Hugging Face's logo

exolabs
/
FLUX.1-Krea-dev-4bit

Text-to-Image
Diffusers
Safetensors
English
image-generation
flux
Model card Files
xet
Community
cbor9 commited on
Commit
92d53e7
·
verified ·
1 Parent(s): 3af486e

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. README.md +113 -0
  2. text_encoder/0.safetensors +3 -0
  3. text_encoder/model.safetensors.index.json +352 -0
  4. text_encoder_2/0.safetensors +3 -0
  5. text_encoder_2/1.safetensors +3 -0
  6. text_encoder_2/model.safetensors.index.json +636 -0
  7. tokenizer/tokenizer.json +0 -0
  8. tokenizer/tokenizer_config.json +14 -0
  9. tokenizer_2/tokenizer.json +0 -0
  10. tokenizer_2/tokenizer_config.json +116 -0
  11. transformer/0.safetensors +3 -0
  12. transformer/1.safetensors +3 -0
  13. transformer/2.safetensors +3 -0
  14. transformer/3.safetensors +3 -0
  15. transformer/model.safetensors.index.json +0 -0
  16. vae/0.safetensors +3 -0
  17. vae/model.safetensors.index.json +268 -0
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: other
5
+ license_name: flux-1-dev-non-commercial-license
6
+ license_link: LICENSE.md
7
+ extra_gated_prompt: >-
8
+ By clicking "Agree", you agree to the [FluxDev Non-Commercial License
9
+ Agreement](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)
10
+ and acknowledge the [Acceptable Use
11
+ Policy](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/POLICY.md).
12
+ tags:
13
+ - text-to-image
14
+ - image-generation
15
+ - flux
16
+ - diffusers
17
+ pipeline_tag: text-to-image
18
+ base_model:
19
+ - black-forest-labs/FLUX.1-dev
20
+ library_name: diffusers
21
+ ---
22
+
23
+ ![FLUX.1 Krea [dev] Grid](./teaser.png)
24
+
25
+
26
+ `FLUX.1 Krea [dev]` is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions.
27
+ For more information, please read our [blog post](https://bfl.ai/announcements/flux-1-krea-dev) and [Krea's blog post](https://www.krea.ai/blog/flux-krea-open-source-release).
28
+
29
+
30
+ # Key Features
31
+ 1. Cutting-edge output quality, with a focus on aesthetic photography.
32
+ 2. Competitive prompt following, matching the performance of closed source alternatives.
33
+ 3. Trained using guidance distillation, making `FLUX.1 Krea [dev]` more efficient.
34
+ 4. Open weights to drive new scientific research, and empower artists to develop innovative workflows.
35
+ 5. Generated outputs can be used for personal, scientific, and commercial purposes, as described in the [flux-1-dev-non-commercial-license](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev).
36
+
37
+ # Usage
38
+ `FLUX.1 Krea [dev]` can be used as a drop-in replacement in every system that supports the original `FLUX.1 [dev]`.
39
+ A reference implementation of `FLUX.1 [dev]` is in our dedicated [github repository](https://github.com/black-forest-labs/flux).
40
+ Developers and creatives looking to build on top of `FLUX.1 [dev]` are encouraged to use this as a starting point.
41
+
42
+ `FLUX.1 Krea [dev]` is also available in both [ComfyUI](https://github.com/comfyanonymous/ComfyUI) and [diffusers](https://github.com/huggingface/diffusers).
43
+
44
+ ## ComfyUI
45
+ To use `FLUX.1 Krea [dev]` in [Comfy UI](https://github.com/comfyanonymous/ComfyUI) download the `*.safetensors` weights [here](https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev/resolve/main/flux1-krea-dev.safetensors)
46
+
47
+ ## 🧨 diffusers
48
+ To use `FLUX.1 Krea [dev]` in [diffusers](https://github.com/huggingface/diffusers), first install or upgrade diffusers
49
+
50
+ ```shell
51
+ pip install -U diffusers
52
+ ```
53
+
54
+ Then you can use `FluxPipeline` to run the model
55
+
56
+ ```python
57
+ import torch
58
+ from diffusers import FluxPipeline
59
+
60
+ pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-Krea-dev", torch_dtype=torch.bfloat16)
61
+ pipe.enable_model_cpu_offload() #save some VRAM by offloading the model to CPU. Remove this if you have enough GPU VRAM
62
+
63
+ prompt = "A frog holding a sign that says hello world"
64
+ image = pipe(
65
+ prompt,
66
+ height=1024,
67
+ width=1024,
68
+ guidance_scale=4.5,
69
+ ).images[0]
70
+ image.save("flux-krea-dev.png")
71
+ ```
72
+
73
+ To learn more check out the [diffusers](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux) documentation
74
+
75
+ ---
76
+
77
+ # Limitations
78
+ - This model is not intended or able to provide factual information.
79
+ - As a statistical model this checkpoint might amplify existing societal biases.
80
+ - The model may fail to generate output that matches the prompts.
81
+ - Prompt following is heavily influenced by the prompting-style.
82
+
83
+ ---
84
+
85
+ # Out-of-Scope Use
86
+ The model and its derivatives may not be used
87
+
88
+ - In any way that violates any applicable national, federal, state, local or international law or regulation.
89
+ - For the purpose of exploiting, harming or attempting to exploit or harm minors in any way; including but not limited to the solicitation, creation, acquisition, or dissemination of child exploitative content.
90
+ - To generate or disseminate verifiably false information and/or content with the purpose of harming others.
91
+ - To generate or disseminate personal identifiable information that can be used to harm an individual.
92
+ - To harass, abuse, threaten, stalk, or bully individuals or groups of individuals.
93
+ - To create non-consensual nudity or illegal pornographic content.
94
+ - For fully automated decision making that adversely impacts an individual's legal rights or otherwise creates or modifies a binding, enforceable obligation.
95
+ - Generating or facilitating large-scale disinformation campaigns.
96
+ - Please reference our [content filters](https://github.com/black-forest-labs/flux/blob/main/src/flux/content_filters.py) to avoid such generations.
97
+
98
+ ---
99
+
100
+ # Risks
101
+
102
+ Black Forest Labs (BFL) and Krea are committed to the responsible development of generative AI technology. Prior to releasing FLUX.1 Krea [dev], BFL and Krea collaboratively evaluated and mitigated a number of risks in the FLUX.1 Krea [dev] model and services, including the generation of unlawful content. We implemented a series of pre-release mitigations to help prevent misuse by third parties, with additional post-release mitigations to help address residual risks:
103
+ 1. **Pre-training mitigation.** BFL filtered pre-training data for multiple categories of “not safe for work” (NSFW) and unlawful content to help prevent a user generating unlawful content in response to text prompts or uploaded images.
104
+ 2. **Post-training mitigation.** BFL has partnered with the Internet Watch Foundation, an independent nonprofit organization dedicated to preventing online abuse, to filter known child sexual abuse material (CSAM) from post-training data. Subsequently, BFL and Krea undertook multiple rounds of targeted fine-tuning to provide additional mitigation against potential abuse. By inhibiting certain behaviors and concepts in the trained model, these techniques can help to prevent a user generating synthetic CSAM or nonconsensual intimate imagery (NCII) from a text prompt.
105
+ 3. **Pre-release evaluation.** Throughout this process, BFL conducted internal and external third-party evaluations of model checkpoints to identify further opportunities for improvement. The third-party evaluations focused on eliciting CSAM and NCII through adversarial testing of the text-to-image model with text-only prompts. We also conducted internal evaluations of the proposed release checkpoints, comparing the model with other leading openly-available generative image models from other companies. The final FLUX.1 Krea [dev] open-weight model checkpoint demonstrated very high resilience against violative inputs, demonstrating higher resilience than other similar open-weight models across these risk categories. Based on these findings, we approved the release of the FLUX.1 Krea [dev] model as openly-available weights under a non-commercial license to support third-party research and development.
106
+ 4. **Inference filters.** The BFL Github repository for the open FLUX.1 Krea [dev] model includes filters for illegal or infringing content. Filters or manual review must be used with the model under the terms of the FLUX.1 [dev] Non-Commercial License. We may approach known deployers of the FLUX.1 Krea [dev] model at random to verify that filters or manual review processes are in place.
107
+ 5. **Policies.** Our FLUX.1 [dev] Non-Commercial License prohibits the generation of unlawful content or the use of generated content for unlawful, defamatory, or abusive purposes. Developers and users must consent to these conditions to access the FLUX.1 Krea [dev] model.
108
+ 6. **Monitoring.** BFL is monitoring for patterns of violative use after release, and may ban developers who we detect intentionally and repeatedly violate our policies. Additionally, BFL provides a dedicated email address (safety@blackforestlabs.ai) to solicit feedback from the community. BFL maintains a reporting relationship with organizations such as the Internet Watch Foundation and the National Center for Missing and Exploited Children, and BFL welcomes ongoing engagement with authorities, developers, and researchers to share intelligence about emerging risks and develop effective mitigations.
109
+
110
+ ---
111
+
112
+ # License
113
+ This model falls under the [`FLUX.1 [dev]` Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
text_encoder/0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bed7a5d5508c439a8c2f4bee65facb983ad5b51ed62eabb9d0bbebef38641751
3
+ size 69436582
text_encoder/model.safetensors.index.json ADDED
@@ -0,0 +1,352 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "quantization_level": "4",
4
+ "mflux_version": "0.3.0"
5
+ },
6
+ "weight_map": {
7
+ "text_model.encoder.layers.0.self_attn.q_proj.weight": "0.safetensors",
8
+ "text_model.encoder.layers.0.self_attn.q_proj.scales": "0.safetensors",
9
+ "text_model.encoder.layers.0.self_attn.q_proj.biases": "0.safetensors",
10
+ "text_model.encoder.layers.0.self_attn.q_proj.bias": "0.safetensors",
11
+ "text_model.encoder.layers.0.self_attn.k_proj.weight": "0.safetensors",
12
+ "text_model.encoder.layers.0.self_attn.k_proj.scales": "0.safetensors",
13
+ "text_model.encoder.layers.0.self_attn.k_proj.biases": "0.safetensors",
14
+ "text_model.encoder.layers.0.self_attn.k_proj.bias": "0.safetensors",
15
+ "text_model.encoder.layers.0.self_attn.v_proj.weight": "0.safetensors",
16
+ "text_model.encoder.layers.0.self_attn.v_proj.scales": "0.safetensors",
17
+ "text_model.encoder.layers.0.self_attn.v_proj.biases": "0.safetensors",
18
+ "text_model.encoder.layers.0.self_attn.v_proj.bias": "0.safetensors",
19
+ "text_model.encoder.layers.0.self_attn.out_proj.weight": "0.safetensors",
20
+ "text_model.encoder.layers.0.self_attn.out_proj.scales": "0.safetensors",
21
+ "text_model.encoder.layers.0.self_attn.out_proj.biases": "0.safetensors",
22
+ "text_model.encoder.layers.0.self_attn.out_proj.bias": "0.safetensors",
23
+ "text_model.encoder.layers.0.layer_norm1.weight": "0.safetensors",
24
+ "text_model.encoder.layers.0.layer_norm1.bias": "0.safetensors",
25
+ "text_model.encoder.layers.0.mlp.fc1.weight": "0.safetensors",
26
+ "text_model.encoder.layers.0.mlp.fc1.scales": "0.safetensors",
27
+ "text_model.encoder.layers.0.mlp.fc1.biases": "0.safetensors",
28
+ "text_model.encoder.layers.0.mlp.fc1.bias": "0.safetensors",
29
+ "text_model.encoder.layers.0.mlp.fc2.weight": "0.safetensors",
30
+ "text_model.encoder.layers.0.mlp.fc2.scales": "0.safetensors",
31
+ "text_model.encoder.layers.0.mlp.fc2.biases": "0.safetensors",
32
+ "text_model.encoder.layers.0.mlp.fc2.bias": "0.safetensors",
33
+ "text_model.encoder.layers.0.layer_norm2.weight": "0.safetensors",
34
+ "text_model.encoder.layers.0.layer_norm2.bias": "0.safetensors",
35
+ "text_model.encoder.layers.1.self_attn.q_proj.weight": "0.safetensors",
36
+ "text_model.encoder.layers.1.self_attn.q_proj.scales": "0.safetensors",
37
+ "text_model.encoder.layers.1.self_attn.q_proj.biases": "0.safetensors",
38
+ "text_model.encoder.layers.1.self_attn.q_proj.bias": "0.safetensors",
39
+ "text_model.encoder.layers.1.self_attn.k_proj.weight": "0.safetensors",
40
+ "text_model.encoder.layers.1.self_attn.k_proj.scales": "0.safetensors",
41
+ "text_model.encoder.layers.1.self_attn.k_proj.biases": "0.safetensors",
42
+ "text_model.encoder.layers.1.self_attn.k_proj.bias": "0.safetensors",
43
+ "text_model.encoder.layers.1.self_attn.v_proj.weight": "0.safetensors",
44
+ "text_model.encoder.layers.1.self_attn.v_proj.scales": "0.safetensors",
45
+ "text_model.encoder.layers.1.self_attn.v_proj.biases": "0.safetensors",
46
+ "text_model.encoder.layers.1.self_attn.v_proj.bias": "0.safetensors",
47
+ "text_model.encoder.layers.1.self_attn.out_proj.weight": "0.safetensors",
48
+ "text_model.encoder.layers.1.self_attn.out_proj.scales": "0.safetensors",
49
+ "text_model.encoder.layers.1.self_attn.out_proj.biases": "0.safetensors",
50
+ "text_model.encoder.layers.1.self_attn.out_proj.bias": "0.safetensors",
51
+ "text_model.encoder.layers.1.layer_norm1.weight": "0.safetensors",
52
+ "text_model.encoder.layers.1.layer_norm1.bias": "0.safetensors",
53
+ "text_model.encoder.layers.1.mlp.fc1.weight": "0.safetensors",
54
+ "text_model.encoder.layers.1.mlp.fc1.scales": "0.safetensors",
55
+ "text_model.encoder.layers.1.mlp.fc1.biases": "0.safetensors",
56
+ "text_model.encoder.layers.1.mlp.fc1.bias": "0.safetensors",
57
+ "text_model.encoder.layers.1.mlp.fc2.weight": "0.safetensors",
58
+ "text_model.encoder.layers.1.mlp.fc2.scales": "0.safetensors",
59
+ "text_model.encoder.layers.1.mlp.fc2.biases": "0.safetensors",
60
+ "text_model.encoder.layers.1.mlp.fc2.bias": "0.safetensors",
61
+ "text_model.encoder.layers.1.layer_norm2.weight": "0.safetensors",
62
+ "text_model.encoder.layers.1.layer_norm2.bias": "0.safetensors",
63
+ "text_model.encoder.layers.2.self_attn.q_proj.weight": "0.safetensors",
64
+ "text_model.encoder.layers.2.self_attn.q_proj.scales": "0.safetensors",
65
+ "text_model.encoder.layers.2.self_attn.q_proj.biases": "0.safetensors",
66
+ "text_model.encoder.layers.2.self_attn.q_proj.bias": "0.safetensors",
67
+ "text_model.encoder.layers.2.self_attn.k_proj.weight": "0.safetensors",
68
+ "text_model.encoder.layers.2.self_attn.k_proj.scales": "0.safetensors",
69
+ "text_model.encoder.layers.2.self_attn.k_proj.biases": "0.safetensors",
70
+ "text_model.encoder.layers.2.self_attn.k_proj.bias": "0.safetensors",
71
+ "text_model.encoder.layers.2.self_attn.v_proj.weight": "0.safetensors",
72
+ "text_model.encoder.layers.2.self_attn.v_proj.scales": "0.safetensors",
73
+ "text_model.encoder.layers.2.self_attn.v_proj.biases": "0.safetensors",
74
+ "text_model.encoder.layers.2.self_attn.v_proj.bias": "0.safetensors",
75
+ "text_model.encoder.layers.2.self_attn.out_proj.weight": "0.safetensors",
76
+ "text_model.encoder.layers.2.self_attn.out_proj.scales": "0.safetensors",
77
+ "text_model.encoder.layers.2.self_attn.out_proj.biases": "0.safetensors",
78
+ "text_model.encoder.layers.2.self_attn.out_proj.bias": "0.safetensors",
79
+ "text_model.encoder.layers.2.layer_norm1.weight": "0.safetensors",
80
+ "text_model.encoder.layers.2.layer_norm1.bias": "0.safetensors",
81
+ "text_model.encoder.layers.2.mlp.fc1.weight": "0.safetensors",
82
+ "text_model.encoder.layers.2.mlp.fc1.scales": "0.safetensors",
83
+ "text_model.encoder.layers.2.mlp.fc1.biases": "0.safetensors",
84
+ "text_model.encoder.layers.2.mlp.fc1.bias": "0.safetensors",
85
+ "text_model.encoder.layers.2.mlp.fc2.weight": "0.safetensors",
86
+ "text_model.encoder.layers.2.mlp.fc2.scales": "0.safetensors",
87
+ "text_model.encoder.layers.2.mlp.fc2.biases": "0.safetensors",
88
+ "text_model.encoder.layers.2.mlp.fc2.bias": "0.safetensors",
89
+ "text_model.encoder.layers.2.layer_norm2.weight": "0.safetensors",
90
+ "text_model.encoder.layers.2.layer_norm2.bias": "0.safetensors",
91
+ "text_model.encoder.layers.3.self_attn.q_proj.weight": "0.safetensors",
92
+ "text_model.encoder.layers.3.self_attn.q_proj.scales": "0.safetensors",
93
+ "text_model.encoder.layers.3.self_attn.q_proj.biases": "0.safetensors",
94
+ "text_model.encoder.layers.3.self_attn.q_proj.bias": "0.safetensors",
95
+ "text_model.encoder.layers.3.self_attn.k_proj.weight": "0.safetensors",
96
+ "text_model.encoder.layers.3.self_attn.k_proj.scales": "0.safetensors",
97
+ "text_model.encoder.layers.3.self_attn.k_proj.biases": "0.safetensors",
98
+ "text_model.encoder.layers.3.self_attn.k_proj.bias": "0.safetensors",
99
+ "text_model.encoder.layers.3.self_attn.v_proj.weight": "0.safetensors",
100
+ "text_model.encoder.layers.3.self_attn.v_proj.scales": "0.safetensors",
101
+ "text_model.encoder.layers.3.self_attn.v_proj.biases": "0.safetensors",
102
+ "text_model.encoder.layers.3.self_attn.v_proj.bias": "0.safetensors",
103
+ "text_model.encoder.layers.3.self_attn.out_proj.weight": "0.safetensors",
104
+ "text_model.encoder.layers.3.self_attn.out_proj.scales": "0.safetensors",
105
+ "text_model.encoder.layers.3.self_attn.out_proj.biases": "0.safetensors",
106
+ "text_model.encoder.layers.3.self_attn.out_proj.bias": "0.safetensors",
107
+ "text_model.encoder.layers.3.layer_norm1.weight": "0.safetensors",
108
+ "text_model.encoder.layers.3.layer_norm1.bias": "0.safetensors",
109
+ "text_model.encoder.layers.3.mlp.fc1.weight": "0.safetensors",
110
+ "text_model.encoder.layers.3.mlp.fc1.scales": "0.safetensors",
111
+ "text_model.encoder.layers.3.mlp.fc1.biases": "0.safetensors",
112
+ "text_model.encoder.layers.3.mlp.fc1.bias": "0.safetensors",
113
+ "text_model.encoder.layers.3.mlp.fc2.weight": "0.safetensors",
114
+ "text_model.encoder.layers.3.mlp.fc2.scales": "0.safetensors",
115
+ "text_model.encoder.layers.3.mlp.fc2.biases": "0.safetensors",
116
+ "text_model.encoder.layers.3.mlp.fc2.bias": "0.safetensors",
117
+ "text_model.encoder.layers.3.layer_norm2.weight": "0.safetensors",
118
+ "text_model.encoder.layers.3.layer_norm2.bias": "0.safetensors",
119
+ "text_model.encoder.layers.4.self_attn.q_proj.weight": "0.safetensors",
120
+ "text_model.encoder.layers.4.self_attn.q_proj.scales": "0.safetensors",
121
+ "text_model.encoder.layers.4.self_attn.q_proj.biases": "0.safetensors",
122
+ "text_model.encoder.layers.4.self_attn.q_proj.bias": "0.safetensors",
123
+ "text_model.encoder.layers.4.self_attn.k_proj.weight": "0.safetensors",
124
+ "text_model.encoder.layers.4.self_attn.k_proj.scales": "0.safetensors",
125
+ "text_model.encoder.layers.4.self_attn.k_proj.biases": "0.safetensors",
126
+ "text_model.encoder.layers.4.self_attn.k_proj.bias": "0.safetensors",
127
+ "text_model.encoder.layers.4.self_attn.v_proj.weight": "0.safetensors",
128
+ "text_model.encoder.layers.4.self_attn.v_proj.scales": "0.safetensors",
129
+ "text_model.encoder.layers.4.self_attn.v_proj.biases": "0.safetensors",
130
+ "text_model.encoder.layers.4.self_attn.v_proj.bias": "0.safetensors",
131
+ "text_model.encoder.layers.4.self_attn.out_proj.weight": "0.safetensors",
132
+ "text_model.encoder.layers.4.self_attn.out_proj.scales": "0.safetensors",
133
+ "text_model.encoder.layers.4.self_attn.out_proj.biases": "0.safetensors",
134
+ "text_model.encoder.layers.4.self_attn.out_proj.bias": "0.safetensors",
135
+ "text_model.encoder.layers.4.layer_norm1.weight": "0.safetensors",
136
+ "text_model.encoder.layers.4.layer_norm1.bias": "0.safetensors",
137
+ "text_model.encoder.layers.4.mlp.fc1.weight": "0.safetensors",
138
+ "text_model.encoder.layers.4.mlp.fc1.scales": "0.safetensors",
139
+ "text_model.encoder.layers.4.mlp.fc1.biases": "0.safetensors",
140
+ "text_model.encoder.layers.4.mlp.fc1.bias": "0.safetensors",
141
+ "text_model.encoder.layers.4.mlp.fc2.weight": "0.safetensors",
142
+ "text_model.encoder.layers.4.mlp.fc2.scales": "0.safetensors",
143
+ "text_model.encoder.layers.4.mlp.fc2.biases": "0.safetensors",
144
+ "text_model.encoder.layers.4.mlp.fc2.bias": "0.safetensors",
145
+ "text_model.encoder.layers.4.layer_norm2.weight": "0.safetensors",
146
+ "text_model.encoder.layers.4.layer_norm2.bias": "0.safetensors",
147
+ "text_model.encoder.layers.5.self_attn.q_proj.weight": "0.safetensors",
148
+ "text_model.encoder.layers.5.self_attn.q_proj.scales": "0.safetensors",
149
+ "text_model.encoder.layers.5.self_attn.q_proj.biases": "0.safetensors",
150
+ "text_model.encoder.layers.5.self_attn.q_proj.bias": "0.safetensors",
151
+ "text_model.encoder.layers.5.self_attn.k_proj.weight": "0.safetensors",
152
+ "text_model.encoder.layers.5.self_attn.k_proj.scales": "0.safetensors",
153
+ "text_model.encoder.layers.5.self_attn.k_proj.biases": "0.safetensors",
154
+ "text_model.encoder.layers.5.self_attn.k_proj.bias": "0.safetensors",
155
+ "text_model.encoder.layers.5.self_attn.v_proj.weight": "0.safetensors",
156
+ "text_model.encoder.layers.5.self_attn.v_proj.scales": "0.safetensors",
157
+ "text_model.encoder.layers.5.self_attn.v_proj.biases": "0.safetensors",
158
+ "text_model.encoder.layers.5.self_attn.v_proj.bias": "0.safetensors",
159
+ "text_model.encoder.layers.5.self_attn.out_proj.weight": "0.safetensors",
160
+ "text_model.encoder.layers.5.self_attn.out_proj.scales": "0.safetensors",
161
+ "text_model.encoder.layers.5.self_attn.out_proj.biases": "0.safetensors",
162
+ "text_model.encoder.layers.5.self_attn.out_proj.bias": "0.safetensors",
163
+ "text_model.encoder.layers.5.layer_norm1.weight": "0.safetensors",
164
+ "text_model.encoder.layers.5.layer_norm1.bias": "0.safetensors",
165
+ "text_model.encoder.layers.5.mlp.fc1.weight": "0.safetensors",
166
+ "text_model.encoder.layers.5.mlp.fc1.scales": "0.safetensors",
167
+ "text_model.encoder.layers.5.mlp.fc1.biases": "0.safetensors",
168
+ "text_model.encoder.layers.5.mlp.fc1.bias": "0.safetensors",
169
+ "text_model.encoder.layers.5.mlp.fc2.weight": "0.safetensors",
170
+ "text_model.encoder.layers.5.mlp.fc2.scales": "0.safetensors",
171
+ "text_model.encoder.layers.5.mlp.fc2.biases": "0.safetensors",
172
+ "text_model.encoder.layers.5.mlp.fc2.bias": "0.safetensors",
173
+ "text_model.encoder.layers.5.layer_norm2.weight": "0.safetensors",
174
+ "text_model.encoder.layers.5.layer_norm2.bias": "0.safetensors",
175
+ "text_model.encoder.layers.6.self_attn.q_proj.weight": "0.safetensors",
176
+ "text_model.encoder.layers.6.self_attn.q_proj.scales": "0.safetensors",
177
+ "text_model.encoder.layers.6.self_attn.q_proj.biases": "0.safetensors",
178
+ "text_model.encoder.layers.6.self_attn.q_proj.bias": "0.safetensors",
179
+ "text_model.encoder.layers.6.self_attn.k_proj.weight": "0.safetensors",
180
+ "text_model.encoder.layers.6.self_attn.k_proj.scales": "0.safetensors",
181
+ "text_model.encoder.layers.6.self_attn.k_proj.biases": "0.safetensors",
182
+ "text_model.encoder.layers.6.self_attn.k_proj.bias": "0.safetensors",
183
+ "text_model.encoder.layers.6.self_attn.v_proj.weight": "0.safetensors",
184
+ "text_model.encoder.layers.6.self_attn.v_proj.scales": "0.safetensors",
185
+ "text_model.encoder.layers.6.self_attn.v_proj.biases": "0.safetensors",
186
+ "text_model.encoder.layers.6.self_attn.v_proj.bias": "0.safetensors",
187
+ "text_model.encoder.layers.6.self_attn.out_proj.weight": "0.safetensors",
188
+ "text_model.encoder.layers.6.self_attn.out_proj.scales": "0.safetensors",
189
+ "text_model.encoder.layers.6.self_attn.out_proj.biases": "0.safetensors",
190
+ "text_model.encoder.layers.6.self_attn.out_proj.bias": "0.safetensors",
191
+ "text_model.encoder.layers.6.layer_norm1.weight": "0.safetensors",
192
+ "text_model.encoder.layers.6.layer_norm1.bias": "0.safetensors",
193
+ "text_model.encoder.layers.6.mlp.fc1.weight": "0.safetensors",
194
+ "text_model.encoder.layers.6.mlp.fc1.scales": "0.safetensors",
195
+ "text_model.encoder.layers.6.mlp.fc1.biases": "0.safetensors",
196
+ "text_model.encoder.layers.6.mlp.fc1.bias": "0.safetensors",
197
+ "text_model.encoder.layers.6.mlp.fc2.weight": "0.safetensors",
198
+ "text_model.encoder.layers.6.mlp.fc2.scales": "0.safetensors",
199
+ "text_model.encoder.layers.6.mlp.fc2.biases": "0.safetensors",
200
+ "text_model.encoder.layers.6.mlp.fc2.bias": "0.safetensors",
201
+ "text_model.encoder.layers.6.layer_norm2.weight": "0.safetensors",
202
+ "text_model.encoder.layers.6.layer_norm2.bias": "0.safetensors",
203
+ "text_model.encoder.layers.7.self_attn.q_proj.weight": "0.safetensors",
204
+ "text_model.encoder.layers.7.self_attn.q_proj.scales": "0.safetensors",
205
+ "text_model.encoder.layers.7.self_attn.q_proj.biases": "0.safetensors",
206
+ "text_model.encoder.layers.7.self_attn.q_proj.bias": "0.safetensors",
207
+ "text_model.encoder.layers.7.self_attn.k_proj.weight": "0.safetensors",
208
+ "text_model.encoder.layers.7.self_attn.k_proj.scales": "0.safetensors",
209
+ "text_model.encoder.layers.7.self_attn.k_proj.biases": "0.safetensors",
210
+ "text_model.encoder.layers.7.self_attn.k_proj.bias": "0.safetensors",
211
+ "text_model.encoder.layers.7.self_attn.v_proj.weight": "0.safetensors",
212
+ "text_model.encoder.layers.7.self_attn.v_proj.scales": "0.safetensors",
213
+ "text_model.encoder.layers.7.self_attn.v_proj.biases": "0.safetensors",
214
+ "text_model.encoder.layers.7.self_attn.v_proj.bias": "0.safetensors",
215
+ "text_model.encoder.layers.7.self_attn.out_proj.weight": "0.safetensors",
216
+ "text_model.encoder.layers.7.self_attn.out_proj.scales": "0.safetensors",
217
+ "text_model.encoder.layers.7.self_attn.out_proj.biases": "0.safetensors",
218
+ "text_model.encoder.layers.7.self_attn.out_proj.bias": "0.safetensors",
219
+ "text_model.encoder.layers.7.layer_norm1.weight": "0.safetensors",
220
+ "text_model.encoder.layers.7.layer_norm1.bias": "0.safetensors",
221
+ "text_model.encoder.layers.7.mlp.fc1.weight": "0.safetensors",
222
+ "text_model.encoder.layers.7.mlp.fc1.scales": "0.safetensors",
223
+ "text_model.encoder.layers.7.mlp.fc1.biases": "0.safetensors",
224
+ "text_model.encoder.layers.7.mlp.fc1.bias": "0.safetensors",
225
+ "text_model.encoder.layers.7.mlp.fc2.weight": "0.safetensors",
226
+ "text_model.encoder.layers.7.mlp.fc2.scales": "0.safetensors",
227
+ "text_model.encoder.layers.7.mlp.fc2.biases": "0.safetensors",
228
+ "text_model.encoder.layers.7.mlp.fc2.bias": "0.safetensors",
229
+ "text_model.encoder.layers.7.layer_norm2.weight": "0.safetensors",
230
+ "text_model.encoder.layers.7.layer_norm2.bias": "0.safetensors",
231
+ "text_model.encoder.layers.8.self_attn.q_proj.weight": "0.safetensors",
232
+ "text_model.encoder.layers.8.self_attn.q_proj.scales": "0.safetensors",
233
+ "text_model.encoder.layers.8.self_attn.q_proj.biases": "0.safetensors",
234
+ "text_model.encoder.layers.8.self_attn.q_proj.bias": "0.safetensors",
235
+ "text_model.encoder.layers.8.self_attn.k_proj.weight": "0.safetensors",
236
+ "text_model.encoder.layers.8.self_attn.k_proj.scales": "0.safetensors",
237
+ "text_model.encoder.layers.8.self_attn.k_proj.biases": "0.safetensors",
238
+ "text_model.encoder.layers.8.self_attn.k_proj.bias": "0.safetensors",
239
+ "text_model.encoder.layers.8.self_attn.v_proj.weight": "0.safetensors",
240
+ "text_model.encoder.layers.8.self_attn.v_proj.scales": "0.safetensors",
241
+ "text_model.encoder.layers.8.self_attn.v_proj.biases": "0.safetensors",
242
+ "text_model.encoder.layers.8.self_attn.v_proj.bias": "0.safetensors",
243
+ "text_model.encoder.layers.8.self_attn.out_proj.weight": "0.safetensors",
244
+ "text_model.encoder.layers.8.self_attn.out_proj.scales": "0.safetensors",
245
+ "text_model.encoder.layers.8.self_attn.out_proj.biases": "0.safetensors",
246
+ "text_model.encoder.layers.8.self_attn.out_proj.bias": "0.safetensors",
247
+ "text_model.encoder.layers.8.layer_norm1.weight": "0.safetensors",
248
+ "text_model.encoder.layers.8.layer_norm1.bias": "0.safetensors",
249
+ "text_model.encoder.layers.8.mlp.fc1.weight": "0.safetensors",
250
+ "text_model.encoder.layers.8.mlp.fc1.scales": "0.safetensors",
251
+ "text_model.encoder.layers.8.mlp.fc1.biases": "0.safetensors",
252
+ "text_model.encoder.layers.8.mlp.fc1.bias": "0.safetensors",
253
+ "text_model.encoder.layers.8.mlp.fc2.weight": "0.safetensors",
254
+ "text_model.encoder.layers.8.mlp.fc2.scales": "0.safetensors",
255
+ "text_model.encoder.layers.8.mlp.fc2.biases": "0.safetensors",
256
+ "text_model.encoder.layers.8.mlp.fc2.bias": "0.safetensors",
257
+ "text_model.encoder.layers.8.layer_norm2.weight": "0.safetensors",
258
+ "text_model.encoder.layers.8.layer_norm2.bias": "0.safetensors",
259
+ "text_model.encoder.layers.9.self_attn.q_proj.weight": "0.safetensors",
260
+ "text_model.encoder.layers.9.self_attn.q_proj.scales": "0.safetensors",
261
+ "text_model.encoder.layers.9.self_attn.q_proj.biases": "0.safetensors",
262
+ "text_model.encoder.layers.9.self_attn.q_proj.bias": "0.safetensors",
263
+ "text_model.encoder.layers.9.self_attn.k_proj.weight": "0.safetensors",
264
+ "text_model.encoder.layers.9.self_attn.k_proj.scales": "0.safetensors",
265
+ "text_model.encoder.layers.9.self_attn.k_proj.biases": "0.safetensors",
266
+ "text_model.encoder.layers.9.self_attn.k_proj.bias": "0.safetensors",
267
+ "text_model.encoder.layers.9.self_attn.v_proj.weight": "0.safetensors",
268
+ "text_model.encoder.layers.9.self_attn.v_proj.scales": "0.safetensors",
269
+ "text_model.encoder.layers.9.self_attn.v_proj.biases": "0.safetensors",
270
+ "text_model.encoder.layers.9.self_attn.v_proj.bias": "0.safetensors",
271
+ "text_model.encoder.layers.9.self_attn.out_proj.weight": "0.safetensors",
272
+ "text_model.encoder.layers.9.self_attn.out_proj.scales": "0.safetensors",
273
+ "text_model.encoder.layers.9.self_attn.out_proj.biases": "0.safetensors",
274
+ "text_model.encoder.layers.9.self_attn.out_proj.bias": "0.safetensors",
275
+ "text_model.encoder.layers.9.layer_norm1.weight": "0.safetensors",
276
+ "text_model.encoder.layers.9.layer_norm1.bias": "0.safetensors",
277
+ "text_model.encoder.layers.9.mlp.fc1.weight": "0.safetensors",
278
+ "text_model.encoder.layers.9.mlp.fc1.scales": "0.safetensors",
279
+ "text_model.encoder.layers.9.mlp.fc1.biases": "0.safetensors",
280
+ "text_model.encoder.layers.9.mlp.fc1.bias": "0.safetensors",
281
+ "text_model.encoder.layers.9.mlp.fc2.weight": "0.safetensors",
282
+ "text_model.encoder.layers.9.mlp.fc2.scales": "0.safetensors",
283
+ "text_model.encoder.layers.9.mlp.fc2.biases": "0.safetensors",
284
+ "text_model.encoder.layers.9.mlp.fc2.bias": "0.safetensors",
285
+ "text_model.encoder.layers.9.layer_norm2.weight": "0.safetensors",
286
+ "text_model.encoder.layers.9.layer_norm2.bias": "0.safetensors",
287
+ "text_model.encoder.layers.10.self_attn.q_proj.weight": "0.safetensors",
288
+ "text_model.encoder.layers.10.self_attn.q_proj.scales": "0.safetensors",
289
+ "text_model.encoder.layers.10.self_attn.q_proj.biases": "0.safetensors",
290
+ "text_model.encoder.layers.10.self_attn.q_proj.bias": "0.safetensors",
291
+ "text_model.encoder.layers.10.self_attn.k_proj.weight": "0.safetensors",
292
+ "text_model.encoder.layers.10.self_attn.k_proj.scales": "0.safetensors",
293
+ "text_model.encoder.layers.10.self_attn.k_proj.biases": "0.safetensors",
294
+ "text_model.encoder.layers.10.self_attn.k_proj.bias": "0.safetensors",
295
+ "text_model.encoder.layers.10.self_attn.v_proj.weight": "0.safetensors",
296
+ "text_model.encoder.layers.10.self_attn.v_proj.scales": "0.safetensors",
297
+ "text_model.encoder.layers.10.self_attn.v_proj.biases": "0.safetensors",
298
+ "text_model.encoder.layers.10.self_attn.v_proj.bias": "0.safetensors",
299
+ "text_model.encoder.layers.10.self_attn.out_proj.weight": "0.safetensors",
300
+ "text_model.encoder.layers.10.self_attn.out_proj.scales": "0.safetensors",
301
+ "text_model.encoder.layers.10.self_attn.out_proj.biases": "0.safetensors",
302
+ "text_model.encoder.layers.10.self_attn.out_proj.bias": "0.safetensors",
303
+ "text_model.encoder.layers.10.layer_norm1.weight": "0.safetensors",
304
+ "text_model.encoder.layers.10.layer_norm1.bias": "0.safetensors",
305
+ "text_model.encoder.layers.10.mlp.fc1.weight": "0.safetensors",
306
+ "text_model.encoder.layers.10.mlp.fc1.scales": "0.safetensors",
307
+ "text_model.encoder.layers.10.mlp.fc1.biases": "0.safetensors",
308
+ "text_model.encoder.layers.10.mlp.fc1.bias": "0.safetensors",
309
+ "text_model.encoder.layers.10.mlp.fc2.weight": "0.safetensors",
310
+ "text_model.encoder.layers.10.mlp.fc2.scales": "0.safetensors",
311
+ "text_model.encoder.layers.10.mlp.fc2.biases": "0.safetensors",
312
+ "text_model.encoder.layers.10.mlp.fc2.bias": "0.safetensors",
313
+ "text_model.encoder.layers.10.layer_norm2.weight": "0.safetensors",
314
+ "text_model.encoder.layers.10.layer_norm2.bias": "0.safetensors",
315
+ "text_model.encoder.layers.11.self_attn.q_proj.weight": "0.safetensors",
316
+ "text_model.encoder.layers.11.self_attn.q_proj.scales": "0.safetensors",
317
+ "text_model.encoder.layers.11.self_attn.q_proj.biases": "0.safetensors",
318
+ "text_model.encoder.layers.11.self_attn.q_proj.bias": "0.safetensors",
319
+ "text_model.encoder.layers.11.self_attn.k_proj.weight": "0.safetensors",
320
+ "text_model.encoder.layers.11.self_attn.k_proj.scales": "0.safetensors",
321
+ "text_model.encoder.layers.11.self_attn.k_proj.biases": "0.safetensors",
322
+ "text_model.encoder.layers.11.self_attn.k_proj.bias": "0.safetensors",
323
+ "text_model.encoder.layers.11.self_attn.v_proj.weight": "0.safetensors",
324
+ "text_model.encoder.layers.11.self_attn.v_proj.scales": "0.safetensors",
325
+ "text_model.encoder.layers.11.self_attn.v_proj.biases": "0.safetensors",
326
+ "text_model.encoder.layers.11.self_attn.v_proj.bias": "0.safetensors",
327
+ "text_model.encoder.layers.11.self_attn.out_proj.weight": "0.safetensors",
328
+ "text_model.encoder.layers.11.self_attn.out_proj.scales": "0.safetensors",
329
+ "text_model.encoder.layers.11.self_attn.out_proj.biases": "0.safetensors",
330
+ "text_model.encoder.layers.11.self_attn.out_proj.bias": "0.safetensors",
331
+ "text_model.encoder.layers.11.layer_norm1.weight": "0.safetensors",
332
+ "text_model.encoder.layers.11.layer_norm1.bias": "0.safetensors",
333
+ "text_model.encoder.layers.11.mlp.fc1.weight": "0.safetensors",
334
+ "text_model.encoder.layers.11.mlp.fc1.scales": "0.safetensors",
335
+ "text_model.encoder.layers.11.mlp.fc1.biases": "0.safetensors",
336
+ "text_model.encoder.layers.11.mlp.fc1.bias": "0.safetensors",
337
+ "text_model.encoder.layers.11.mlp.fc2.weight": "0.safetensors",
338
+ "text_model.encoder.layers.11.mlp.fc2.scales": "0.safetensors",
339
+ "text_model.encoder.layers.11.mlp.fc2.biases": "0.safetensors",
340
+ "text_model.encoder.layers.11.mlp.fc2.bias": "0.safetensors",
341
+ "text_model.encoder.layers.11.layer_norm2.weight": "0.safetensors",
342
+ "text_model.encoder.layers.11.layer_norm2.bias": "0.safetensors",
343
+ "text_model.embeddings.position_embedding.weight": "0.safetensors",
344
+ "text_model.embeddings.position_embedding.scales": "0.safetensors",
345
+ "text_model.embeddings.position_embedding.biases": "0.safetensors",
346
+ "text_model.embeddings.token_embedding.weight": "0.safetensors",
347
+ "text_model.embeddings.token_embedding.scales": "0.safetensors",
348
+ "text_model.embeddings.token_embedding.biases": "0.safetensors",
349
+ "text_model.final_layer_norm.weight": "0.safetensors",
350
+ "text_model.final_layer_norm.bias": "0.safetensors"
351
+ }
352
+ }
text_encoder_2/0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6276bb5ce76b96f8749a11ea260d44b4e4086638289993d63759f5863bd9a24
3
+ size 2145878330
text_encoder_2/1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60843d0ba4fa6a3675afcef08d089f32b3f1f9e6a0547d0deac76e0fffda2d2
3
+ size 533312161
text_encoder_2/model.safetensors.index.json ADDED
@@ -0,0 +1,636 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "quantization_level": "4",
4
+ "mflux_version": "0.3.0"
5
+ },
6
+ "weight_map": {
7
+ "shared.weight": "0.safetensors",
8
+ "shared.scales": "0.safetensors",
9
+ "shared.biases": "0.safetensors",
10
+ "t5_blocks.0.attention.SelfAttention.q.weight": "0.safetensors",
11
+ "t5_blocks.0.attention.SelfAttention.q.scales": "0.safetensors",
12
+ "t5_blocks.0.attention.SelfAttention.q.biases": "0.safetensors",
13
+ "t5_blocks.0.attention.SelfAttention.k.weight": "0.safetensors",
14
+ "t5_blocks.0.attention.SelfAttention.k.scales": "0.safetensors",
15
+ "t5_blocks.0.attention.SelfAttention.k.biases": "0.safetensors",
16
+ "t5_blocks.0.attention.SelfAttention.v.weight": "0.safetensors",
17
+ "t5_blocks.0.attention.SelfAttention.v.scales": "0.safetensors",
18
+ "t5_blocks.0.attention.SelfAttention.v.biases": "0.safetensors",
19
+ "t5_blocks.0.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
20
+ "t5_blocks.0.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
21
+ "t5_blocks.0.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
22
+ "t5_blocks.0.attention.SelfAttention.o.weight": "0.safetensors",
23
+ "t5_blocks.0.attention.SelfAttention.o.scales": "0.safetensors",
24
+ "t5_blocks.0.attention.SelfAttention.o.biases": "0.safetensors",
25
+ "t5_blocks.0.attention.layer_norm.weight": "0.safetensors",
26
+ "t5_blocks.0.ff.layer_norm.weight": "0.safetensors",
27
+ "t5_blocks.0.ff.DenseReluDense.wi_0.weight": "0.safetensors",
28
+ "t5_blocks.0.ff.DenseReluDense.wi_0.scales": "0.safetensors",
29
+ "t5_blocks.0.ff.DenseReluDense.wi_0.biases": "0.safetensors",
30
+ "t5_blocks.0.ff.DenseReluDense.wi_1.weight": "0.safetensors",
31
+ "t5_blocks.0.ff.DenseReluDense.wi_1.scales": "0.safetensors",
32
+ "t5_blocks.0.ff.DenseReluDense.wi_1.biases": "0.safetensors",
33
+ "t5_blocks.0.ff.DenseReluDense.wo.weight": "0.safetensors",
34
+ "t5_blocks.0.ff.DenseReluDense.wo.scales": "0.safetensors",
35
+ "t5_blocks.0.ff.DenseReluDense.wo.biases": "0.safetensors",
36
+ "t5_blocks.1.attention.SelfAttention.q.weight": "0.safetensors",
37
+ "t5_blocks.1.attention.SelfAttention.q.scales": "0.safetensors",
38
+ "t5_blocks.1.attention.SelfAttention.q.biases": "0.safetensors",
39
+ "t5_blocks.1.attention.SelfAttention.k.weight": "0.safetensors",
40
+ "t5_blocks.1.attention.SelfAttention.k.scales": "0.safetensors",
41
+ "t5_blocks.1.attention.SelfAttention.k.biases": "0.safetensors",
42
+ "t5_blocks.1.attention.SelfAttention.v.weight": "0.safetensors",
43
+ "t5_blocks.1.attention.SelfAttention.v.scales": "0.safetensors",
44
+ "t5_blocks.1.attention.SelfAttention.v.biases": "0.safetensors",
45
+ "t5_blocks.1.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
46
+ "t5_blocks.1.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
47
+ "t5_blocks.1.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
48
+ "t5_blocks.1.attention.SelfAttention.o.weight": "0.safetensors",
49
+ "t5_blocks.1.attention.SelfAttention.o.scales": "0.safetensors",
50
+ "t5_blocks.1.attention.SelfAttention.o.biases": "0.safetensors",
51
+ "t5_blocks.1.attention.layer_norm.weight": "0.safetensors",
52
+ "t5_blocks.1.ff.layer_norm.weight": "0.safetensors",
53
+ "t5_blocks.1.ff.DenseReluDense.wi_0.weight": "0.safetensors",
54
+ "t5_blocks.1.ff.DenseReluDense.wi_0.scales": "0.safetensors",
55
+ "t5_blocks.1.ff.DenseReluDense.wi_0.biases": "0.safetensors",
56
+ "t5_blocks.1.ff.DenseReluDense.wi_1.weight": "0.safetensors",
57
+ "t5_blocks.1.ff.DenseReluDense.wi_1.scales": "0.safetensors",
58
+ "t5_blocks.1.ff.DenseReluDense.wi_1.biases": "0.safetensors",
59
+ "t5_blocks.1.ff.DenseReluDense.wo.weight": "0.safetensors",
60
+ "t5_blocks.1.ff.DenseReluDense.wo.scales": "0.safetensors",
61
+ "t5_blocks.1.ff.DenseReluDense.wo.biases": "0.safetensors",
62
+ "t5_blocks.2.attention.SelfAttention.q.weight": "0.safetensors",
63
+ "t5_blocks.2.attention.SelfAttention.q.scales": "0.safetensors",
64
+ "t5_blocks.2.attention.SelfAttention.q.biases": "0.safetensors",
65
+ "t5_blocks.2.attention.SelfAttention.k.weight": "0.safetensors",
66
+ "t5_blocks.2.attention.SelfAttention.k.scales": "0.safetensors",
67
+ "t5_blocks.2.attention.SelfAttention.k.biases": "0.safetensors",
68
+ "t5_blocks.2.attention.SelfAttention.v.weight": "0.safetensors",
69
+ "t5_blocks.2.attention.SelfAttention.v.scales": "0.safetensors",
70
+ "t5_blocks.2.attention.SelfAttention.v.biases": "0.safetensors",
71
+ "t5_blocks.2.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
72
+ "t5_blocks.2.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
73
+ "t5_blocks.2.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
74
+ "t5_blocks.2.attention.SelfAttention.o.weight": "0.safetensors",
75
+ "t5_blocks.2.attention.SelfAttention.o.scales": "0.safetensors",
76
+ "t5_blocks.2.attention.SelfAttention.o.biases": "0.safetensors",
77
+ "t5_blocks.2.attention.layer_norm.weight": "0.safetensors",
78
+ "t5_blocks.2.ff.layer_norm.weight": "0.safetensors",
79
+ "t5_blocks.2.ff.DenseReluDense.wi_0.weight": "0.safetensors",
80
+ "t5_blocks.2.ff.DenseReluDense.wi_0.scales": "0.safetensors",
81
+ "t5_blocks.2.ff.DenseReluDense.wi_0.biases": "0.safetensors",
82
+ "t5_blocks.2.ff.DenseReluDense.wi_1.weight": "0.safetensors",
83
+ "t5_blocks.2.ff.DenseReluDense.wi_1.scales": "0.safetensors",
84
+ "t5_blocks.2.ff.DenseReluDense.wi_1.biases": "0.safetensors",
85
+ "t5_blocks.2.ff.DenseReluDense.wo.weight": "0.safetensors",
86
+ "t5_blocks.2.ff.DenseReluDense.wo.scales": "0.safetensors",
87
+ "t5_blocks.2.ff.DenseReluDense.wo.biases": "0.safetensors",
88
+ "t5_blocks.3.attention.SelfAttention.q.weight": "0.safetensors",
89
+ "t5_blocks.3.attention.SelfAttention.q.scales": "0.safetensors",
90
+ "t5_blocks.3.attention.SelfAttention.q.biases": "0.safetensors",
91
+ "t5_blocks.3.attention.SelfAttention.k.weight": "0.safetensors",
92
+ "t5_blocks.3.attention.SelfAttention.k.scales": "0.safetensors",
93
+ "t5_blocks.3.attention.SelfAttention.k.biases": "0.safetensors",
94
+ "t5_blocks.3.attention.SelfAttention.v.weight": "0.safetensors",
95
+ "t5_blocks.3.attention.SelfAttention.v.scales": "0.safetensors",
96
+ "t5_blocks.3.attention.SelfAttention.v.biases": "0.safetensors",
97
+ "t5_blocks.3.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
98
+ "t5_blocks.3.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
99
+ "t5_blocks.3.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
100
+ "t5_blocks.3.attention.SelfAttention.o.weight": "0.safetensors",
101
+ "t5_blocks.3.attention.SelfAttention.o.scales": "0.safetensors",
102
+ "t5_blocks.3.attention.SelfAttention.o.biases": "0.safetensors",
103
+ "t5_blocks.3.attention.layer_norm.weight": "0.safetensors",
104
+ "t5_blocks.3.ff.layer_norm.weight": "0.safetensors",
105
+ "t5_blocks.3.ff.DenseReluDense.wi_0.weight": "0.safetensors",
106
+ "t5_blocks.3.ff.DenseReluDense.wi_0.scales": "0.safetensors",
107
+ "t5_blocks.3.ff.DenseReluDense.wi_0.biases": "0.safetensors",
108
+ "t5_blocks.3.ff.DenseReluDense.wi_1.weight": "0.safetensors",
109
+ "t5_blocks.3.ff.DenseReluDense.wi_1.scales": "0.safetensors",
110
+ "t5_blocks.3.ff.DenseReluDense.wi_1.biases": "0.safetensors",
111
+ "t5_blocks.3.ff.DenseReluDense.wo.weight": "0.safetensors",
112
+ "t5_blocks.3.ff.DenseReluDense.wo.scales": "0.safetensors",
113
+ "t5_blocks.3.ff.DenseReluDense.wo.biases": "0.safetensors",
114
+ "t5_blocks.4.attention.SelfAttention.q.weight": "0.safetensors",
115
+ "t5_blocks.4.attention.SelfAttention.q.scales": "0.safetensors",
116
+ "t5_blocks.4.attention.SelfAttention.q.biases": "0.safetensors",
117
+ "t5_blocks.4.attention.SelfAttention.k.weight": "0.safetensors",
118
+ "t5_blocks.4.attention.SelfAttention.k.scales": "0.safetensors",
119
+ "t5_blocks.4.attention.SelfAttention.k.biases": "0.safetensors",
120
+ "t5_blocks.4.attention.SelfAttention.v.weight": "0.safetensors",
121
+ "t5_blocks.4.attention.SelfAttention.v.scales": "0.safetensors",
122
+ "t5_blocks.4.attention.SelfAttention.v.biases": "0.safetensors",
123
+ "t5_blocks.4.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
124
+ "t5_blocks.4.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
125
+ "t5_blocks.4.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
126
+ "t5_blocks.4.attention.SelfAttention.o.weight": "0.safetensors",
127
+ "t5_blocks.4.attention.SelfAttention.o.scales": "0.safetensors",
128
+ "t5_blocks.4.attention.SelfAttention.o.biases": "0.safetensors",
129
+ "t5_blocks.4.attention.layer_norm.weight": "0.safetensors",
130
+ "t5_blocks.4.ff.layer_norm.weight": "0.safetensors",
131
+ "t5_blocks.4.ff.DenseReluDense.wi_0.weight": "0.safetensors",
132
+ "t5_blocks.4.ff.DenseReluDense.wi_0.scales": "0.safetensors",
133
+ "t5_blocks.4.ff.DenseReluDense.wi_0.biases": "0.safetensors",
134
+ "t5_blocks.4.ff.DenseReluDense.wi_1.weight": "0.safetensors",
135
+ "t5_blocks.4.ff.DenseReluDense.wi_1.scales": "0.safetensors",
136
+ "t5_blocks.4.ff.DenseReluDense.wi_1.biases": "0.safetensors",
137
+ "t5_blocks.4.ff.DenseReluDense.wo.weight": "0.safetensors",
138
+ "t5_blocks.4.ff.DenseReluDense.wo.scales": "0.safetensors",
139
+ "t5_blocks.4.ff.DenseReluDense.wo.biases": "0.safetensors",
140
+ "t5_blocks.5.attention.SelfAttention.q.weight": "0.safetensors",
141
+ "t5_blocks.5.attention.SelfAttention.q.scales": "0.safetensors",
142
+ "t5_blocks.5.attention.SelfAttention.q.biases": "0.safetensors",
143
+ "t5_blocks.5.attention.SelfAttention.k.weight": "0.safetensors",
144
+ "t5_blocks.5.attention.SelfAttention.k.scales": "0.safetensors",
145
+ "t5_blocks.5.attention.SelfAttention.k.biases": "0.safetensors",
146
+ "t5_blocks.5.attention.SelfAttention.v.weight": "0.safetensors",
147
+ "t5_blocks.5.attention.SelfAttention.v.scales": "0.safetensors",
148
+ "t5_blocks.5.attention.SelfAttention.v.biases": "0.safetensors",
149
+ "t5_blocks.5.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
150
+ "t5_blocks.5.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
151
+ "t5_blocks.5.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
152
+ "t5_blocks.5.attention.SelfAttention.o.weight": "0.safetensors",
153
+ "t5_blocks.5.attention.SelfAttention.o.scales": "0.safetensors",
154
+ "t5_blocks.5.attention.SelfAttention.o.biases": "0.safetensors",
155
+ "t5_blocks.5.attention.layer_norm.weight": "0.safetensors",
156
+ "t5_blocks.5.ff.layer_norm.weight": "0.safetensors",
157
+ "t5_blocks.5.ff.DenseReluDense.wi_0.weight": "0.safetensors",
158
+ "t5_blocks.5.ff.DenseReluDense.wi_0.scales": "0.safetensors",
159
+ "t5_blocks.5.ff.DenseReluDense.wi_0.biases": "0.safetensors",
160
+ "t5_blocks.5.ff.DenseReluDense.wi_1.weight": "0.safetensors",
161
+ "t5_blocks.5.ff.DenseReluDense.wi_1.scales": "0.safetensors",
162
+ "t5_blocks.5.ff.DenseReluDense.wi_1.biases": "0.safetensors",
163
+ "t5_blocks.5.ff.DenseReluDense.wo.weight": "0.safetensors",
164
+ "t5_blocks.5.ff.DenseReluDense.wo.scales": "0.safetensors",
165
+ "t5_blocks.5.ff.DenseReluDense.wo.biases": "0.safetensors",
166
+ "t5_blocks.6.attention.SelfAttention.q.weight": "0.safetensors",
167
+ "t5_blocks.6.attention.SelfAttention.q.scales": "0.safetensors",
168
+ "t5_blocks.6.attention.SelfAttention.q.biases": "0.safetensors",
169
+ "t5_blocks.6.attention.SelfAttention.k.weight": "0.safetensors",
170
+ "t5_blocks.6.attention.SelfAttention.k.scales": "0.safetensors",
171
+ "t5_blocks.6.attention.SelfAttention.k.biases": "0.safetensors",
172
+ "t5_blocks.6.attention.SelfAttention.v.weight": "0.safetensors",
173
+ "t5_blocks.6.attention.SelfAttention.v.scales": "0.safetensors",
174
+ "t5_blocks.6.attention.SelfAttention.v.biases": "0.safetensors",
175
+ "t5_blocks.6.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
176
+ "t5_blocks.6.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
177
+ "t5_blocks.6.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
178
+ "t5_blocks.6.attention.SelfAttention.o.weight": "0.safetensors",
179
+ "t5_blocks.6.attention.SelfAttention.o.scales": "0.safetensors",
180
+ "t5_blocks.6.attention.SelfAttention.o.biases": "0.safetensors",
181
+ "t5_blocks.6.attention.layer_norm.weight": "0.safetensors",
182
+ "t5_blocks.6.ff.layer_norm.weight": "0.safetensors",
183
+ "t5_blocks.6.ff.DenseReluDense.wi_0.weight": "0.safetensors",
184
+ "t5_blocks.6.ff.DenseReluDense.wi_0.scales": "0.safetensors",
185
+ "t5_blocks.6.ff.DenseReluDense.wi_0.biases": "0.safetensors",
186
+ "t5_blocks.6.ff.DenseReluDense.wi_1.weight": "0.safetensors",
187
+ "t5_blocks.6.ff.DenseReluDense.wi_1.scales": "0.safetensors",
188
+ "t5_blocks.6.ff.DenseReluDense.wi_1.biases": "0.safetensors",
189
+ "t5_blocks.6.ff.DenseReluDense.wo.weight": "0.safetensors",
190
+ "t5_blocks.6.ff.DenseReluDense.wo.scales": "0.safetensors",
191
+ "t5_blocks.6.ff.DenseReluDense.wo.biases": "0.safetensors",
192
+ "t5_blocks.7.attention.SelfAttention.q.weight": "0.safetensors",
193
+ "t5_blocks.7.attention.SelfAttention.q.scales": "0.safetensors",
194
+ "t5_blocks.7.attention.SelfAttention.q.biases": "0.safetensors",
195
+ "t5_blocks.7.attention.SelfAttention.k.weight": "0.safetensors",
196
+ "t5_blocks.7.attention.SelfAttention.k.scales": "0.safetensors",
197
+ "t5_blocks.7.attention.SelfAttention.k.biases": "0.safetensors",
198
+ "t5_blocks.7.attention.SelfAttention.v.weight": "0.safetensors",
199
+ "t5_blocks.7.attention.SelfAttention.v.scales": "0.safetensors",
200
+ "t5_blocks.7.attention.SelfAttention.v.biases": "0.safetensors",
201
+ "t5_blocks.7.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
202
+ "t5_blocks.7.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
203
+ "t5_blocks.7.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
204
+ "t5_blocks.7.attention.SelfAttention.o.weight": "0.safetensors",
205
+ "t5_blocks.7.attention.SelfAttention.o.scales": "0.safetensors",
206
+ "t5_blocks.7.attention.SelfAttention.o.biases": "0.safetensors",
207
+ "t5_blocks.7.attention.layer_norm.weight": "0.safetensors",
208
+ "t5_blocks.7.ff.layer_norm.weight": "0.safetensors",
209
+ "t5_blocks.7.ff.DenseReluDense.wi_0.weight": "0.safetensors",
210
+ "t5_blocks.7.ff.DenseReluDense.wi_0.scales": "0.safetensors",
211
+ "t5_blocks.7.ff.DenseReluDense.wi_0.biases": "0.safetensors",
212
+ "t5_blocks.7.ff.DenseReluDense.wi_1.weight": "0.safetensors",
213
+ "t5_blocks.7.ff.DenseReluDense.wi_1.scales": "0.safetensors",
214
+ "t5_blocks.7.ff.DenseReluDense.wi_1.biases": "0.safetensors",
215
+ "t5_blocks.7.ff.DenseReluDense.wo.weight": "0.safetensors",
216
+ "t5_blocks.7.ff.DenseReluDense.wo.scales": "0.safetensors",
217
+ "t5_blocks.7.ff.DenseReluDense.wo.biases": "0.safetensors",
218
+ "t5_blocks.8.attention.SelfAttention.q.weight": "0.safetensors",
219
+ "t5_blocks.8.attention.SelfAttention.q.scales": "0.safetensors",
220
+ "t5_blocks.8.attention.SelfAttention.q.biases": "0.safetensors",
221
+ "t5_blocks.8.attention.SelfAttention.k.weight": "0.safetensors",
222
+ "t5_blocks.8.attention.SelfAttention.k.scales": "0.safetensors",
223
+ "t5_blocks.8.attention.SelfAttention.k.biases": "0.safetensors",
224
+ "t5_blocks.8.attention.SelfAttention.v.weight": "0.safetensors",
225
+ "t5_blocks.8.attention.SelfAttention.v.scales": "0.safetensors",
226
+ "t5_blocks.8.attention.SelfAttention.v.biases": "0.safetensors",
227
+ "t5_blocks.8.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
228
+ "t5_blocks.8.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
229
+ "t5_blocks.8.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
230
+ "t5_blocks.8.attention.SelfAttention.o.weight": "0.safetensors",
231
+ "t5_blocks.8.attention.SelfAttention.o.scales": "0.safetensors",
232
+ "t5_blocks.8.attention.SelfAttention.o.biases": "0.safetensors",
233
+ "t5_blocks.8.attention.layer_norm.weight": "0.safetensors",
234
+ "t5_blocks.8.ff.layer_norm.weight": "0.safetensors",
235
+ "t5_blocks.8.ff.DenseReluDense.wi_0.weight": "0.safetensors",
236
+ "t5_blocks.8.ff.DenseReluDense.wi_0.scales": "0.safetensors",
237
+ "t5_blocks.8.ff.DenseReluDense.wi_0.biases": "0.safetensors",
238
+ "t5_blocks.8.ff.DenseReluDense.wi_1.weight": "0.safetensors",
239
+ "t5_blocks.8.ff.DenseReluDense.wi_1.scales": "0.safetensors",
240
+ "t5_blocks.8.ff.DenseReluDense.wi_1.biases": "0.safetensors",
241
+ "t5_blocks.8.ff.DenseReluDense.wo.weight": "0.safetensors",
242
+ "t5_blocks.8.ff.DenseReluDense.wo.scales": "0.safetensors",
243
+ "t5_blocks.8.ff.DenseReluDense.wo.biases": "0.safetensors",
244
+ "t5_blocks.9.attention.SelfAttention.q.weight": "0.safetensors",
245
+ "t5_blocks.9.attention.SelfAttention.q.scales": "0.safetensors",
246
+ "t5_blocks.9.attention.SelfAttention.q.biases": "0.safetensors",
247
+ "t5_blocks.9.attention.SelfAttention.k.weight": "0.safetensors",
248
+ "t5_blocks.9.attention.SelfAttention.k.scales": "0.safetensors",
249
+ "t5_blocks.9.attention.SelfAttention.k.biases": "0.safetensors",
250
+ "t5_blocks.9.attention.SelfAttention.v.weight": "0.safetensors",
251
+ "t5_blocks.9.attention.SelfAttention.v.scales": "0.safetensors",
252
+ "t5_blocks.9.attention.SelfAttention.v.biases": "0.safetensors",
253
+ "t5_blocks.9.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
254
+ "t5_blocks.9.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
255
+ "t5_blocks.9.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
256
+ "t5_blocks.9.attention.SelfAttention.o.weight": "0.safetensors",
257
+ "t5_blocks.9.attention.SelfAttention.o.scales": "0.safetensors",
258
+ "t5_blocks.9.attention.SelfAttention.o.biases": "0.safetensors",
259
+ "t5_blocks.9.attention.layer_norm.weight": "0.safetensors",
260
+ "t5_blocks.9.ff.layer_norm.weight": "0.safetensors",
261
+ "t5_blocks.9.ff.DenseReluDense.wi_0.weight": "0.safetensors",
262
+ "t5_blocks.9.ff.DenseReluDense.wi_0.scales": "0.safetensors",
263
+ "t5_blocks.9.ff.DenseReluDense.wi_0.biases": "0.safetensors",
264
+ "t5_blocks.9.ff.DenseReluDense.wi_1.weight": "0.safetensors",
265
+ "t5_blocks.9.ff.DenseReluDense.wi_1.scales": "0.safetensors",
266
+ "t5_blocks.9.ff.DenseReluDense.wi_1.biases": "0.safetensors",
267
+ "t5_blocks.9.ff.DenseReluDense.wo.weight": "0.safetensors",
268
+ "t5_blocks.9.ff.DenseReluDense.wo.scales": "0.safetensors",
269
+ "t5_blocks.9.ff.DenseReluDense.wo.biases": "0.safetensors",
270
+ "t5_blocks.10.attention.SelfAttention.q.weight": "0.safetensors",
271
+ "t5_blocks.10.attention.SelfAttention.q.scales": "0.safetensors",
272
+ "t5_blocks.10.attention.SelfAttention.q.biases": "0.safetensors",
273
+ "t5_blocks.10.attention.SelfAttention.k.weight": "0.safetensors",
274
+ "t5_blocks.10.attention.SelfAttention.k.scales": "0.safetensors",
275
+ "t5_blocks.10.attention.SelfAttention.k.biases": "0.safetensors",
276
+ "t5_blocks.10.attention.SelfAttention.v.weight": "0.safetensors",
277
+ "t5_blocks.10.attention.SelfAttention.v.scales": "0.safetensors",
278
+ "t5_blocks.10.attention.SelfAttention.v.biases": "0.safetensors",
279
+ "t5_blocks.10.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
280
+ "t5_blocks.10.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
281
+ "t5_blocks.10.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
282
+ "t5_blocks.10.attention.SelfAttention.o.weight": "0.safetensors",
283
+ "t5_blocks.10.attention.SelfAttention.o.scales": "0.safetensors",
284
+ "t5_blocks.10.attention.SelfAttention.o.biases": "0.safetensors",
285
+ "t5_blocks.10.attention.layer_norm.weight": "0.safetensors",
286
+ "t5_blocks.10.ff.layer_norm.weight": "0.safetensors",
287
+ "t5_blocks.10.ff.DenseReluDense.wi_0.weight": "0.safetensors",
288
+ "t5_blocks.10.ff.DenseReluDense.wi_0.scales": "0.safetensors",
289
+ "t5_blocks.10.ff.DenseReluDense.wi_0.biases": "0.safetensors",
290
+ "t5_blocks.10.ff.DenseReluDense.wi_1.weight": "0.safetensors",
291
+ "t5_blocks.10.ff.DenseReluDense.wi_1.scales": "0.safetensors",
292
+ "t5_blocks.10.ff.DenseReluDense.wi_1.biases": "0.safetensors",
293
+ "t5_blocks.10.ff.DenseReluDense.wo.weight": "0.safetensors",
294
+ "t5_blocks.10.ff.DenseReluDense.wo.scales": "0.safetensors",
295
+ "t5_blocks.10.ff.DenseReluDense.wo.biases": "0.safetensors",
296
+ "t5_blocks.11.attention.SelfAttention.q.weight": "0.safetensors",
297
+ "t5_blocks.11.attention.SelfAttention.q.scales": "0.safetensors",
298
+ "t5_blocks.11.attention.SelfAttention.q.biases": "0.safetensors",
299
+ "t5_blocks.11.attention.SelfAttention.k.weight": "0.safetensors",
300
+ "t5_blocks.11.attention.SelfAttention.k.scales": "0.safetensors",
301
+ "t5_blocks.11.attention.SelfAttention.k.biases": "0.safetensors",
302
+ "t5_blocks.11.attention.SelfAttention.v.weight": "0.safetensors",
303
+ "t5_blocks.11.attention.SelfAttention.v.scales": "0.safetensors",
304
+ "t5_blocks.11.attention.SelfAttention.v.biases": "0.safetensors",
305
+ "t5_blocks.11.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
306
+ "t5_blocks.11.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
307
+ "t5_blocks.11.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
308
+ "t5_blocks.11.attention.SelfAttention.o.weight": "0.safetensors",
309
+ "t5_blocks.11.attention.SelfAttention.o.scales": "0.safetensors",
310
+ "t5_blocks.11.attention.SelfAttention.o.biases": "0.safetensors",
311
+ "t5_blocks.11.attention.layer_norm.weight": "0.safetensors",
312
+ "t5_blocks.11.ff.layer_norm.weight": "0.safetensors",
313
+ "t5_blocks.11.ff.DenseReluDense.wi_0.weight": "0.safetensors",
314
+ "t5_blocks.11.ff.DenseReluDense.wi_0.scales": "0.safetensors",
315
+ "t5_blocks.11.ff.DenseReluDense.wi_0.biases": "0.safetensors",
316
+ "t5_blocks.11.ff.DenseReluDense.wi_1.weight": "0.safetensors",
317
+ "t5_blocks.11.ff.DenseReluDense.wi_1.scales": "0.safetensors",
318
+ "t5_blocks.11.ff.DenseReluDense.wi_1.biases": "0.safetensors",
319
+ "t5_blocks.11.ff.DenseReluDense.wo.weight": "0.safetensors",
320
+ "t5_blocks.11.ff.DenseReluDense.wo.scales": "0.safetensors",
321
+ "t5_blocks.11.ff.DenseReluDense.wo.biases": "0.safetensors",
322
+ "t5_blocks.12.attention.SelfAttention.q.weight": "0.safetensors",
323
+ "t5_blocks.12.attention.SelfAttention.q.scales": "0.safetensors",
324
+ "t5_blocks.12.attention.SelfAttention.q.biases": "0.safetensors",
325
+ "t5_blocks.12.attention.SelfAttention.k.weight": "0.safetensors",
326
+ "t5_blocks.12.attention.SelfAttention.k.scales": "0.safetensors",
327
+ "t5_blocks.12.attention.SelfAttention.k.biases": "0.safetensors",
328
+ "t5_blocks.12.attention.SelfAttention.v.weight": "0.safetensors",
329
+ "t5_blocks.12.attention.SelfAttention.v.scales": "0.safetensors",
330
+ "t5_blocks.12.attention.SelfAttention.v.biases": "0.safetensors",
331
+ "t5_blocks.12.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
332
+ "t5_blocks.12.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
333
+ "t5_blocks.12.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
334
+ "t5_blocks.12.attention.SelfAttention.o.weight": "0.safetensors",
335
+ "t5_blocks.12.attention.SelfAttention.o.scales": "0.safetensors",
336
+ "t5_blocks.12.attention.SelfAttention.o.biases": "0.safetensors",
337
+ "t5_blocks.12.attention.layer_norm.weight": "0.safetensors",
338
+ "t5_blocks.12.ff.layer_norm.weight": "0.safetensors",
339
+ "t5_blocks.12.ff.DenseReluDense.wi_0.weight": "0.safetensors",
340
+ "t5_blocks.12.ff.DenseReluDense.wi_0.scales": "0.safetensors",
341
+ "t5_blocks.12.ff.DenseReluDense.wi_0.biases": "0.safetensors",
342
+ "t5_blocks.12.ff.DenseReluDense.wi_1.weight": "0.safetensors",
343
+ "t5_blocks.12.ff.DenseReluDense.wi_1.scales": "0.safetensors",
344
+ "t5_blocks.12.ff.DenseReluDense.wi_1.biases": "0.safetensors",
345
+ "t5_blocks.12.ff.DenseReluDense.wo.weight": "0.safetensors",
346
+ "t5_blocks.12.ff.DenseReluDense.wo.scales": "0.safetensors",
347
+ "t5_blocks.12.ff.DenseReluDense.wo.biases": "0.safetensors",
348
+ "t5_blocks.13.attention.SelfAttention.q.weight": "0.safetensors",
349
+ "t5_blocks.13.attention.SelfAttention.q.scales": "0.safetensors",
350
+ "t5_blocks.13.attention.SelfAttention.q.biases": "0.safetensors",
351
+ "t5_blocks.13.attention.SelfAttention.k.weight": "0.safetensors",
352
+ "t5_blocks.13.attention.SelfAttention.k.scales": "0.safetensors",
353
+ "t5_blocks.13.attention.SelfAttention.k.biases": "0.safetensors",
354
+ "t5_blocks.13.attention.SelfAttention.v.weight": "0.safetensors",
355
+ "t5_blocks.13.attention.SelfAttention.v.scales": "0.safetensors",
356
+ "t5_blocks.13.attention.SelfAttention.v.biases": "0.safetensors",
357
+ "t5_blocks.13.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
358
+ "t5_blocks.13.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
359
+ "t5_blocks.13.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
360
+ "t5_blocks.13.attention.SelfAttention.o.weight": "0.safetensors",
361
+ "t5_blocks.13.attention.SelfAttention.o.scales": "0.safetensors",
362
+ "t5_blocks.13.attention.SelfAttention.o.biases": "0.safetensors",
363
+ "t5_blocks.13.attention.layer_norm.weight": "0.safetensors",
364
+ "t5_blocks.13.ff.layer_norm.weight": "0.safetensors",
365
+ "t5_blocks.13.ff.DenseReluDense.wi_0.weight": "0.safetensors",
366
+ "t5_blocks.13.ff.DenseReluDense.wi_0.scales": "0.safetensors",
367
+ "t5_blocks.13.ff.DenseReluDense.wi_0.biases": "0.safetensors",
368
+ "t5_blocks.13.ff.DenseReluDense.wi_1.weight": "0.safetensors",
369
+ "t5_blocks.13.ff.DenseReluDense.wi_1.scales": "0.safetensors",
370
+ "t5_blocks.13.ff.DenseReluDense.wi_1.biases": "0.safetensors",
371
+ "t5_blocks.13.ff.DenseReluDense.wo.weight": "0.safetensors",
372
+ "t5_blocks.13.ff.DenseReluDense.wo.scales": "0.safetensors",
373
+ "t5_blocks.13.ff.DenseReluDense.wo.biases": "0.safetensors",
374
+ "t5_blocks.14.attention.SelfAttention.q.weight": "0.safetensors",
375
+ "t5_blocks.14.attention.SelfAttention.q.scales": "0.safetensors",
376
+ "t5_blocks.14.attention.SelfAttention.q.biases": "0.safetensors",
377
+ "t5_blocks.14.attention.SelfAttention.k.weight": "0.safetensors",
378
+ "t5_blocks.14.attention.SelfAttention.k.scales": "0.safetensors",
379
+ "t5_blocks.14.attention.SelfAttention.k.biases": "0.safetensors",
380
+ "t5_blocks.14.attention.SelfAttention.v.weight": "0.safetensors",
381
+ "t5_blocks.14.attention.SelfAttention.v.scales": "0.safetensors",
382
+ "t5_blocks.14.attention.SelfAttention.v.biases": "0.safetensors",
383
+ "t5_blocks.14.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
384
+ "t5_blocks.14.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
385
+ "t5_blocks.14.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
386
+ "t5_blocks.14.attention.SelfAttention.o.weight": "0.safetensors",
387
+ "t5_blocks.14.attention.SelfAttention.o.scales": "0.safetensors",
388
+ "t5_blocks.14.attention.SelfAttention.o.biases": "0.safetensors",
389
+ "t5_blocks.14.attention.layer_norm.weight": "0.safetensors",
390
+ "t5_blocks.14.ff.layer_norm.weight": "0.safetensors",
391
+ "t5_blocks.14.ff.DenseReluDense.wi_0.weight": "0.safetensors",
392
+ "t5_blocks.14.ff.DenseReluDense.wi_0.scales": "0.safetensors",
393
+ "t5_blocks.14.ff.DenseReluDense.wi_0.biases": "0.safetensors",
394
+ "t5_blocks.14.ff.DenseReluDense.wi_1.weight": "0.safetensors",
395
+ "t5_blocks.14.ff.DenseReluDense.wi_1.scales": "0.safetensors",
396
+ "t5_blocks.14.ff.DenseReluDense.wi_1.biases": "0.safetensors",
397
+ "t5_blocks.14.ff.DenseReluDense.wo.weight": "0.safetensors",
398
+ "t5_blocks.14.ff.DenseReluDense.wo.scales": "0.safetensors",
399
+ "t5_blocks.14.ff.DenseReluDense.wo.biases": "0.safetensors",
400
+ "t5_blocks.15.attention.SelfAttention.q.weight": "0.safetensors",
401
+ "t5_blocks.15.attention.SelfAttention.q.scales": "0.safetensors",
402
+ "t5_blocks.15.attention.SelfAttention.q.biases": "0.safetensors",
403
+ "t5_blocks.15.attention.SelfAttention.k.weight": "0.safetensors",
404
+ "t5_blocks.15.attention.SelfAttention.k.scales": "0.safetensors",
405
+ "t5_blocks.15.attention.SelfAttention.k.biases": "0.safetensors",
406
+ "t5_blocks.15.attention.SelfAttention.v.weight": "0.safetensors",
407
+ "t5_blocks.15.attention.SelfAttention.v.scales": "0.safetensors",
408
+ "t5_blocks.15.attention.SelfAttention.v.biases": "0.safetensors",
409
+ "t5_blocks.15.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
410
+ "t5_blocks.15.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
411
+ "t5_blocks.15.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
412
+ "t5_blocks.15.attention.SelfAttention.o.weight": "0.safetensors",
413
+ "t5_blocks.15.attention.SelfAttention.o.scales": "0.safetensors",
414
+ "t5_blocks.15.attention.SelfAttention.o.biases": "0.safetensors",
415
+ "t5_blocks.15.attention.layer_norm.weight": "0.safetensors",
416
+ "t5_blocks.15.ff.layer_norm.weight": "0.safetensors",
417
+ "t5_blocks.15.ff.DenseReluDense.wi_0.weight": "0.safetensors",
418
+ "t5_blocks.15.ff.DenseReluDense.wi_0.scales": "0.safetensors",
419
+ "t5_blocks.15.ff.DenseReluDense.wi_0.biases": "0.safetensors",
420
+ "t5_blocks.15.ff.DenseReluDense.wi_1.weight": "0.safetensors",
421
+ "t5_blocks.15.ff.DenseReluDense.wi_1.scales": "0.safetensors",
422
+ "t5_blocks.15.ff.DenseReluDense.wi_1.biases": "0.safetensors",
423
+ "t5_blocks.15.ff.DenseReluDense.wo.weight": "0.safetensors",
424
+ "t5_blocks.15.ff.DenseReluDense.wo.scales": "0.safetensors",
425
+ "t5_blocks.15.ff.DenseReluDense.wo.biases": "0.safetensors",
426
+ "t5_blocks.16.attention.SelfAttention.q.weight": "0.safetensors",
427
+ "t5_blocks.16.attention.SelfAttention.q.scales": "0.safetensors",
428
+ "t5_blocks.16.attention.SelfAttention.q.biases": "0.safetensors",
429
+ "t5_blocks.16.attention.SelfAttention.k.weight": "0.safetensors",
430
+ "t5_blocks.16.attention.SelfAttention.k.scales": "0.safetensors",
431
+ "t5_blocks.16.attention.SelfAttention.k.biases": "0.safetensors",
432
+ "t5_blocks.16.attention.SelfAttention.v.weight": "0.safetensors",
433
+ "t5_blocks.16.attention.SelfAttention.v.scales": "0.safetensors",
434
+ "t5_blocks.16.attention.SelfAttention.v.biases": "0.safetensors",
435
+ "t5_blocks.16.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
436
+ "t5_blocks.16.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
437
+ "t5_blocks.16.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
438
+ "t5_blocks.16.attention.SelfAttention.o.weight": "0.safetensors",
439
+ "t5_blocks.16.attention.SelfAttention.o.scales": "0.safetensors",
440
+ "t5_blocks.16.attention.SelfAttention.o.biases": "0.safetensors",
441
+ "t5_blocks.16.attention.layer_norm.weight": "0.safetensors",
442
+ "t5_blocks.16.ff.layer_norm.weight": "0.safetensors",
443
+ "t5_blocks.16.ff.DenseReluDense.wi_0.weight": "0.safetensors",
444
+ "t5_blocks.16.ff.DenseReluDense.wi_0.scales": "0.safetensors",
445
+ "t5_blocks.16.ff.DenseReluDense.wi_0.biases": "0.safetensors",
446
+ "t5_blocks.16.ff.DenseReluDense.wi_1.weight": "0.safetensors",
447
+ "t5_blocks.16.ff.DenseReluDense.wi_1.scales": "0.safetensors",
448
+ "t5_blocks.16.ff.DenseReluDense.wi_1.biases": "0.safetensors",
449
+ "t5_blocks.16.ff.DenseReluDense.wo.weight": "0.safetensors",
450
+ "t5_blocks.16.ff.DenseReluDense.wo.scales": "0.safetensors",
451
+ "t5_blocks.16.ff.DenseReluDense.wo.biases": "0.safetensors",
452
+ "t5_blocks.17.attention.SelfAttention.q.weight": "0.safetensors",
453
+ "t5_blocks.17.attention.SelfAttention.q.scales": "0.safetensors",
454
+ "t5_blocks.17.attention.SelfAttention.q.biases": "0.safetensors",
455
+ "t5_blocks.17.attention.SelfAttention.k.weight": "0.safetensors",
456
+ "t5_blocks.17.attention.SelfAttention.k.scales": "0.safetensors",
457
+ "t5_blocks.17.attention.SelfAttention.k.biases": "0.safetensors",
458
+ "t5_blocks.17.attention.SelfAttention.v.weight": "0.safetensors",
459
+ "t5_blocks.17.attention.SelfAttention.v.scales": "0.safetensors",
460
+ "t5_blocks.17.attention.SelfAttention.v.biases": "0.safetensors",
461
+ "t5_blocks.17.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
462
+ "t5_blocks.17.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
463
+ "t5_blocks.17.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
464
+ "t5_blocks.17.attention.SelfAttention.o.weight": "0.safetensors",
465
+ "t5_blocks.17.attention.SelfAttention.o.scales": "0.safetensors",
466
+ "t5_blocks.17.attention.SelfAttention.o.biases": "0.safetensors",
467
+ "t5_blocks.17.attention.layer_norm.weight": "0.safetensors",
468
+ "t5_blocks.17.ff.layer_norm.weight": "0.safetensors",
469
+ "t5_blocks.17.ff.DenseReluDense.wi_0.weight": "0.safetensors",
470
+ "t5_blocks.17.ff.DenseReluDense.wi_0.scales": "0.safetensors",
471
+ "t5_blocks.17.ff.DenseReluDense.wi_0.biases": "0.safetensors",
472
+ "t5_blocks.17.ff.DenseReluDense.wi_1.weight": "0.safetensors",
473
+ "t5_blocks.17.ff.DenseReluDense.wi_1.scales": "0.safetensors",
474
+ "t5_blocks.17.ff.DenseReluDense.wi_1.biases": "0.safetensors",
475
+ "t5_blocks.17.ff.DenseReluDense.wo.weight": "0.safetensors",
476
+ "t5_blocks.17.ff.DenseReluDense.wo.scales": "0.safetensors",
477
+ "t5_blocks.17.ff.DenseReluDense.wo.biases": "0.safetensors",
478
+ "t5_blocks.18.attention.SelfAttention.q.weight": "0.safetensors",
479
+ "t5_blocks.18.attention.SelfAttention.q.scales": "0.safetensors",
480
+ "t5_blocks.18.attention.SelfAttention.q.biases": "0.safetensors",
481
+ "t5_blocks.18.attention.SelfAttention.k.weight": "0.safetensors",
482
+ "t5_blocks.18.attention.SelfAttention.k.scales": "0.safetensors",
483
+ "t5_blocks.18.attention.SelfAttention.k.biases": "0.safetensors",
484
+ "t5_blocks.18.attention.SelfAttention.v.weight": "0.safetensors",
485
+ "t5_blocks.18.attention.SelfAttention.v.scales": "0.safetensors",
486
+ "t5_blocks.18.attention.SelfAttention.v.biases": "0.safetensors",
487
+ "t5_blocks.18.attention.SelfAttention.relative_attention_bias.weight": "0.safetensors",
488
+ "t5_blocks.18.attention.SelfAttention.relative_attention_bias.scales": "0.safetensors",
489
+ "t5_blocks.18.attention.SelfAttention.relative_attention_bias.biases": "0.safetensors",
490
+ "t5_blocks.18.attention.SelfAttention.o.weight": "0.safetensors",
491
+ "t5_blocks.18.attention.SelfAttention.o.scales": "0.safetensors",
492
+ "t5_blocks.18.attention.SelfAttention.o.biases": "0.safetensors",
493
+ "t5_blocks.18.attention.layer_norm.weight": "0.safetensors",
494
+ "t5_blocks.18.ff.layer_norm.weight": "0.safetensors",
495
+ "t5_blocks.18.ff.DenseReluDense.wi_0.weight": "0.safetensors",
496
+ "t5_blocks.18.ff.DenseReluDense.wi_0.scales": "0.safetensors",
497
+ "t5_blocks.18.ff.DenseReluDense.wi_0.biases": "0.safetensors",
498
+ "t5_blocks.18.ff.DenseReluDense.wi_1.weight": "0.safetensors",
499
+ "t5_blocks.18.ff.DenseReluDense.wi_1.scales": "0.safetensors",
500
+ "t5_blocks.18.ff.DenseReluDense.wi_1.biases": "0.safetensors",
501
+ "t5_blocks.18.ff.DenseReluDense.wo.weight": "0.safetensors",
502
+ "t5_blocks.18.ff.DenseReluDense.wo.scales": "0.safetensors",
503
+ "t5_blocks.18.ff.DenseReluDense.wo.biases": "0.safetensors",
504
+ "t5_blocks.19.attention.SelfAttention.q.weight": "0.safetensors",
505
+ "t5_blocks.19.attention.SelfAttention.q.scales": "0.safetensors",
506
+ "t5_blocks.19.attention.SelfAttention.q.biases": "0.safetensors",
507
+ "t5_blocks.19.attention.SelfAttention.k.weight": "1.safetensors",
508
+ "t5_blocks.19.attention.SelfAttention.k.scales": "1.safetensors",
509
+ "t5_blocks.19.attention.SelfAttention.k.biases": "1.safetensors",
510
+ "t5_blocks.19.attention.SelfAttention.v.weight": "1.safetensors",
511
+ "t5_blocks.19.attention.SelfAttention.v.scales": "1.safetensors",
512
+ "t5_blocks.19.attention.SelfAttention.v.biases": "1.safetensors",
513
+ "t5_blocks.19.attention.SelfAttention.relative_attention_bias.weight": "1.safetensors",
514
+ "t5_blocks.19.attention.SelfAttention.relative_attention_bias.scales": "1.safetensors",
515
+ "t5_blocks.19.attention.SelfAttention.relative_attention_bias.biases": "1.safetensors",
516
+ "t5_blocks.19.attention.SelfAttention.o.weight": "1.safetensors",
517
+ "t5_blocks.19.attention.SelfAttention.o.scales": "1.safetensors",
518
+ "t5_blocks.19.attention.SelfAttention.o.biases": "1.safetensors",
519
+ "t5_blocks.19.attention.layer_norm.weight": "1.safetensors",
520
+ "t5_blocks.19.ff.layer_norm.weight": "1.safetensors",
521
+ "t5_blocks.19.ff.DenseReluDense.wi_0.weight": "1.safetensors",
522
+ "t5_blocks.19.ff.DenseReluDense.wi_0.scales": "1.safetensors",
523
+ "t5_blocks.19.ff.DenseReluDense.wi_0.biases": "1.safetensors",
524
+ "t5_blocks.19.ff.DenseReluDense.wi_1.weight": "1.safetensors",
525
+ "t5_blocks.19.ff.DenseReluDense.wi_1.scales": "1.safetensors",
526
+ "t5_blocks.19.ff.DenseReluDense.wi_1.biases": "1.safetensors",
527
+ "t5_blocks.19.ff.DenseReluDense.wo.weight": "1.safetensors",
528
+ "t5_blocks.19.ff.DenseReluDense.wo.scales": "1.safetensors",
529
+ "t5_blocks.19.ff.DenseReluDense.wo.biases": "1.safetensors",
530
+ "t5_blocks.20.attention.SelfAttention.q.weight": "1.safetensors",
531
+ "t5_blocks.20.attention.SelfAttention.q.scales": "1.safetensors",
532
+ "t5_blocks.20.attention.SelfAttention.q.biases": "1.safetensors",
533
+ "t5_blocks.20.attention.SelfAttention.k.weight": "1.safetensors",
534
+ "t5_blocks.20.attention.SelfAttention.k.scales": "1.safetensors",
535
+ "t5_blocks.20.attention.SelfAttention.k.biases": "1.safetensors",
536
+ "t5_blocks.20.attention.SelfAttention.v.weight": "1.safetensors",
537
+ "t5_blocks.20.attention.SelfAttention.v.scales": "1.safetensors",
538
+ "t5_blocks.20.attention.SelfAttention.v.biases": "1.safetensors",
539
+ "t5_blocks.20.attention.SelfAttention.relative_attention_bias.weight": "1.safetensors",
540
+ "t5_blocks.20.attention.SelfAttention.relative_attention_bias.scales": "1.safetensors",
541
+ "t5_blocks.20.attention.SelfAttention.relative_attention_bias.biases": "1.safetensors",
542
+ "t5_blocks.20.attention.SelfAttention.o.weight": "1.safetensors",
543
+ "t5_blocks.20.attention.SelfAttention.o.scales": "1.safetensors",
544
+ "t5_blocks.20.attention.SelfAttention.o.biases": "1.safetensors",
545
+ "t5_blocks.20.attention.layer_norm.weight": "1.safetensors",
546
+ "t5_blocks.20.ff.layer_norm.weight": "1.safetensors",
547
+ "t5_blocks.20.ff.DenseReluDense.wi_0.weight": "1.safetensors",
548
+ "t5_blocks.20.ff.DenseReluDense.wi_0.scales": "1.safetensors",
549
+ "t5_blocks.20.ff.DenseReluDense.wi_0.biases": "1.safetensors",
550
+ "t5_blocks.20.ff.DenseReluDense.wi_1.weight": "1.safetensors",
551
+ "t5_blocks.20.ff.DenseReluDense.wi_1.scales": "1.safetensors",
552
+ "t5_blocks.20.ff.DenseReluDense.wi_1.biases": "1.safetensors",
553
+ "t5_blocks.20.ff.DenseReluDense.wo.weight": "1.safetensors",
554
+ "t5_blocks.20.ff.DenseReluDense.wo.scales": "1.safetensors",
555
+ "t5_blocks.20.ff.DenseReluDense.wo.biases": "1.safetensors",
556
+ "t5_blocks.21.attention.SelfAttention.q.weight": "1.safetensors",
557
+ "t5_blocks.21.attention.SelfAttention.q.scales": "1.safetensors",
558
+ "t5_blocks.21.attention.SelfAttention.q.biases": "1.safetensors",
559
+ "t5_blocks.21.attention.SelfAttention.k.weight": "1.safetensors",
560
+ "t5_blocks.21.attention.SelfAttention.k.scales": "1.safetensors",
561
+ "t5_blocks.21.attention.SelfAttention.k.biases": "1.safetensors",
562
+ "t5_blocks.21.attention.SelfAttention.v.weight": "1.safetensors",
563
+ "t5_blocks.21.attention.SelfAttention.v.scales": "1.safetensors",
564
+ "t5_blocks.21.attention.SelfAttention.v.biases": "1.safetensors",
565
+ "t5_blocks.21.attention.SelfAttention.relative_attention_bias.weight": "1.safetensors",
566
+ "t5_blocks.21.attention.SelfAttention.relative_attention_bias.scales": "1.safetensors",
567
+ "t5_blocks.21.attention.SelfAttention.relative_attention_bias.biases": "1.safetensors",
568
+ "t5_blocks.21.attention.SelfAttention.o.weight": "1.safetensors",
569
+ "t5_blocks.21.attention.SelfAttention.o.scales": "1.safetensors",
570
+ "t5_blocks.21.attention.SelfAttention.o.biases": "1.safetensors",
571
+ "t5_blocks.21.attention.layer_norm.weight": "1.safetensors",
572
+ "t5_blocks.21.ff.layer_norm.weight": "1.safetensors",
573
+ "t5_blocks.21.ff.DenseReluDense.wi_0.weight": "1.safetensors",
574
+ "t5_blocks.21.ff.DenseReluDense.wi_0.scales": "1.safetensors",
575
+ "t5_blocks.21.ff.DenseReluDense.wi_0.biases": "1.safetensors",
576
+ "t5_blocks.21.ff.DenseReluDense.wi_1.weight": "1.safetensors",
577
+ "t5_blocks.21.ff.DenseReluDense.wi_1.scales": "1.safetensors",
578
+ "t5_blocks.21.ff.DenseReluDense.wi_1.biases": "1.safetensors",
579
+ "t5_blocks.21.ff.DenseReluDense.wo.weight": "1.safetensors",
580
+ "t5_blocks.21.ff.DenseReluDense.wo.scales": "1.safetensors",
581
+ "t5_blocks.21.ff.DenseReluDense.wo.biases": "1.safetensors",
582
+ "t5_blocks.22.attention.SelfAttention.q.weight": "1.safetensors",
583
+ "t5_blocks.22.attention.SelfAttention.q.scales": "1.safetensors",
584
+ "t5_blocks.22.attention.SelfAttention.q.biases": "1.safetensors",
585
+ "t5_blocks.22.attention.SelfAttention.k.weight": "1.safetensors",
586
+ "t5_blocks.22.attention.SelfAttention.k.scales": "1.safetensors",
587
+ "t5_blocks.22.attention.SelfAttention.k.biases": "1.safetensors",
588
+ "t5_blocks.22.attention.SelfAttention.v.weight": "1.safetensors",
589
+ "t5_blocks.22.attention.SelfAttention.v.scales": "1.safetensors",
590
+ "t5_blocks.22.attention.SelfAttention.v.biases": "1.safetensors",
591
+ "t5_blocks.22.attention.SelfAttention.relative_attention_bias.weight": "1.safetensors",
592
+ "t5_blocks.22.attention.SelfAttention.relative_attention_bias.scales": "1.safetensors",
593
+ "t5_blocks.22.attention.SelfAttention.relative_attention_bias.biases": "1.safetensors",
594
+ "t5_blocks.22.attention.SelfAttention.o.weight": "1.safetensors",
595
+ "t5_blocks.22.attention.SelfAttention.o.scales": "1.safetensors",
596
+ "t5_blocks.22.attention.SelfAttention.o.biases": "1.safetensors",
597
+ "t5_blocks.22.attention.layer_norm.weight": "1.safetensors",
598
+ "t5_blocks.22.ff.layer_norm.weight": "1.safetensors",
599
+ "t5_blocks.22.ff.DenseReluDense.wi_0.weight": "1.safetensors",
600
+ "t5_blocks.22.ff.DenseReluDense.wi_0.scales": "1.safetensors",
601
+ "t5_blocks.22.ff.DenseReluDense.wi_0.biases": "1.safetensors",
602
+ "t5_blocks.22.ff.DenseReluDense.wi_1.weight": "1.safetensors",
603
+ "t5_blocks.22.ff.DenseReluDense.wi_1.scales": "1.safetensors",
604
+ "t5_blocks.22.ff.DenseReluDense.wi_1.biases": "1.safetensors",
605
+ "t5_blocks.22.ff.DenseReluDense.wo.weight": "1.safetensors",
606
+ "t5_blocks.22.ff.DenseReluDense.wo.scales": "1.safetensors",
607
+ "t5_blocks.22.ff.DenseReluDense.wo.biases": "1.safetensors",
608
+ "t5_blocks.23.attention.SelfAttention.q.weight": "1.safetensors",
609
+ "t5_blocks.23.attention.SelfAttention.q.scales": "1.safetensors",
610
+ "t5_blocks.23.attention.SelfAttention.q.biases": "1.safetensors",
611
+ "t5_blocks.23.attention.SelfAttention.k.weight": "1.safetensors",
612
+ "t5_blocks.23.attention.SelfAttention.k.scales": "1.safetensors",
613
+ "t5_blocks.23.attention.SelfAttention.k.biases": "1.safetensors",
614
+ "t5_blocks.23.attention.SelfAttention.v.weight": "1.safetensors",
615
+ "t5_blocks.23.attention.SelfAttention.v.scales": "1.safetensors",
616
+ "t5_blocks.23.attention.SelfAttention.v.biases": "1.safetensors",
617
+ "t5_blocks.23.attention.SelfAttention.relative_attention_bias.weight": "1.safetensors",
618
+ "t5_blocks.23.attention.SelfAttention.relative_attention_bias.scales": "1.safetensors",
619
+ "t5_blocks.23.attention.SelfAttention.relative_attention_bias.biases": "1.safetensors",
620
+ "t5_blocks.23.attention.SelfAttention.o.weight": "1.safetensors",
621
+ "t5_blocks.23.attention.SelfAttention.o.scales": "1.safetensors",
622
+ "t5_blocks.23.attention.SelfAttention.o.biases": "1.safetensors",
623
+ "t5_blocks.23.attention.layer_norm.weight": "1.safetensors",
624
+ "t5_blocks.23.ff.layer_norm.weight": "1.safetensors",
625
+ "t5_blocks.23.ff.DenseReluDense.wi_0.weight": "1.safetensors",
626
+ "t5_blocks.23.ff.DenseReluDense.wi_0.scales": "1.safetensors",
627
+ "t5_blocks.23.ff.DenseReluDense.wi_0.biases": "1.safetensors",
628
+ "t5_blocks.23.ff.DenseReluDense.wi_1.weight": "1.safetensors",
629
+ "t5_blocks.23.ff.DenseReluDense.wi_1.scales": "1.safetensors",
630
+ "t5_blocks.23.ff.DenseReluDense.wi_1.biases": "1.safetensors",
631
+ "t5_blocks.23.ff.DenseReluDense.wo.weight": "1.safetensors",
632
+ "t5_blocks.23.ff.DenseReluDense.wo.scales": "1.safetensors",
633
+ "t5_blocks.23.ff.DenseReluDense.wo.biases": "1.safetensors",
634
+ "final_layer_norm.weight": "1.safetensors"
635
+ }
636
+ }
tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|startoftext|>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "do_lower_case": true,
7
+ "eos_token": "<|endoftext|>",
8
+ "errors": "replace",
9
+ "is_local": true,
10
+ "model_max_length": 77,
11
+ "pad_token": "<|endoftext|>",
12
+ "tokenizer_class": "CLIPTokenizer",
13
+ "unk_token": "<|endoftext|>"
14
+ }
tokenizer_2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/tokenizer_config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "</s>",
6
+ "extra_ids": 100,
7
+ "extra_special_tokens": [
8
+ "<extra_id_0>",
9
+ "<extra_id_1>",
10
+ "<extra_id_2>",
11
+ "<extra_id_3>",
12
+ "<extra_id_4>",
13
+ "<extra_id_5>",
14
+ "<extra_id_6>",
15
+ "<extra_id_7>",
16
+ "<extra_id_8>",
17
+ "<extra_id_9>",
18
+ "<extra_id_10>",
19
+ "<extra_id_11>",
20
+ "<extra_id_12>",
21
+ "<extra_id_13>",
22
+ "<extra_id_14>",
23
+ "<extra_id_15>",
24
+ "<extra_id_16>",
25
+ "<extra_id_17>",
26
+ "<extra_id_18>",
27
+ "<extra_id_19>",
28
+ "<extra_id_20>",
29
+ "<extra_id_21>",
30
+ "<extra_id_22>",
31
+ "<extra_id_23>",
32
+ "<extra_id_24>",
33
+ "<extra_id_25>",
34
+ "<extra_id_26>",
35
+ "<extra_id_27>",
36
+ "<extra_id_28>",
37
+ "<extra_id_29>",
38
+ "<extra_id_30>",
39
+ "<extra_id_31>",
40
+ "<extra_id_32>",
41
+ "<extra_id_33>",
42
+ "<extra_id_34>",
43
+ "<extra_id_35>",
44
+ "<extra_id_36>",
45
+ "<extra_id_37>",
46
+ "<extra_id_38>",
47
+ "<extra_id_39>",
48
+ "<extra_id_40>",
49
+ "<extra_id_41>",
50
+ "<extra_id_42>",
51
+ "<extra_id_43>",
52
+ "<extra_id_44>",
53
+ "<extra_id_45>",
54
+ "<extra_id_46>",
55
+ "<extra_id_47>",
56
+ "<extra_id_48>",
57
+ "<extra_id_49>",
58
+ "<extra_id_50>",
59
+ "<extra_id_51>",
60
+ "<extra_id_52>",
61
+ "<extra_id_53>",
62
+ "<extra_id_54>",
63
+ "<extra_id_55>",
64
+ "<extra_id_56>",
65
+ "<extra_id_57>",
66
+ "<extra_id_58>",
67
+ "<extra_id_59>",
68
+ "<extra_id_60>",
69
+ "<extra_id_61>",
70
+ "<extra_id_62>",
71
+ "<extra_id_63>",
72
+ "<extra_id_64>",
73
+ "<extra_id_65>",
74
+ "<extra_id_66>",
75
+ "<extra_id_67>",
76
+ "<extra_id_68>",
77
+ "<extra_id_69>",
78
+ "<extra_id_70>",
79
+ "<extra_id_71>",
80
+ "<extra_id_72>",
81
+ "<extra_id_73>",
82
+ "<extra_id_74>",
83
+ "<extra_id_75>",
84
+ "<extra_id_76>",
85
+ "<extra_id_77>",
86
+ "<extra_id_78>",
87
+ "<extra_id_79>",
88
+ "<extra_id_80>",
89
+ "<extra_id_81>",
90
+ "<extra_id_82>",
91
+ "<extra_id_83>",
92
+ "<extra_id_84>",
93
+ "<extra_id_85>",
94
+ "<extra_id_86>",
95
+ "<extra_id_87>",
96
+ "<extra_id_88>",
97
+ "<extra_id_89>",
98
+ "<extra_id_90>",
99
+ "<extra_id_91>",
100
+ "<extra_id_92>",
101
+ "<extra_id_93>",
102
+ "<extra_id_94>",
103
+ "<extra_id_95>",
104
+ "<extra_id_96>",
105
+ "<extra_id_97>",
106
+ "<extra_id_98>",
107
+ "<extra_id_99>"
108
+ ],
109
+ "is_local": true,
110
+ "legacy": true,
111
+ "model_max_length": 512,
112
+ "pad_token": "<pad>",
113
+ "sp_model_kwargs": {},
114
+ "tokenizer_class": "T5Tokenizer",
115
+ "unk_token": "<unk>"
116
+ }
transformer/0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af5a10a95a6958377629a2bfbd0364f9899cdb5efc0d3f3b3c4610bf309b63d
3
+ size 2129626741
transformer/1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b82a2894b5a5de32821a99d2e3def3837fa67de967f0561b74198bc8e566058d
3
+ size 2141393618
transformer/2.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f216fe21b0238ebf47c4006ce9894a92f07ab06d2bc8f310c414b12abab34d
3
+ size 2130572514
transformer/3.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:774a90d016ebca6643572da712c2f36221f244624920d4fa25b4aaf207fbaafa
3
+ size 297640239
transformer/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
vae/0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69fe087c512933d1755e759caed00459050763e9a03e5deb8059b96e19880cc1
3
+ size 164654152
vae/model.safetensors.index.json ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "quantization_level": "4",
4
+ "mflux_version": "0.3.0"
5
+ },
6
+ "weight_map": {
7
+ "decoder.conv_in.conv2d.weight": "0.safetensors",
8
+ "decoder.conv_in.conv2d.bias": "0.safetensors",
9
+ "decoder.mid_block.attentions.0.group_norm.bias": "0.safetensors",
10
+ "decoder.mid_block.attentions.0.group_norm.weight": "0.safetensors",
11
+ "decoder.mid_block.attentions.0.to_q.weight": "0.safetensors",
12
+ "decoder.mid_block.attentions.0.to_q.scales": "0.safetensors",
13
+ "decoder.mid_block.attentions.0.to_q.biases": "0.safetensors",
14
+ "decoder.mid_block.attentions.0.to_q.bias": "0.safetensors",
15
+ "decoder.mid_block.attentions.0.to_k.weight": "0.safetensors",
16
+ "decoder.mid_block.attentions.0.to_k.scales": "0.safetensors",
17
+ "decoder.mid_block.attentions.0.to_k.biases": "0.safetensors",
18
+ "decoder.mid_block.attentions.0.to_k.bias": "0.safetensors",
19
+ "decoder.mid_block.attentions.0.to_v.weight": "0.safetensors",
20
+ "decoder.mid_block.attentions.0.to_v.scales": "0.safetensors",
21
+ "decoder.mid_block.attentions.0.to_v.biases": "0.safetensors",
22
+ "decoder.mid_block.attentions.0.to_v.bias": "0.safetensors",
23
+ "decoder.mid_block.attentions.0.to_out.0.weight": "0.safetensors",
24
+ "decoder.mid_block.attentions.0.to_out.0.scales": "0.safetensors",
25
+ "decoder.mid_block.attentions.0.to_out.0.biases": "0.safetensors",
26
+ "decoder.mid_block.attentions.0.to_out.0.bias": "0.safetensors",
27
+ "decoder.mid_block.resnets.0.norm1.bias": "0.safetensors",
28
+ "decoder.mid_block.resnets.0.norm1.weight": "0.safetensors",
29
+ "decoder.mid_block.resnets.0.norm2.bias": "0.safetensors",
30
+ "decoder.mid_block.resnets.0.norm2.weight": "0.safetensors",
31
+ "decoder.mid_block.resnets.0.conv1.weight": "0.safetensors",
32
+ "decoder.mid_block.resnets.0.conv1.bias": "0.safetensors",
33
+ "decoder.mid_block.resnets.0.conv2.weight": "0.safetensors",
34
+ "decoder.mid_block.resnets.0.conv2.bias": "0.safetensors",
35
+ "decoder.mid_block.resnets.1.norm1.bias": "0.safetensors",
36
+ "decoder.mid_block.resnets.1.norm1.weight": "0.safetensors",
37
+ "decoder.mid_block.resnets.1.norm2.bias": "0.safetensors",
38
+ "decoder.mid_block.resnets.1.norm2.weight": "0.safetensors",
39
+ "decoder.mid_block.resnets.1.conv1.weight": "0.safetensors",
40
+ "decoder.mid_block.resnets.1.conv1.bias": "0.safetensors",
41
+ "decoder.mid_block.resnets.1.conv2.weight": "0.safetensors",
42
+ "decoder.mid_block.resnets.1.conv2.bias": "0.safetensors",
43
+ "decoder.up_blocks.0.resnets.0.norm1.bias": "0.safetensors",
44
+ "decoder.up_blocks.0.resnets.0.norm1.weight": "0.safetensors",
45
+ "decoder.up_blocks.0.resnets.0.norm2.bias": "0.safetensors",
46
+ "decoder.up_blocks.0.resnets.0.norm2.weight": "0.safetensors",
47
+ "decoder.up_blocks.0.resnets.0.conv1.weight": "0.safetensors",
48
+ "decoder.up_blocks.0.resnets.0.conv1.bias": "0.safetensors",
49
+ "decoder.up_blocks.0.resnets.0.conv2.weight": "0.safetensors",
50
+ "decoder.up_blocks.0.resnets.0.conv2.bias": "0.safetensors",
51
+ "decoder.up_blocks.0.resnets.1.norm1.bias": "0.safetensors",
52
+ "decoder.up_blocks.0.resnets.1.norm1.weight": "0.safetensors",
53
+ "decoder.up_blocks.0.resnets.1.norm2.bias": "0.safetensors",
54
+ "decoder.up_blocks.0.resnets.1.norm2.weight": "0.safetensors",
55
+ "decoder.up_blocks.0.resnets.1.conv1.weight": "0.safetensors",
56
+ "decoder.up_blocks.0.resnets.1.conv1.bias": "0.safetensors",
57
+ "decoder.up_blocks.0.resnets.1.conv2.weight": "0.safetensors",
58
+ "decoder.up_blocks.0.resnets.1.conv2.bias": "0.safetensors",
59
+ "decoder.up_blocks.0.resnets.2.norm1.bias": "0.safetensors",
60
+ "decoder.up_blocks.0.resnets.2.norm1.weight": "0.safetensors",
61
+ "decoder.up_blocks.0.resnets.2.norm2.bias": "0.safetensors",
62
+ "decoder.up_blocks.0.resnets.2.norm2.weight": "0.safetensors",
63
+ "decoder.up_blocks.0.resnets.2.conv1.weight": "0.safetensors",
64
+ "decoder.up_blocks.0.resnets.2.conv1.bias": "0.safetensors",
65
+ "decoder.up_blocks.0.resnets.2.conv2.weight": "0.safetensors",
66
+ "decoder.up_blocks.0.resnets.2.conv2.bias": "0.safetensors",
67
+ "decoder.up_blocks.0.upsamplers.0.conv.weight": "0.safetensors",
68
+ "decoder.up_blocks.0.upsamplers.0.conv.bias": "0.safetensors",
69
+ "decoder.up_blocks.1.resnets.0.norm1.bias": "0.safetensors",
70
+ "decoder.up_blocks.1.resnets.0.norm1.weight": "0.safetensors",
71
+ "decoder.up_blocks.1.resnets.0.norm2.bias": "0.safetensors",
72
+ "decoder.up_blocks.1.resnets.0.norm2.weight": "0.safetensors",
73
+ "decoder.up_blocks.1.resnets.0.conv1.weight": "0.safetensors",
74
+ "decoder.up_blocks.1.resnets.0.conv1.bias": "0.safetensors",
75
+ "decoder.up_blocks.1.resnets.0.conv2.weight": "0.safetensors",
76
+ "decoder.up_blocks.1.resnets.0.conv2.bias": "0.safetensors",
77
+ "decoder.up_blocks.1.resnets.1.norm1.bias": "0.safetensors",
78
+ "decoder.up_blocks.1.resnets.1.norm1.weight": "0.safetensors",
79
+ "decoder.up_blocks.1.resnets.1.norm2.bias": "0.safetensors",
80
+ "decoder.up_blocks.1.resnets.1.norm2.weight": "0.safetensors",
81
+ "decoder.up_blocks.1.resnets.1.conv1.weight": "0.safetensors",
82
+ "decoder.up_blocks.1.resnets.1.conv1.bias": "0.safetensors",
83
+ "decoder.up_blocks.1.resnets.1.conv2.weight": "0.safetensors",
84
+ "decoder.up_blocks.1.resnets.1.conv2.bias": "0.safetensors",
85
+ "decoder.up_blocks.1.resnets.2.norm1.bias": "0.safetensors",
86
+ "decoder.up_blocks.1.resnets.2.norm1.weight": "0.safetensors",
87
+ "decoder.up_blocks.1.resnets.2.norm2.bias": "0.safetensors",
88
+ "decoder.up_blocks.1.resnets.2.norm2.weight": "0.safetensors",
89
+ "decoder.up_blocks.1.resnets.2.conv1.weight": "0.safetensors",
90
+ "decoder.up_blocks.1.resnets.2.conv1.bias": "0.safetensors",
91
+ "decoder.up_blocks.1.resnets.2.conv2.weight": "0.safetensors",
92
+ "decoder.up_blocks.1.resnets.2.conv2.bias": "0.safetensors",
93
+ "decoder.up_blocks.1.upsamplers.0.conv.weight": "0.safetensors",
94
+ "decoder.up_blocks.1.upsamplers.0.conv.bias": "0.safetensors",
95
+ "decoder.up_blocks.2.resnets.0.norm1.bias": "0.safetensors",
96
+ "decoder.up_blocks.2.resnets.0.norm1.weight": "0.safetensors",
97
+ "decoder.up_blocks.2.resnets.0.norm2.bias": "0.safetensors",
98
+ "decoder.up_blocks.2.resnets.0.norm2.weight": "0.safetensors",
99
+ "decoder.up_blocks.2.resnets.0.conv1.weight": "0.safetensors",
100
+ "decoder.up_blocks.2.resnets.0.conv1.bias": "0.safetensors",
101
+ "decoder.up_blocks.2.resnets.0.conv2.weight": "0.safetensors",
102
+ "decoder.up_blocks.2.resnets.0.conv2.bias": "0.safetensors",
103
+ "decoder.up_blocks.2.resnets.0.conv_shortcut.weight": "0.safetensors",
104
+ "decoder.up_blocks.2.resnets.0.conv_shortcut.bias": "0.safetensors",
105
+ "decoder.up_blocks.2.resnets.1.norm1.bias": "0.safetensors",
106
+ "decoder.up_blocks.2.resnets.1.norm1.weight": "0.safetensors",
107
+ "decoder.up_blocks.2.resnets.1.norm2.bias": "0.safetensors",
108
+ "decoder.up_blocks.2.resnets.1.norm2.weight": "0.safetensors",
109
+ "decoder.up_blocks.2.resnets.1.conv1.weight": "0.safetensors",
110
+ "decoder.up_blocks.2.resnets.1.conv1.bias": "0.safetensors",
111
+ "decoder.up_blocks.2.resnets.1.conv2.weight": "0.safetensors",
112
+ "decoder.up_blocks.2.resnets.1.conv2.bias": "0.safetensors",
113
+ "decoder.up_blocks.2.resnets.2.norm1.bias": "0.safetensors",
114
+ "decoder.up_blocks.2.resnets.2.norm1.weight": "0.safetensors",
115
+ "decoder.up_blocks.2.resnets.2.norm2.bias": "0.safetensors",
116
+ "decoder.up_blocks.2.resnets.2.norm2.weight": "0.safetensors",
117
+ "decoder.up_blocks.2.resnets.2.conv1.weight": "0.safetensors",
118
+ "decoder.up_blocks.2.resnets.2.conv1.bias": "0.safetensors",
119
+ "decoder.up_blocks.2.resnets.2.conv2.weight": "0.safetensors",
120
+ "decoder.up_blocks.2.resnets.2.conv2.bias": "0.safetensors",
121
+ "decoder.up_blocks.2.upsamplers.0.conv.weight": "0.safetensors",
122
+ "decoder.up_blocks.2.upsamplers.0.conv.bias": "0.safetensors",
123
+ "decoder.up_blocks.3.resnets.0.norm1.bias": "0.safetensors",
124
+ "decoder.up_blocks.3.resnets.0.norm1.weight": "0.safetensors",
125
+ "decoder.up_blocks.3.resnets.0.norm2.bias": "0.safetensors",
126
+ "decoder.up_blocks.3.resnets.0.norm2.weight": "0.safetensors",
127
+ "decoder.up_blocks.3.resnets.0.conv1.weight": "0.safetensors",
128
+ "decoder.up_blocks.3.resnets.0.conv1.bias": "0.safetensors",
129
+ "decoder.up_blocks.3.resnets.0.conv2.weight": "0.safetensors",
130
+ "decoder.up_blocks.3.resnets.0.conv2.bias": "0.safetensors",
131
+ "decoder.up_blocks.3.resnets.0.conv_shortcut.weight": "0.safetensors",
132
+ "decoder.up_blocks.3.resnets.0.conv_shortcut.bias": "0.safetensors",
133
+ "decoder.up_blocks.3.resnets.1.norm1.bias": "0.safetensors",
134
+ "decoder.up_blocks.3.resnets.1.norm1.weight": "0.safetensors",
135
+ "decoder.up_blocks.3.resnets.1.norm2.bias": "0.safetensors",
136
+ "decoder.up_blocks.3.resnets.1.norm2.weight": "0.safetensors",
137
+ "decoder.up_blocks.3.resnets.1.conv1.weight": "0.safetensors",
138
+ "decoder.up_blocks.3.resnets.1.conv1.bias": "0.safetensors",
139
+ "decoder.up_blocks.3.resnets.1.conv2.weight": "0.safetensors",
140
+ "decoder.up_blocks.3.resnets.1.conv2.bias": "0.safetensors",
141
+ "decoder.up_blocks.3.resnets.2.norm1.bias": "0.safetensors",
142
+ "decoder.up_blocks.3.resnets.2.norm1.weight": "0.safetensors",
143
+ "decoder.up_blocks.3.resnets.2.norm2.bias": "0.safetensors",
144
+ "decoder.up_blocks.3.resnets.2.norm2.weight": "0.safetensors",
145
+ "decoder.up_blocks.3.resnets.2.conv1.weight": "0.safetensors",
146
+ "decoder.up_blocks.3.resnets.2.conv1.bias": "0.safetensors",
147
+ "decoder.up_blocks.3.resnets.2.conv2.weight": "0.safetensors",
148
+ "decoder.up_blocks.3.resnets.2.conv2.bias": "0.safetensors",
149
+ "decoder.conv_norm_out.norm.bias": "0.safetensors",
150
+ "decoder.conv_norm_out.norm.weight": "0.safetensors",
151
+ "decoder.conv_out.conv2d.weight": "0.safetensors",
152
+ "decoder.conv_out.conv2d.bias": "0.safetensors",
153
+ "encoder.conv_in.conv2d.weight": "0.safetensors",
154
+ "encoder.conv_in.conv2d.bias": "0.safetensors",
155
+ "encoder.mid_block.attentions.0.group_norm.bias": "0.safetensors",
156
+ "encoder.mid_block.attentions.0.group_norm.weight": "0.safetensors",
157
+ "encoder.mid_block.attentions.0.to_q.weight": "0.safetensors",
158
+ "encoder.mid_block.attentions.0.to_q.scales": "0.safetensors",
159
+ "encoder.mid_block.attentions.0.to_q.biases": "0.safetensors",
160
+ "encoder.mid_block.attentions.0.to_q.bias": "0.safetensors",
161
+ "encoder.mid_block.attentions.0.to_k.weight": "0.safetensors",
162
+ "encoder.mid_block.attentions.0.to_k.scales": "0.safetensors",
163
+ "encoder.mid_block.attentions.0.to_k.biases": "0.safetensors",
164
+ "encoder.mid_block.attentions.0.to_k.bias": "0.safetensors",
165
+ "encoder.mid_block.attentions.0.to_v.weight": "0.safetensors",
166
+ "encoder.mid_block.attentions.0.to_v.scales": "0.safetensors",
167
+ "encoder.mid_block.attentions.0.to_v.biases": "0.safetensors",
168
+ "encoder.mid_block.attentions.0.to_v.bias": "0.safetensors",
169
+ "encoder.mid_block.attentions.0.to_out.0.weight": "0.safetensors",
170
+ "encoder.mid_block.attentions.0.to_out.0.scales": "0.safetensors",
171
+ "encoder.mid_block.attentions.0.to_out.0.biases": "0.safetensors",
172
+ "encoder.mid_block.attentions.0.to_out.0.bias": "0.safetensors",
173
+ "encoder.mid_block.resnets.0.norm1.bias": "0.safetensors",
174
+ "encoder.mid_block.resnets.0.norm1.weight": "0.safetensors",
175
+ "encoder.mid_block.resnets.0.norm2.bias": "0.safetensors",
176
+ "encoder.mid_block.resnets.0.norm2.weight": "0.safetensors",
177
+ "encoder.mid_block.resnets.0.conv1.weight": "0.safetensors",
178
+ "encoder.mid_block.resnets.0.conv1.bias": "0.safetensors",
179
+ "encoder.mid_block.resnets.0.conv2.weight": "0.safetensors",
180
+ "encoder.mid_block.resnets.0.conv2.bias": "0.safetensors",
181
+ "encoder.mid_block.resnets.1.norm1.bias": "0.safetensors",
182
+ "encoder.mid_block.resnets.1.norm1.weight": "0.safetensors",
183
+ "encoder.mid_block.resnets.1.norm2.bias": "0.safetensors",
184
+ "encoder.mid_block.resnets.1.norm2.weight": "0.safetensors",
185
+ "encoder.mid_block.resnets.1.conv1.weight": "0.safetensors",
186
+ "encoder.mid_block.resnets.1.conv1.bias": "0.safetensors",
187
+ "encoder.mid_block.resnets.1.conv2.weight": "0.safetensors",
188
+ "encoder.mid_block.resnets.1.conv2.bias": "0.safetensors",
189
+ "encoder.down_blocks.0.resnets.0.norm1.bias": "0.safetensors",
190
+ "encoder.down_blocks.0.resnets.0.norm1.weight": "0.safetensors",
191
+ "encoder.down_blocks.0.resnets.0.norm2.bias": "0.safetensors",
192
+ "encoder.down_blocks.0.resnets.0.norm2.weight": "0.safetensors",
193
+ "encoder.down_blocks.0.resnets.0.conv1.weight": "0.safetensors",
194
+ "encoder.down_blocks.0.resnets.0.conv1.bias": "0.safetensors",
195
+ "encoder.down_blocks.0.resnets.0.conv2.weight": "0.safetensors",
196
+ "encoder.down_blocks.0.resnets.0.conv2.bias": "0.safetensors",
197
+ "encoder.down_blocks.0.resnets.1.norm1.bias": "0.safetensors",
198
+ "encoder.down_blocks.0.resnets.1.norm1.weight": "0.safetensors",
199
+ "encoder.down_blocks.0.resnets.1.norm2.bias": "0.safetensors",
200
+ "encoder.down_blocks.0.resnets.1.norm2.weight": "0.safetensors",
201
+ "encoder.down_blocks.0.resnets.1.conv1.weight": "0.safetensors",
202
+ "encoder.down_blocks.0.resnets.1.conv1.bias": "0.safetensors",
203
+ "encoder.down_blocks.0.resnets.1.conv2.weight": "0.safetensors",
204
+ "encoder.down_blocks.0.resnets.1.conv2.bias": "0.safetensors",
205
+ "encoder.down_blocks.0.downsamplers.0.conv.weight": "0.safetensors",
206
+ "encoder.down_blocks.0.downsamplers.0.conv.bias": "0.safetensors",
207
+ "encoder.down_blocks.1.resnets.0.norm1.bias": "0.safetensors",
208
+ "encoder.down_blocks.1.resnets.0.norm1.weight": "0.safetensors",
209
+ "encoder.down_blocks.1.resnets.0.norm2.bias": "0.safetensors",
210
+ "encoder.down_blocks.1.resnets.0.norm2.weight": "0.safetensors",
211
+ "encoder.down_blocks.1.resnets.0.conv1.weight": "0.safetensors",
212
+ "encoder.down_blocks.1.resnets.0.conv1.bias": "0.safetensors",
213
+ "encoder.down_blocks.1.resnets.0.conv2.weight": "0.safetensors",
214
+ "encoder.down_blocks.1.resnets.0.conv2.bias": "0.safetensors",
215
+ "encoder.down_blocks.1.resnets.0.conv_shortcut.weight": "0.safetensors",
216
+ "encoder.down_blocks.1.resnets.0.conv_shortcut.bias": "0.safetensors",
217
+ "encoder.down_blocks.1.resnets.1.norm1.bias": "0.safetensors",
218
+ "encoder.down_blocks.1.resnets.1.norm1.weight": "0.safetensors",
219
+ "encoder.down_blocks.1.resnets.1.norm2.bias": "0.safetensors",
220
+ "encoder.down_blocks.1.resnets.1.norm2.weight": "0.safetensors",
221
+ "encoder.down_blocks.1.resnets.1.conv1.weight": "0.safetensors",
222
+ "encoder.down_blocks.1.resnets.1.conv1.bias": "0.safetensors",
223
+ "encoder.down_blocks.1.resnets.1.conv2.weight": "0.safetensors",
224
+ "encoder.down_blocks.1.resnets.1.conv2.bias": "0.safetensors",
225
+ "encoder.down_blocks.1.downsamplers.0.conv.weight": "0.safetensors",
226
+ "encoder.down_blocks.1.downsamplers.0.conv.bias": "0.safetensors",
227
+ "encoder.down_blocks.2.resnets.0.norm1.bias": "0.safetensors",
228
+ "encoder.down_blocks.2.resnets.0.norm1.weight": "0.safetensors",
229
+ "encoder.down_blocks.2.resnets.0.norm2.bias": "0.safetensors",
230
+ "encoder.down_blocks.2.resnets.0.norm2.weight": "0.safetensors",
231
+ "encoder.down_blocks.2.resnets.0.conv1.weight": "0.safetensors",
232
+ "encoder.down_blocks.2.resnets.0.conv1.bias": "0.safetensors",
233
+ "encoder.down_blocks.2.resnets.0.conv2.weight": "0.safetensors",
234
+ "encoder.down_blocks.2.resnets.0.conv2.bias": "0.safetensors",
235
+ "encoder.down_blocks.2.resnets.0.conv_shortcut.weight": "0.safetensors",
236
+ "encoder.down_blocks.2.resnets.0.conv_shortcut.bias": "0.safetensors",
237
+ "encoder.down_blocks.2.resnets.1.norm1.bias": "0.safetensors",
238
+ "encoder.down_blocks.2.resnets.1.norm1.weight": "0.safetensors",
239
+ "encoder.down_blocks.2.resnets.1.norm2.bias": "0.safetensors",
240
+ "encoder.down_blocks.2.resnets.1.norm2.weight": "0.safetensors",
241
+ "encoder.down_blocks.2.resnets.1.conv1.weight": "0.safetensors",
242
+ "encoder.down_blocks.2.resnets.1.conv1.bias": "0.safetensors",
243
+ "encoder.down_blocks.2.resnets.1.conv2.weight": "0.safetensors",
244
+ "encoder.down_blocks.2.resnets.1.conv2.bias": "0.safetensors",
245
+ "encoder.down_blocks.2.downsamplers.0.conv.weight": "0.safetensors",
246
+ "encoder.down_blocks.2.downsamplers.0.conv.bias": "0.safetensors",
247
+ "encoder.down_blocks.3.resnets.0.norm1.bias": "0.safetensors",
248
+ "encoder.down_blocks.3.resnets.0.norm1.weight": "0.safetensors",
249
+ "encoder.down_blocks.3.resnets.0.norm2.bias": "0.safetensors",
250
+ "encoder.down_blocks.3.resnets.0.norm2.weight": "0.safetensors",
251
+ "encoder.down_blocks.3.resnets.0.conv1.weight": "0.safetensors",
252
+ "encoder.down_blocks.3.resnets.0.conv1.bias": "0.safetensors",
253
+ "encoder.down_blocks.3.resnets.0.conv2.weight": "0.safetensors",
254
+ "encoder.down_blocks.3.resnets.0.conv2.bias": "0.safetensors",
255
+ "encoder.down_blocks.3.resnets.1.norm1.bias": "0.safetensors",
256
+ "encoder.down_blocks.3.resnets.1.norm1.weight": "0.safetensors",
257
+ "encoder.down_blocks.3.resnets.1.norm2.bias": "0.safetensors",
258
+ "encoder.down_blocks.3.resnets.1.norm2.weight": "0.safetensors",
259
+ "encoder.down_blocks.3.resnets.1.conv1.weight": "0.safetensors",
260
+ "encoder.down_blocks.3.resnets.1.conv1.bias": "0.safetensors",
261
+ "encoder.down_blocks.3.resnets.1.conv2.weight": "0.safetensors",
262
+ "encoder.down_blocks.3.resnets.1.conv2.bias": "0.safetensors",
263
+ "encoder.conv_norm_out.norm.bias": "0.safetensors",
264
+ "encoder.conv_norm_out.norm.weight": "0.safetensors",
265
+ "encoder.conv_out.conv2d.weight": "0.safetensors",
266
+ "encoder.conv_out.conv2d.bias": "0.safetensors"
267
+ }
268
+ }