issues: safety@stability.ai
241
+ * Security issues: security@stability.ai
242
+ * Privacy issues: privacy@stability.ai
243
+ * License and general: https://stability.ai/license
244
+ * Enterprise license: https://stability.ai/enterprise
SD3.5L_Turbo_example_workflow.json ADDED
@@ -0,0 +1,688 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "last_node_id": 300,
3
+ "last_link_id": 605,
4
+ "nodes": [
5
+ {
6
+ "id": 70,
7
+ "type": "ConditioningSetTimestepRange",
8
+ "pos": [
9
+ 126,
10
+ 252
11
+ ],
12
+ "size": {
13
+ "0": 317.4000244140625,
14
+ "1": 82
15
+ },
16
+ "flags": {},
17
+ "order": 7,
18
+ "mode": 0,
19
+ "inputs": [
20
+ {
21
+ "name": "conditioning",
22
+ "type": "CONDITIONING",
23
+ "link": 93,
24
+ "slot_index": 0
25
+ }
26
+ ],
27
+ "outputs": [
28
+ {
29
+ "name": "CONDITIONING",
30
+ "type": "CONDITIONING",
31
+ "links": [
32
+ 92
33
+ ],
34
+ "shape": 3,
35
+ "slot_index": 0
36
+ }
37
+ ],
38
+ "properties": {
39
+ "Node name for S&R": "ConditioningSetTimestepRange"
40
+ },
41
+ "widgets_values": [
42
+ 0,
43
+ 0.1
44
+ ]
45
+ },
46
+ {
47
+ "id": 68,
48
+ "type": "ConditioningSetTimestepRange",
49
+ "pos": [
50
+ 126,
51
+ 126
52
+ ],
53
+ "size": {
54
+ "0": 317.4000244140625,
55
+ "1": 82
56
+ },
57
+ "flags": {},
58
+ "order": 9,
59
+ "mode": 0,
60
+ "inputs": [
61
+ {
62
+ "name": "conditioning",
63
+ "type": "CONDITIONING",
64
+ "link": 90
65
+ }
66
+ ],
67
+ "outputs": [
68
+ {
69
+ "name": "CONDITIONING",
70
+ "type": "CONDITIONING",
71
+ "links": [
72
+ 91
73
+ ],
74
+ "shape": 3,
75
+ "slot_index": 0
76
+ }
77
+ ],
78
+ "properties": {
79
+ "Node name for S&R": "ConditioningSetTimestepRange"
80
+ },
81
+ "widgets_values": [
82
+ 0.1,
83
+ 1
84
+ ]
85
+ },
86
+ {
87
+ "id": 67,
88
+ "type": "ConditioningZeroOut",
89
+ "pos": [
90
+ -126,
91
+ 126
92
+ ],
93
+ "size": {
94
+ "0": 211.60000610351562,
95
+ "1": 26
96
+ },
97
+ "flags": {},
98
+ "order": 8,
99
+ "mode": 0,
100
+ "inputs": [
101
+ {
102
+ "name": "conditioning",
103
+ "type": "CONDITIONING",
104
+ "link": 597
105
+ }
106
+ ],
107
+ "outputs": [
108
+ {
109
+ "name": "CONDITIONING",
110
+ "type": "CONDITIONING",
111
+ "links": [
112
+ 90
113
+ ],
114
+ "shape": 3,
115
+ "slot_index": 0
116
+ }
117
+ ],
118
+ "properties": {
119
+ "Node name for S&R": "ConditioningZeroOut"
120
+ }
121
+ },
122
+ {
123
+ "id": 71,
124
+ "type": "CLIPTextEncode",
125
+ "pos": [
126
+ -1010,
127
+ 252
128
+ ],
129
+ "size": [
130
+ 351.8130934034689,
131
+ 195.5754530459866
132
+ ],
133
+ "flags": {},
134
+ "order": 5,
135
+ "mode": 0,
136
+ "inputs": [
137
+ {
138
+ "name": "clip",
139
+ "type": "CLIP",
140
+ "link": 94
141
+ }
142
+ ],
143
+ "outputs": [
144
+ {
145
+ "name": "CONDITIONING",
146
+ "type": "CONDITIONING",
147
+ "links": [
148
+ 93,
149
+ 597
150
+ ],
151
+ "shape": 3,
152
+ "slot_index": 0
153
+ }
154
+ ],
155
+ "properties": {
156
+ "Node name for S&R": "CLIPTextEncode"
157
+ },
158
+ "widgets_values": [
159
+ ""
160
+ ],
161
+ "color": "#322",
162
+ "bgcolor": "#533"
163
+ },
164
+ {
165
+ "id": 6,
166
+ "type": "CLIPTextEncode",
167
+ "pos": [
168
+ -1008,
169
+ 2
170
+ ],
171
+ "size": [
172
+ 342.83352734520565,
173
+ 177.20867231021555
174
+ ],
175
+ "flags": {},
176
+ "order": 4,
177
+ "mode": 0,
178
+ "inputs": [
179
+ {
180
+ "name": "clip",
181
+ "type": "CLIP",
182
+ "link": 5
183
+ }
184
+ ],
185
+ "outputs": [
186
+ {
187
+ "name": "CONDITIONING",
188
+ "type": "CONDITIONING",
189
+ "links": [
190
+ 569
191
+ ],
192
+ "shape": 3,
193
+ "slot_index": 0
194
+ }
195
+ ],
196
+ "properties": {
197
+ "Node name for S&R": "CLIPTextEncode"
198
+ },
199
+ "widgets_values": [
200
+ "beautiful scenery nature glass bottle landscape, purple galaxy bottle,"
201
+ ],
202
+ "color": "#232",
203
+ "bgcolor": "#353"
204
+ },
205
+ {
206
+ "id": 13,
207
+ "type": "ModelSamplingSD3",
208
+ "pos": [
209
+ 126,
210
+ -504
211
+ ],
212
+ "size": {
213
+ "0": 315,
214
+ "1": 58
215
+ },
216
+ "flags": {
217
+ "collapsed": false
218
+ },
219
+ "order": 6,
220
+ "mode": 0,
221
+ "inputs": [
222
+ {
223
+ "name": "model",
224
+ "type": "MODEL",
225
+ "link": 445
226
+ }
227
+ ],
228
+ "outputs": [
229
+ {
230
+ "name": "MODEL",
231
+ "type": "MODEL",
232
+ "links": [
233
+ 568
234
+ ],
235
+ "shape": 3,
236
+ "slot_index": 0
237
+ }
238
+ ],
239
+ "properties": {
240
+ "Node name for S&R": "ModelSamplingSD3"
241
+ },
242
+ "widgets_values": [
243
+ 3
244
+ ]
245
+ },
246
+ {
247
+ "id": 69,
248
+ "type": "ConditioningCombine",
249
+ "pos": [
250
+ 504,
251
+ 126
252
+ ],
253
+ "size": {
254
+ "0": 228.39999389648438,
255
+ "1": 46
256
+ },
257
+ "flags": {},
258
+ "order": 10,
259
+ "mode": 0,
260
+ "inputs": [
261
+ {
262
+ "name": "conditioning_1",
263
+ "type": "CONDITIONING",
264
+ "link": 91
265
+ },
266
+ {
267
+ "name": "conditioning_2",
268
+ "type": "CONDITIONING",
269
+ "link": 92
270
+ }
271
+ ],
272
+ "outputs": [
273
+ {
274
+ "name": "CONDITIONING",
275
+ "type": "CONDITIONING",
276
+ "links": [
277
+ 604
278
+ ],
279
+ "shape": 3,
280
+ "slot_index": 0
281
+ }
282
+ ],
283
+ "properties": {
284
+ "Node name for S&R": "ConditioningCombine"
285
+ }
286
+ },
287
+ {
288
+ "id": 8,
289
+ "type": "VAEDecode",
290
+ "pos": [
291
+ 1386,
292
+ -504
293
+ ],
294
+ "size": {
295
+ "0": 210,
296
+ "1": 46
297
+ },
298
+ "flags": {},
299
+ "order": 12,
300
+ "mode": 0,
301
+ "inputs": [
302
+ {
303
+ "name": "samples",
304
+ "type": "LATENT",
305
+ "link": 572
306
+ },
307
+ {
308
+ "name": "vae",
309
+ "type": "VAE",
310
+ "link": 605
311
+ }
312
+ ],
313
+ "outputs": [
314
+ {
315
+ "name": "IMAGE",
316
+ "type": "IMAGE",
317
+ "links": [
318
+ 274
319
+ ],
320
+ "shape": 3,
321
+ "slot_index": 0
322
+ }
323
+ ],
324
+ "properties": {
325
+ "Node name for S&R": "VAEDecode"
326
+ }
327
+ },
328
+ {
329
+ "id": 50,
330
+ "type": "PreviewImage",
331
+ "pos": [
332
+ 1764,
333
+ -504
334
+ ],
335
+ "size": {
336
+ "0": 616.689697265625,
337
+ "1": 613.84130859375
338
+ },
339
+ "flags": {},
340
+ "order": 13,
341
+ "mode": 0,
342
+ "inputs": [
343
+ {
344
+ "name": "images",
345
+ "type": "IMAGE",
346
+ "link": 274
347
+ }
348
+ ],
349
+ "properties": {
350
+ "Node name for S&R": "PreviewImage"
351
+ }
352
+ },
353
+ {
354
+ "id": 135,
355
+ "type": "EmptySD3LatentImage",
356
+ "pos": [
357
+ -1008,
358
+ -252
359
+ ],
360
+ "size": [
361
+ 315,
362
+ 106
363
+ ],
364
+ "flags": {},
365
+ "order": 0,
366
+ "mode": 0,
367
+ "inputs": [],
368
+ "outputs": [
369
+ {
370
+ "name": "LATENT",
371
+ "type": "LATENT",
372
+ "links": [
373
+ 598
374
+ ],
375
+ "shape": 3,
376
+ "slot_index": 0
377
+ }
378
+ ],
379
+ "properties": {
380
+ "Node name for S&R": "EmptySD3LatentImage"
381
+ },
382
+ "widgets_values": [
383
+ 1024,
384
+ 1024,
385
+ 1
386
+ ]
387
+ },
388
+ {
389
+ "id": 105,
390
+ "type": "Note",
391
+ "pos": [
392
+ -1260,
393
+ -252
394
+ ],
395
+ "size": [
396
+ 210,
397
+ 110.1894832228611
398
+ ],
399
+ "flags": {},
400
+ "order": 1,
401
+ "mode": 0,
402
+ "properties": {
403
+ "text": ""
404
+ },
405
+ "widgets_values": [
406
+ "Make sure the resolution is multiple of 64 pixels and adds up to around 1 megapixel. "
407
+ ],
408
+ "color": "#432",
409
+ "bgcolor": "#653"
410
+ },
411
+ {
412
+ "id": 11,
413
+ "type": "TripleCLIPLoader",
414
+ "pos": [
415
+ -2016,
416
+ -252
417
+ ],
418
+ "size": {
419
+ "0": 315,
420
+ "1": 106
421
+ },
422
+ "flags": {},
423
+ "order": 2,
424
+ "mode": 0,
425
+ "outputs": [
426
+ {
427
+ "name": "CLIP",
428
+ "type": "CLIP",
429
+ "links": [
430
+ 5,
431
+ 94
432
+ ],
433
+ "shape": 3,
434
+ "slot_index": 0
435
+ }
436
+ ],
437
+ "properties": {
438
+ "Node name for S&R": "TripleCLIPLoader"
439
+ },
440
+ "widgets_values": [
441
+ "clip_g_sdxl_base.safetensors",
442
+ "clip_l_sdxl_base.safetensors",
443
+ "t5xxl.safetensors"
444
+ ]
445
+ },
446
+ {
447
+ "id": 294,
448
+ "type": "KSampler",
449
+ "pos": [
450
+ 882,
451
+ -504
452
+ ],
453
+ "size": [
454
+ 378,
455
+ 504
456
+ ],
457
+ "flags": {},
458
+ "order": 11,
459
+ "mode": 0,
460
+ "inputs": [
461
+ {
462
+ "name": "model",
463
+ "type": "MODEL",
464
+ "link": 568
465
+ },
466
+ {
467
+ "name": "positive",
468
+ "type": "CONDITIONING",
469
+ "link": 569
470
+ },
471
+ {
472
+ "name": "negative",
473
+ "type": "CONDITIONING",
474
+ "link": 604
475
+ },
476
+ {
477
+ "name": "latent_image",
478
+ "type": "LATENT",
479
+ "link": 598
480
+ }
481
+ ],
482
+ "outputs": [
483
+ {
484
+ "name": "LATENT",
485
+ "type": "LATENT",
486
+ "links": [
487
+ 572
488
+ ],
489
+ "shape": 3,
490
+ "slot_index": 0
491
+ }
492
+ ],
493
+ "properties": {
494
+ "Node name for S&R": "KSampler"
495
+ },
496
+ "widgets_values": [
497
+ 349467226218834,
498
+ "randomize",
499
+ 4,
500
+ 1,
501
+ "dpmpp_2m",
502
+ "sgm_uniform",
503
+ 1
504
+ ]
505
+ },
506
+ {
507
+ "id": 4,
508
+ "type": "CheckpointLoaderSimple",
509
+ "pos": [
510
+ -2016,
511
+ -504
512
+ ],
513
+ "size": {
514
+ "0": 632.6060180664062,
515
+ "1": 98
516
+ },
517
+ "flags": {},
518
+ "order": 3,
519
+ "mode": 0,
520
+ "outputs": [
521
+ {
522
+ "name": "MODEL",
523
+ "type": "MODEL",
524
+ "links": [
525
+ 445
526
+ ],
527
+ "shape": 3,
528
+ "slot_index": 0
529
+ },
530
+ {
531
+ "name": "CLIP",
532
+ "type": "CLIP",
533
+ "links": null,
534
+ "shape": 3
535
+ },
536
+ {
537
+ "name": "VAE",
538
+ "type": "VAE",
539
+ "links": [
540
+ 605
541
+ ],
542
+ "shape": 3,
543
+ "slot_index": 2
544
+ }
545
+ ],
546
+ "properties": {
547
+ "Node name for S&R": "CheckpointLoaderSimple"
548
+ },
549
+ "widgets_values": [
550
+ "sd3.5_large_turbo.safetensors"
551
+ ]
552
+ }
553
+ ],
554
+ "links": [
555
+ [
556
+ 5,
557
+ 11,
558
+ 0,
559
+ 6,
560
+ 0,
561
+ "CLIP"
562
+ ],
563
+ [
564
+ 90,
565
+ 67,
566
+ 0,
567
+ 68,
568
+ 0,
569
+ "CONDITIONING"
570
+ ],
571
+ [
572
+ 91,
573
+ 68,
574
+ 0,
575
+ 69,
576
+ 0,
577
+ "CONDITIONING"
578
+ ],
579
+ [
580
+ 92,
581
+ 70,
582
+ 0,
583
+ 69,
584
+ 1,
585
+ "CONDITIONING"
586
+ ],
587
+ [
588
+ 93,
589
+ 71,
590
+ 0,
591
+ 70,
592
+ 0,
593
+ "CONDITIONING"
594
+ ],
595
+ [
596
+ 94,
597
+ 11,
598
+ 0,
599
+ 71,
600
+ 0,
601
+ "CLIP"
602
+ ],
603
+ [
604
+ 274,
605
+ 8,
606
+ 0,
607
+ 50,
608
+ 0,
609
+ "IMAGE"
610
+ ],
611
+ [
612
+ 445,
613
+ 4,
614
+ 0,
615
+ 13,
616
+ 0,
617
+ "MODEL"
618
+ ],
619
+ [
620
+ 568,
621
+ 13,
622
+ 0,
623
+ 294,
624
+ 0,
625
+ "MODEL"
626
+ ],
627
+ [
628
+ 569,
629
+ 6,
630
+ 0,
631
+ 294,
632
+ 1,
633
+ "CONDITIONING"
634
+ ],
635
+ [
636
+ 572,
637
+ 294,
638
+ 0,
639
+ 8,
640
+ 0,
641
+ "LATENT"
642
+ ],
643
+ [
644
+ 597,
645
+ 71,
646
+ 0,
647
+ 67,
648
+ 0,
649
+ "CONDITIONING"
650
+ ],
651
+ [
652
+ 598,
653
+ 135,
654
+ 0,
655
+ 294,
656
+ 3,
657
+ "LATENT"
658
+ ],
659
+ [
660
+ 604,
661
+ 69,
662
+ 0,
663
+ 294,
664
+ 2,
665
+ "CONDITIONING"
666
+ ],
667
+ [
668
+ 605,
669
+ 4,
670
+ 2,
671
+ 8,
672
+ 1,
673
+ "VAE"
674
+ ]
675
+ ],
676
+ "groups": [],
677
+ "config": {},
678
+ "extra": {
679
+ "ds": {
680
+ "scale": 0.3452271214393102,
681
+ "offset": [
682
+ 2070.782739748983,
683
+ 1025.5502104141715
684
+ ]
685
+ }
686
+ },
687
+ "version": 0.4
688
+ }
mmdit.png ADDED
model_index.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusion3Pipeline",
3
+ "_diffusers_version": "0.30.3.dev0",
4
+ "scheduler": [
5
+ "diffusers",
6
+ "FlowMatchEulerDiscreteScheduler"
7
+ ],
8
+ "text_encoder": [
9
+ "transformers",
10
+ "CLIPTextModelWithProjection"
11
+ ],
12
+ "text_encoder_2": [
13
+ "transformers",
14
+ "CLIPTextModelWithProjection"
15
+ ],
16
+ "text_encoder_3": [
17
+ "transformers",
18
+ "T5EncoderModel"
19
+ ],
20
+ "tokenizer": [
21
+ "transformers",
22
+ "CLIPTokenizer"
23
+ ],
24
+ "tokenizer_2": [
25
+ "transformers",
26
+ "CLIPTokenizer"
27
+ ],
28
+ "tokenizer_3": [
29
+ "transformers",
30
+ "T5TokenizerFast"
31
+ ],
32
+ "transformer": [
33
+ "diffusers",
34
+ "SD3Transformer2DModel"
35
+ ],
36
+ "vae": [
37
+ "diffusers",
38
+ "AutoencoderKL"
39
+ ]
40
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "num_train_timesteps": 1000,
5
+ "shift": 3.0
6
+ }
sd3.5_large_turbo.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb64610bf8d73eb064b8d528eef85d062bf2b4b1204ff7bc73e57ad28b24489c
3
+ size 16460374454
sd3.5_large_turbo_demo.png ADDED

Git LFS Details

  • SHA256: 1d3c462ffbb9b15af3cdb3e62d1a232ac81a6f1f1efa0e39cf32a6eba9cf0efc
  • Pointer size: 133 Bytes
  • Size of remote file: 15.3 MB
text_encoder/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPTextModelWithProjection"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 0,
7
+ "dropout": 0.0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "quick_gelu",
10
+ "hidden_size": 768,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 77,
16
+ "model_type": "clip_text_model",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "projection_dim": 768,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.41.2",
23
+ "vocab_size": 49408
24
+ }
text_encoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1
3
+ size 247323896
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1
3
+ size 247323896
text_encoder_2/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPTextModelWithProjection"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 0,
7
+ "dropout": 0.0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 1280,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5120,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 77,
16
+ "model_type": "clip_text_model",
17
+ "num_attention_heads": 20,
18
+ "num_hidden_layers": 32,
19
+ "pad_token_id": 1,
20
+ "projection_dim": 1280,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.41.2",
23
+ "vocab_size": 49408
24
+ }
text_encoder_2/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
3
+ size 1389382176
text_encoder_2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
3
+ size 1389382176
text_encoder_3/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5EncoderModel"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 10240,
7
+ "d_kv": 64,
8
+ "d_model": 4096,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "num_decoder_layers": 24,
20
+ "num_heads": 64,
21
+ "num_layers": 24,
22
+ "output_past": true,
23
+ "pad_token_id": 0,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.41.2",
29
+ "use_cache": true,
30
+ "vocab_size": 32128
31
+ }
text_encoder_3/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2751ceeb2a96edd693e539dc5d6bba0b8d3814f49a9b3798403a0cec4b2e3d
3
+ size 4994582104
text_encoder_3/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f63154532130422309532ff56f11945fbea8266c958e3133e8e5aef85c6293c7
3
+ size 4530066248
text_encoder_3/model.fp16-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2751ceeb2a96edd693e539dc5d6bba0b8d3814f49a9b3798403a0cec4b2e3d
3
+ size 4994582104
text_encoder_3/model.fp16-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f63154532130422309532ff56f11945fbea8266c958e3133e8e5aef85c6293c7
3
+ size 4530066248
text_encoder_3/model.safetensors.index.fp16.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 9524621312
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
7
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
8
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
9
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00001-of-00002.safetensors",
10
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
11
+ "encoder.block.0.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
12
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
13
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
14
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
15
+ "encoder.block.0.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
16
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
17
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
18
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
19
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
20
+ "encoder.block.1.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
21
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
22
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
23
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
24
+ "encoder.block.1.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
25
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
26
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
27
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
28
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
29
+ "encoder.block.10.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
30
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
31
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
32
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
33
+ "encoder.block.10.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
34
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
35
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
36
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
37
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
38
+ "encoder.block.11.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
39
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
40
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
41
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
42
+ "encoder.block.11.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
43
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
44
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
45
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
46
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
47
+ "encoder.block.12.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
48
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
49
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
50
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
51
+ "encoder.block.12.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
52
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
53
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
54
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
55
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
56
+ "encoder.block.13.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
57
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
58
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
59
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
60
+ "encoder.block.13.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
61
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
62
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
63
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
64
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
65
+ "encoder.block.14.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
66
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
67
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
68
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
69
+ "encoder.block.14.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
70
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
71
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
72
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
73
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
74
+ "encoder.block.15.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
75
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
76
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
77
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
78
+ "encoder.block.15.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
79
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
80
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
81
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
82
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
83
+ "encoder.block.16.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
84
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
85
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
86
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
87
+ "encoder.block.16.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
88
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
89
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
90
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
91
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
92
+ "encoder.block.17.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
93
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
94
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
95
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
96
+ "encoder.block.17.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
97
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
98
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
99
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
100
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
101
+ "encoder.block.18.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
102
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
103
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
104
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
105
+ "encoder.block.18.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
106
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
107
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
108
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
109
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
110
+ "encoder.block.19.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
111
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
112
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
113
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
114
+ "encoder.block.19.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
115
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
116
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
117
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
118
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
119
+ "encoder.block.2.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
120
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
121
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
122
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
123
+ "encoder.block.2.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
124
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
125
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
126
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
127
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
128
+ "encoder.block.20.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
129
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
130
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
131
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
132
+ "encoder.block.20.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
133
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
134
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
135
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
136
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
137
+ "encoder.block.21.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
138
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
139
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
140
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
141
+ "encoder.block.21.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
142
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
143
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
144
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
145
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
146
+ "encoder.block.22.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
147
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
148
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
149
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
150
+ "encoder.block.22.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
151
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
152
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
153
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
154
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
155
+ "encoder.block.23.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
156
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
157
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
158
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
159
+ "encoder.block.23.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
160
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
161
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
162
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
163
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
164
+ "encoder.block.3.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
165
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
166
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
167
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
168
+ "encoder.block.3.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
169
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
170
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
171
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
172
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
173
+ "encoder.block.4.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
174
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
175
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
176
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
177
+ "encoder.block.4.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
178
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
179
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
180
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
181
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
182
+ "encoder.block.5.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
183
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
184
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
185
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
186
+ "encoder.block.5.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
187
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
188
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
189
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
190
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
191
+ "encoder.block.6.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
192
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
193
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
194
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
195
+ "encoder.block.6.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
196
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
197
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
198
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
199
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
200
+ "encoder.block.7.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
201
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
202
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
203
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
204
+ "encoder.block.7.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
205
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
206
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
207
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
208
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
209
+ "encoder.block.8.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
210
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
211
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
212
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
213
+ "encoder.block.8.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
214
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
215
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
216
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
217
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
218
+ "encoder.block.9.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
219
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
220
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
221
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
222
+ "encoder.block.9.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
223
+ "encoder.final_layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
224
+ "shared.weight": "model.fp16-00001-of-00002.safetensors"
225
+ }
226
+ }
text_encoder_3/model.safetensors.index.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 9524621312
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
7
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
8
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
9
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
10
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
11
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
12
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
13
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
14
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
15
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
16
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
17
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
18
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
19
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
20
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
21
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
22
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
23
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
24
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
25
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
26
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
27
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
28
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
29
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
30
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
31
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
32
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
33
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
34
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
35
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
36
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
37
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
38
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
39
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
40
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
41
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
42
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
43
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
44
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
45
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
46
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
47
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
48
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
49
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
50
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
51
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
52
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
53
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
54
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
55
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
56
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
57
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
58
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
59
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
60
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
61
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
62
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
63
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
64
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
65
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
66
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
67
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
68
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
69
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
70
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
71
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
72
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
73
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
74
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
75
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
76
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
77
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
78
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
79
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
80
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
81
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
82
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
83
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
84
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
85
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
86
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
87
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
88
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
89
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
90
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
91
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
92
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
93
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
94
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
95
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
96
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
97
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
98
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
99
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
100
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
101
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
102
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
103
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
104
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
105
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
106
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
107
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
108
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
109
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
110
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
111
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
112
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
113
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
114
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
115
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
116
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
117
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
118
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
119
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
120
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
121
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
122
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
123
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
124
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
125
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
126
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
127
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
128
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
129
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
130
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
131
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
132
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
133
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
134
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
135
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
136
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
137
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
138
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
139
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
140
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
141
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
142
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
143
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
144
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
145
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
146
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
147
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
148
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
149
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
150
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
151
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
152
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
153
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
154
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
155
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
156
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
157
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
158
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
159
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
160
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
161
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
162
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
163
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
164
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
165
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
166
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
167
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
168
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
169
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
170
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
171
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
172
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
173
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
174
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
175
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
176
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
177
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
178
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
179
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
180
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
181
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
182
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
183
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
184
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
185
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
186
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
187
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
188
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
189
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
190
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
191
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
192
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
193
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
194
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
195
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
196
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
197
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
198
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
199
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
200
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
201
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
202
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
203
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
204
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
205
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
206
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
207
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
208
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
209
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
210
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
211
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
212
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
213
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
214
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
215
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
216
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
217
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
218
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
219
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
220
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
221
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
222
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
223
+ "encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
224
+ "shared.weight": "model-00001-of-00002.safetensors"
225
+ }
226
+ }
text_encoders/README.md ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ CLIP-ViT/L:
2
+ * [https://huggingface.co/openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14/blob/main/README.md)
3
+ * [MIT License](https://github.com/openai/CLIP/blob/main/LICENSE)
4
+
5
+ OpenCLIP-ViT/G:
6
+ * [https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k](https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k/blob/main/README.md)
7
+ * [MIT License](https://choosealicense.com/licenses/mit)
8
+
9
+ T5 Version 1.1:
10
+ * [https://huggingface.co/google/t5-v1_1-xxl](https://huggingface.co/google/t5-v1_1-xxl/blob/main/README.md)
11
+ * [Apache License 2.0](https://choosealicense.com/licenses/apache-2.0)
text_encoders/clip_g.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
3
+ size 1389382176
text_encoders/clip_l.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
3
+ size 246144152
text_encoders/t5xxl_fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635
3
+ size 9787841024
text_encoders/t5xxl_fp8_e4m3fn.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d330da4816157540d6bb7838bf63a0f02f573fc48ca4d8de34bb0cbfd514f09
3
+ size 4893934904
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|startoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "model_max_length": 77,
27
+ "pad_token": "<|endoftext|>",
28
+ "tokenizer_class": "CLIPTokenizer",
29
+ "unk_token": "<|endoftext|>"
30
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "!",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_2/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "!",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49406": {
13
+ "content": "<|startoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "49407": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "bos_token": "<|startoftext|>",
30
+ "clean_up_tokenization_spaces": true,
31
+ "do_lower_case": true,
32
+ "eos_token": "<|endoftext|>",
33
+ "errors": "replace",
34
+ "model_max_length": 77,
35
+ "pad_token": "!",
36
+ "tokenizer_class": "CLIPTokenizer",
37
+ "unk_token": "<|endoftext|>"
38
+ }
tokenizer_2/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_3/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
tokenizer_3/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer_3/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_3/tokenizer_config.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": true,
783
+ "normalized": false,
784
+ "rstrip": true,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": true,
791
+ "normalized": false,
792
+ "rstrip": true,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": true,
799
+ "normalized": false,
800
+ "rstrip": true,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": true,
807
+ "normalized": false,
808
+ "rstrip": true,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": true,
815
+ "normalized": false,
816
+ "rstrip": true,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": true,
823
+ "normalized": false,
824
+ "rstrip": true,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": true,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "legacy": true,
935
+ "model_max_length": 512,
936
+ "pad_token": "<pad>",
937
+ "sp_model_kwargs": {},
938
+ "tokenizer_class": "T5Tokenizer",
939
+ "unk_token": "<unk>"
940
+ }
transformer/config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "SD3Transformer2DModel",
3
+ "_diffusers_version": "0.31.0.dev0",
4
+ "attention_head_dim": 64,
5
+ "caption_projection_dim": 2432,
6
+ "in_channels": 16,
7
+ "joint_attention_dim": 4096,
8
+ "num_attention_heads": 38,
9
+ "num_layers": 38,
10
+ "out_channels": 16,
11
+ "patch_size": 2,
12
+ "pooled_projection_dim": 2048,
13
+ "pos_embed_max_size": 192,
14
+ "qk_norm": "rms_norm",
15
+ "sample_size": 128
16
+ }
transformer/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5ce9ed17cd13d87fd61b4743ce046c1c114a422364542b7167121b147bc110
3
+ size 9985185992
transformer/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34374d4c2ea0d26baf986094f485dec2161c3778cc57c5b9840cabd9a8f3839a
3
+ size 6307519304
transformer/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
vae/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.31.0.dev0",
4
+ "_name_or_path": "../sdxl-vae/",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "force_upcast": true,
19
+ "in_channels": 3,
20
+ "latent_channels": 16,
21
+ "latents_mean": null,
22
+ "latents_std": null,
23
+ "layers_per_block": 2,
24
+ "mid_block_add_attention": true,
25
+ "norm_num_groups": 32,
26
+ "out_channels": 3,
27
+ "sample_size": 1024,
28
+ "scaling_factor": 1.5305,
29
+ "shift_factor": 0.0609,
30
+ "up_block_types": [
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D",
34
+ "UpDecoderBlock2D"
35
+ ],
36
+ "use_post_quant_conv": false,
37
+ "use_quant_conv": false
38
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f53304a79335b55e13ec50f63e5157fee4deb2f30d5fae0654e2b2653c109dc
3
+ size 167666902