Commit ·
3ce9bf4
0
Parent(s):
Upload model
Browse files- .gitattributes +37 -0
- README.md +174 -0
- aether_config.json +41 -0
- lora_manifest.yaml +53 -0
- model_index.json +25 -0
- scheduler/scheduler_config.json +18 -0
- text_encoder/config.json +71 -0
- text_encoder/model.safetensors +3 -0
- tokenizer/chat_template.jinja +89 -0
- tokenizer/tokenizer.json +3 -0
- tokenizer/tokenizer_config.json +29 -0
- transformer/config.json +33 -0
- transformer/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
- transformer/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
- transformer/diffusion_pytorch_model.safetensors.index.json +528 -0
- vae/config.json +38 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
- vlm_judge/chat_template.jinja +263 -0
- vlm_judge/config.json +112 -0
- vlm_judge/generation_config.json +14 -0
- vlm_judge/model.safetensors +3 -0
- vlm_judge/tokenizer.json +3 -0
- vlm_judge/tokenizer_config.json +95 -0
.gitattributes
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
vlm_judge/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- ko
|
| 6 |
+
library_name: diffusers
|
| 7 |
+
pipeline_tag: text-to-image
|
| 8 |
+
tags:
|
| 9 |
+
- darwin-image
|
| 10 |
+
- aether-metacognitive
|
| 11 |
+
- z-image
|
| 12 |
+
- lora-merge
|
| 13 |
+
- korean-text
|
| 14 |
+
- vlm-judge
|
| 15 |
+
base_model:
|
| 16 |
+
- Tongyi-MAI/Z-Image-Turbo
|
| 17 |
+
- Shakker-Labs/AWPortrait-Z
|
| 18 |
+
- qqnyanddld/nsfw-z-image-lora
|
| 19 |
+
- renderartist/Technically-Color-Z-Image-Turbo
|
| 20 |
+
- wcde/Z-Image-Turbo-DeJPEG-Lora
|
| 21 |
+
inference: false
|
| 22 |
+
---
|
| 23 |
+
|
| 24 |
+
# Darwin-Image-v1 — Unified DiT + VLM
|
| 25 |
+
|
| 26 |
+
**Darwin-Image-v1** is a **physically unified** model repository that
|
| 27 |
+
combines two models into a single HF repo:
|
| 28 |
+
|
| 29 |
+
1. **Z-Image Turbo** (6B DiT) at the repo root, with 4 LoRAs fused into
|
| 30 |
+
the transformer weights (no runtime adapter loading).
|
| 31 |
+
2. **Darwin-4B-David** (Gemma4 multimodal VLM, ~16GB bf16) inside the
|
| 32 |
+
`vlm_judge/` subfolder.
|
| 33 |
+
|
| 34 |
+
Both models coexist as real safetensors files in this single repo, so a
|
| 35 |
+
single `from_pretrained()` call downloads everything needed for the
|
| 36 |
+
AETHER metacognitive image generation pipeline.
|
| 37 |
+
|
| 38 |
+
## Repo Layout
|
| 39 |
+
|
| 40 |
+
```
|
| 41 |
+
FINAL-Bench/Darwin-Image-v1/
|
| 42 |
+
├── model_index.json # Z-Image pipeline manifest
|
| 43 |
+
├── scheduler/ # Z-Image components
|
| 44 |
+
├── text_encoder/ # (Qwen3)
|
| 45 |
+
├── tokenizer/
|
| 46 |
+
├── transformer/ # ★ DiT with 4 LoRAs fused
|
| 47 |
+
├── vae/
|
| 48 |
+
├── vlm_judge/ # ★★ Darwin-4B-David
|
| 49 |
+
│ ├── config.json # Gemma4ForConditionalGeneration
|
| 50 |
+
│ ├── model.safetensors # ~16GB bfloat16
|
| 51 |
+
│ ├── tokenizer.json
|
| 52 |
+
│ ├── chat_template.jinja
|
| 53 |
+
│ └── generation_config.json
|
| 54 |
+
├── lora_manifest.yaml
|
| 55 |
+
├── aether_config.json
|
| 56 |
+
├── fuse_report.json
|
| 57 |
+
└── README.md (this file)
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
+
## LoRA Stack Fused Into DiT (v2, 2026-04-10)
|
| 61 |
+
|
| 62 |
+
```
|
| 63 |
+
Z-Image Turbo (6B DiT, bf16)
|
| 64 |
+
└── + Shakker-Labs/AWPortrait-Z (scale 0.7) → portrait quality
|
| 65 |
+
└── + qqnyanddld/nsfw-z-image-lora (scale 0.5) → uncensored
|
| 66 |
+
└── + renderartist/Technically-Color-Z-Image-Turbo (scale 0.3) → color
|
| 67 |
+
```
|
| 68 |
+
|
| 69 |
+
All LoRAs use the ai-toolkit standard format (480 keys each,
|
| 70 |
+
`diffusion_model.layers.N.X.lora_A/B.weight`). Fused via direct matrix
|
| 71 |
+
update (`pipeline/manual_fuse.py`): `W += (B @ A) × (alpha/rank) × scale`.
|
| 72 |
+
|
| 73 |
+
### v2 Changelog
|
| 74 |
+
|
| 75 |
+
- **Removed** `wcde/Z-Image-Turbo-DeJPEG-Lora/dejpeg_v3` — caused over-smoothing
|
| 76 |
+
that destroyed portrait/color detail. delta_norm was 3.67 vs 0.14~0.41 for
|
| 77 |
+
other LoRAs (26× baseline). Z-Image Turbo is distilled and has minimal
|
| 78 |
+
JPEG artifacts to begin with, so dejpeg was unnecessary.
|
| 79 |
+
- **Reduced** `Technically-Color-Z-Image-Turbo` scale 0.4 → 0.3 to prevent
|
| 80 |
+
over-saturation on high-contrast/neon scenes.
|
| 81 |
+
|
| 82 |
+
## Usage
|
| 83 |
+
|
| 84 |
+
### DiT only (text-to-image)
|
| 85 |
+
```python
|
| 86 |
+
from diffusers import DiffusionPipeline
|
| 87 |
+
import torch
|
| 88 |
+
|
| 89 |
+
pipe = DiffusionPipeline.from_pretrained(
|
| 90 |
+
"FINAL-Bench/Darwin-Image-v1",
|
| 91 |
+
torch_dtype=torch.bfloat16,
|
| 92 |
+
token="hf_...",
|
| 93 |
+
).to("cuda")
|
| 94 |
+
|
| 95 |
+
image = pipe(
|
| 96 |
+
prompt="cinematic portrait of a korean woman, golden hour, 85mm f1.4",
|
| 97 |
+
num_inference_steps=8,
|
| 98 |
+
guidance_scale=3.5,
|
| 99 |
+
height=1024,
|
| 100 |
+
width=1024,
|
| 101 |
+
).images[0]
|
| 102 |
+
```
|
| 103 |
+
|
| 104 |
+
### Load the bundled VLM judge (from subfolder)
|
| 105 |
+
```python
|
| 106 |
+
from transformers import AutoModel, AutoProcessor
|
| 107 |
+
import torch
|
| 108 |
+
|
| 109 |
+
judge = AutoModel.from_pretrained(
|
| 110 |
+
"FINAL-Bench/Darwin-Image-v1",
|
| 111 |
+
subfolder="vlm_judge",
|
| 112 |
+
torch_dtype=torch.bfloat16,
|
| 113 |
+
device_map="cuda",
|
| 114 |
+
token="hf_...",
|
| 115 |
+
)
|
| 116 |
+
processor = AutoProcessor.from_pretrained(
|
| 117 |
+
"FINAL-Bench/Darwin-Image-v1",
|
| 118 |
+
subfolder="vlm_judge",
|
| 119 |
+
token="hf_...",
|
| 120 |
+
)
|
| 121 |
+
```
|
| 122 |
+
|
| 123 |
+
## AETHER Integration
|
| 124 |
+
|
| 125 |
+
For the full metacognitive pipeline (VLM prompt enhancement + quality
|
| 126 |
+
judging + Korean text inpainting), use the Darwin Image pipeline code:
|
| 127 |
+
|
| 128 |
+
```python
|
| 129 |
+
from darwin_image.pipeline import DarwinZImagePipeline, DarwinJudge, run_aether, AetherConfig
|
| 130 |
+
|
| 131 |
+
pipe = DarwinZImagePipeline(base_model="FINAL-Bench/Darwin-Image-v1")
|
| 132 |
+
judge = DarwinJudge() # loads Darwin-4B-David
|
| 133 |
+
|
| 134 |
+
result = run_aether(
|
| 135 |
+
user_prompt='영화 포스터: "봄의 서울" 벚꽃 남산타워',
|
| 136 |
+
pipe=pipe,
|
| 137 |
+
judge=judge,
|
| 138 |
+
config=AetherConfig(max_iter=3, threshold=8.0),
|
| 139 |
+
seed=42,
|
| 140 |
+
)
|
| 141 |
+
result.final_image.save("out.png")
|
| 142 |
+
```
|
| 143 |
+
|
| 144 |
+
## Default AETHER Config
|
| 145 |
+
|
| 146 |
+
See `aether_config.json` for the default metacognitive loop parameters:
|
| 147 |
+
- `max_iter`: 3 (up to 3 retries)
|
| 148 |
+
- `threshold`: 8.0 (overall score threshold to exit early)
|
| 149 |
+
- `enable_vlm_enhance`: true (VLM rewrites prompts)
|
| 150 |
+
- `enable_vlm_judge`: true (VLM scores each iteration)
|
| 151 |
+
- `enable_mti`: false (experimental, off by default on 8-step distilled models)
|
| 152 |
+
|
| 153 |
+
## License
|
| 154 |
+
|
| 155 |
+
Apache 2.0 — inherits from Z-Image Turbo and all LoRA base models.
|
| 156 |
+
|
| 157 |
+
## Citation
|
| 158 |
+
|
| 159 |
+
If you use Darwin-Image-v1, please cite:
|
| 160 |
+
|
| 161 |
+
```bibtex
|
| 162 |
+
@misc{darwin-image-2026,
|
| 163 |
+
title={Darwin Image: VLM-Guided Metacognitive Image Generation with Korean Text Integration},
|
| 164 |
+
author={VIDRAFT and 지니젠AI and FINAL-Bench},
|
| 165 |
+
year={2026},
|
| 166 |
+
howpublished={\url{https://huggingface.co/FINAL-Bench/Darwin-Image-v1}},
|
| 167 |
+
}
|
| 168 |
+
```
|
| 169 |
+
|
| 170 |
+
## Safety Notice
|
| 171 |
+
|
| 172 |
+
This model includes an uncensored LoRA component. Use responsibly.
|
| 173 |
+
The AETHER pipeline Space (`darwin-image-gen`) is deployed as **private**
|
| 174 |
+
(FINAL-Bench org only) for this reason.
|
aether_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0.0",
|
| 3 |
+
"model_id": "FINAL-Bench/Darwin-Image-v1",
|
| 4 |
+
"vlm_judge_id": "FINAL-Bench/Darwin-4B-David",
|
| 5 |
+
"aether_loop": {
|
| 6 |
+
"max_iter": 3,
|
| 7 |
+
"threshold": 8.0,
|
| 8 |
+
"enable_vlm_enhance": true,
|
| 9 |
+
"enable_vlm_judge": true,
|
| 10 |
+
"enable_mti": false,
|
| 11 |
+
"seed_increment": 1,
|
| 12 |
+
"keep_all_iterations": true
|
| 13 |
+
},
|
| 14 |
+
"generation_defaults": {
|
| 15 |
+
"num_inference_steps": 9,
|
| 16 |
+
"guidance_scale": 0.0,
|
| 17 |
+
"height": 1024,
|
| 18 |
+
"width": 1024,
|
| 19 |
+
"negative_prompt": "",
|
| 20 |
+
"note": "Z-Image Turbo is a distilled model. CFG must be disabled (0.0); higher values cause darkening and flow matching drift."
|
| 21 |
+
},
|
| 22 |
+
"inpaint": {
|
| 23 |
+
"strength": 0.35,
|
| 24 |
+
"num_steps": 12,
|
| 25 |
+
"mask_dilate_px": 12,
|
| 26 |
+
"font_default": "NotoSansCJK-Bold"
|
| 27 |
+
},
|
| 28 |
+
"mti": {
|
| 29 |
+
"entropy_percentile": 0.75,
|
| 30 |
+
"cfg_boost": 1.5,
|
| 31 |
+
"apply_to_steps": null
|
| 32 |
+
},
|
| 33 |
+
"lora_stack": [
|
| 34 |
+
{"repo_id": "Shakker-Labs/AWPortrait-Z", "scale": 0.7, "purpose": "portrait"},
|
| 35 |
+
{"repo_id": "qqnyanddld/nsfw-z-image-lora", "scale": 0.5, "purpose": "uncensored"},
|
| 36 |
+
{"repo_id": "renderartist/Technically-Color-Z-Image-Turbo", "scale": 0.3, "purpose": "color"}
|
| 37 |
+
],
|
| 38 |
+
"lora_stack_changelog": {
|
| 39 |
+
"v2_2026-04-10": "Removed dejpeg (delta_norm 3.67 caused over-smoothing); reduced color 0.4→0.3"
|
| 40 |
+
}
|
| 41 |
+
}
|
lora_manifest.yaml
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
# LoRA stack to fuse into Z-Image Turbo for Darwin-Image-v1 (v2: rebalanced)
|
| 3 |
+
#
|
| 4 |
+
# All LoRAs share the ai-toolkit standard format (480 keys,
|
| 5 |
+
# `diffusion_model.layers.N.X.lora_A/B.weight`, 30 DiT layers × 8 modules × 2).
|
| 6 |
+
# Direct matrix fusion via `pipeline/manual_fuse.py` — W += (B@A)*(alpha/rank)*scale.
|
| 7 |
+
#
|
| 8 |
+
# v2 CHANGELOG (2026-04-10):
|
| 9 |
+
# - REMOVED `dejpeg` (wcde/Z-Image-Turbo-DeJPEG-Lora/dejpeg_v3)
|
| 10 |
+
# Reason: delta_norm 3.67 (26× other LoRAs) caused over-smoothing,
|
| 11 |
+
# destroying portrait/color detail. The LoRA's intended goal — JPEG
|
| 12 |
+
# artifact removal — is unnecessary for Z-Image Turbo (distilled model
|
| 13 |
+
# has no JPEG artifacts to remove by design).
|
| 14 |
+
# - REDUCED `color` scale 0.4 → 0.3
|
| 15 |
+
# Reason: prevent over-saturation on neon/night scenes.
|
| 16 |
+
#
|
| 17 |
+
# Final stack (3 LoRAs, combined delta_norm well within baseline):
|
| 18 |
+
# portrait 0.7 + nsfw 0.5 + color 0.3
|
| 19 |
+
|
| 20 |
+
base_model: Tongyi-MAI/Z-Image-Turbo
|
| 21 |
+
output_repo: FINAL-Bench/Darwin-Image-v1
|
| 22 |
+
|
| 23 |
+
loras:
|
| 24 |
+
- repo_id: Shakker-Labs/AWPortrait-Z
|
| 25 |
+
weight_name: AWPortrait-Z.safetensors
|
| 26 |
+
adapter_name: portrait
|
| 27 |
+
scale: 0.7
|
| 28 |
+
purpose: "Human portrait quality (denoise, lighting, diverse ethnicities)"
|
| 29 |
+
|
| 30 |
+
- repo_id: qqnyanddld/nsfw-z-image-lora
|
| 31 |
+
weight_name: lora-women.safetensors
|
| 32 |
+
adapter_name: nsfw
|
| 33 |
+
scale: 0.5
|
| 34 |
+
purpose: "Uncensored generation — generic women anatomy"
|
| 35 |
+
|
| 36 |
+
- repo_id: renderartist/Technically-Color-Z-Image-Turbo
|
| 37 |
+
weight_name: Technically_Color_Z_Image_Turbo_v1_renderartist_2000.safetensors
|
| 38 |
+
adapter_name: color
|
| 39 |
+
scale: 0.3
|
| 40 |
+
purpose: "Enhanced color/saturation palette (reduced from 0.4 to prevent over-saturation)"
|
| 41 |
+
|
| 42 |
+
validation:
|
| 43 |
+
test_prompts:
|
| 44 |
+
- "cinematic portrait of a woman, golden hour, 85mm f1.4"
|
| 45 |
+
- "vibrant street photography, tokyo at night, neon lights"
|
| 46 |
+
- "detailed close-up of a cat's eye, macro photography"
|
| 47 |
+
expected_test_latency_sec: 3.0
|
| 48 |
+
min_output_size_gb: 10
|
| 49 |
+
# Z-Image Turbo official recommended generation params
|
| 50 |
+
sampler:
|
| 51 |
+
num_inference_steps: 9
|
| 52 |
+
guidance_scale: 0.0
|
| 53 |
+
negative_prompt: ""
|
model_index.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ZImagePipeline",
|
| 3 |
+
"_diffusers_version": "0.37.1",
|
| 4 |
+
"_name_or_path": "Tongyi-MAI/Z-Image-Turbo",
|
| 5 |
+
"scheduler": [
|
| 6 |
+
"diffusers",
|
| 7 |
+
"FlowMatchEulerDiscreteScheduler"
|
| 8 |
+
],
|
| 9 |
+
"text_encoder": [
|
| 10 |
+
"transformers",
|
| 11 |
+
"Qwen3Model"
|
| 12 |
+
],
|
| 13 |
+
"tokenizer": [
|
| 14 |
+
"transformers",
|
| 15 |
+
"Qwen2Tokenizer"
|
| 16 |
+
],
|
| 17 |
+
"transformer": [
|
| 18 |
+
"diffusers",
|
| 19 |
+
"ZImageTransformer2DModel"
|
| 20 |
+
],
|
| 21 |
+
"vae": [
|
| 22 |
+
"diffusers",
|
| 23 |
+
"AutoencoderKL"
|
| 24 |
+
]
|
| 25 |
+
}
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
+
"_diffusers_version": "0.37.1",
|
| 4 |
+
"base_image_seq_len": 256,
|
| 5 |
+
"base_shift": 0.5,
|
| 6 |
+
"invert_sigmas": false,
|
| 7 |
+
"max_image_seq_len": 4096,
|
| 8 |
+
"max_shift": 1.15,
|
| 9 |
+
"num_train_timesteps": 1000,
|
| 10 |
+
"shift": 3.0,
|
| 11 |
+
"shift_terminal": null,
|
| 12 |
+
"stochastic_sampling": false,
|
| 13 |
+
"time_shift_type": "exponential",
|
| 14 |
+
"use_beta_sigmas": false,
|
| 15 |
+
"use_dynamic_shifting": false,
|
| 16 |
+
"use_exponential_sigmas": false,
|
| 17 |
+
"use_karras_sigmas": false
|
| 18 |
+
}
|
text_encoder/config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3Model"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2560,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 9728,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention"
|
| 52 |
+
],
|
| 53 |
+
"max_position_embeddings": 40960,
|
| 54 |
+
"max_window_layers": 36,
|
| 55 |
+
"model_type": "qwen3",
|
| 56 |
+
"num_attention_heads": 32,
|
| 57 |
+
"num_hidden_layers": 36,
|
| 58 |
+
"num_key_value_heads": 8,
|
| 59 |
+
"pad_token_id": null,
|
| 60 |
+
"rms_norm_eps": 1e-06,
|
| 61 |
+
"rope_parameters": {
|
| 62 |
+
"rope_theta": 1000000,
|
| 63 |
+
"rope_type": "default"
|
| 64 |
+
},
|
| 65 |
+
"sliding_window": null,
|
| 66 |
+
"tie_word_embeddings": true,
|
| 67 |
+
"transformers_version": "5.5.3",
|
| 68 |
+
"use_cache": true,
|
| 69 |
+
"use_sliding_window": false,
|
| 70 |
+
"vocab_size": 151936
|
| 71 |
+
}
|
text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c1c66c8c05c4bb6764a40f0fa52156dc0818a46fee29e197b0d92d88c6d757f
|
| 3 |
+
size 8044979688
|
tokenizer/chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
tokenizer/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
+
size 11422650
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": true,
|
| 24 |
+
"model_max_length": 131072,
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null
|
| 29 |
+
}
|
transformer/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ZImageTransformer2DModel",
|
| 3 |
+
"_diffusers_version": "0.37.1",
|
| 4 |
+
"_name_or_path": "/home/user/.cache/huggingface/hub/models--Tongyi-MAI--Z-Image-Turbo/snapshots/f332072aa78be7aecdf3ee76d5c247082da564a6/transformer",
|
| 5 |
+
"all_f_patch_size": [
|
| 6 |
+
1
|
| 7 |
+
],
|
| 8 |
+
"all_patch_size": [
|
| 9 |
+
2
|
| 10 |
+
],
|
| 11 |
+
"axes_dims": [
|
| 12 |
+
32,
|
| 13 |
+
48,
|
| 14 |
+
48
|
| 15 |
+
],
|
| 16 |
+
"axes_lens": [
|
| 17 |
+
1536,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"cap_feat_dim": 2560,
|
| 22 |
+
"dim": 3840,
|
| 23 |
+
"in_channels": 16,
|
| 24 |
+
"n_heads": 30,
|
| 25 |
+
"n_kv_heads": 30,
|
| 26 |
+
"n_layers": 30,
|
| 27 |
+
"n_refiner_layers": 2,
|
| 28 |
+
"norm_eps": 1e-05,
|
| 29 |
+
"qk_norm": true,
|
| 30 |
+
"rope_theta": 256.0,
|
| 31 |
+
"siglip_feat_dim": null,
|
| 32 |
+
"t_scale": 1000.0
|
| 33 |
+
}
|
transformer/diffusion_pytorch_model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e23e033f426c5d4af07db0e76d6863d9190107d408cb6cae649ceef32f10c8cf
|
| 3 |
+
size 9973727144
|
transformer/diffusion_pytorch_model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7eeb285acb0d2135adbea8a9336eb0322653e334d611cef54aaebbbc2be61014
|
| 3 |
+
size 2336146728
|
transformer/diffusion_pytorch_model.safetensors.index.json
ADDED
|
@@ -0,0 +1,528 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 12309817472
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"all_final_layer.2-1.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 7 |
+
"all_final_layer.2-1.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 8 |
+
"all_final_layer.2-1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 9 |
+
"all_final_layer.2-1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 10 |
+
"all_x_embedder.2-1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 11 |
+
"all_x_embedder.2-1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 12 |
+
"cap_embedder.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 13 |
+
"cap_embedder.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 14 |
+
"cap_embedder.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 15 |
+
"cap_pad_token": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 16 |
+
"context_refiner.0.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 17 |
+
"context_refiner.0.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 18 |
+
"context_refiner.0.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 19 |
+
"context_refiner.0.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 20 |
+
"context_refiner.0.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 21 |
+
"context_refiner.0.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 22 |
+
"context_refiner.0.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 23 |
+
"context_refiner.0.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 24 |
+
"context_refiner.0.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 25 |
+
"context_refiner.0.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 26 |
+
"context_refiner.0.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 27 |
+
"context_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 28 |
+
"context_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 29 |
+
"context_refiner.1.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 30 |
+
"context_refiner.1.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 31 |
+
"context_refiner.1.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 32 |
+
"context_refiner.1.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 33 |
+
"context_refiner.1.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 34 |
+
"context_refiner.1.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 35 |
+
"context_refiner.1.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 36 |
+
"context_refiner.1.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 37 |
+
"context_refiner.1.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 38 |
+
"context_refiner.1.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 39 |
+
"context_refiner.1.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 40 |
+
"context_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 41 |
+
"context_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 42 |
+
"layers.0.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 43 |
+
"layers.0.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 44 |
+
"layers.0.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 45 |
+
"layers.0.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 46 |
+
"layers.0.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 47 |
+
"layers.0.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 48 |
+
"layers.0.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 49 |
+
"layers.0.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 50 |
+
"layers.0.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 51 |
+
"layers.0.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 52 |
+
"layers.0.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 53 |
+
"layers.0.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 54 |
+
"layers.0.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 55 |
+
"layers.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 56 |
+
"layers.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 57 |
+
"layers.1.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 58 |
+
"layers.1.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 59 |
+
"layers.1.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 60 |
+
"layers.1.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 61 |
+
"layers.1.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 62 |
+
"layers.1.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 63 |
+
"layers.1.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 64 |
+
"layers.1.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 65 |
+
"layers.1.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 66 |
+
"layers.1.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 67 |
+
"layers.1.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 68 |
+
"layers.1.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 69 |
+
"layers.1.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 70 |
+
"layers.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 71 |
+
"layers.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 72 |
+
"layers.10.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 73 |
+
"layers.10.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 74 |
+
"layers.10.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 75 |
+
"layers.10.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 76 |
+
"layers.10.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 77 |
+
"layers.10.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 78 |
+
"layers.10.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 79 |
+
"layers.10.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 80 |
+
"layers.10.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 81 |
+
"layers.10.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 82 |
+
"layers.10.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 83 |
+
"layers.10.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 84 |
+
"layers.10.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 85 |
+
"layers.10.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 86 |
+
"layers.10.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 87 |
+
"layers.11.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 88 |
+
"layers.11.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 89 |
+
"layers.11.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 90 |
+
"layers.11.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 91 |
+
"layers.11.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 92 |
+
"layers.11.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 93 |
+
"layers.11.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 94 |
+
"layers.11.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 95 |
+
"layers.11.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 96 |
+
"layers.11.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 97 |
+
"layers.11.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 98 |
+
"layers.11.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 99 |
+
"layers.11.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 100 |
+
"layers.11.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 101 |
+
"layers.11.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 102 |
+
"layers.12.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 103 |
+
"layers.12.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 104 |
+
"layers.12.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 105 |
+
"layers.12.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 106 |
+
"layers.12.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 107 |
+
"layers.12.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 108 |
+
"layers.12.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 109 |
+
"layers.12.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 110 |
+
"layers.12.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 111 |
+
"layers.12.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 112 |
+
"layers.12.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 113 |
+
"layers.12.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 114 |
+
"layers.12.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 115 |
+
"layers.12.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 116 |
+
"layers.12.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 117 |
+
"layers.13.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 118 |
+
"layers.13.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 119 |
+
"layers.13.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 120 |
+
"layers.13.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 121 |
+
"layers.13.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 122 |
+
"layers.13.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 123 |
+
"layers.13.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 124 |
+
"layers.13.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 125 |
+
"layers.13.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 126 |
+
"layers.13.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 127 |
+
"layers.13.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 128 |
+
"layers.13.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 129 |
+
"layers.13.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 130 |
+
"layers.13.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 131 |
+
"layers.13.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 132 |
+
"layers.14.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 133 |
+
"layers.14.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 134 |
+
"layers.14.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 135 |
+
"layers.14.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 136 |
+
"layers.14.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 137 |
+
"layers.14.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 138 |
+
"layers.14.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 139 |
+
"layers.14.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 140 |
+
"layers.14.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 141 |
+
"layers.14.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 142 |
+
"layers.14.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 143 |
+
"layers.14.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 144 |
+
"layers.14.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 145 |
+
"layers.14.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 146 |
+
"layers.14.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 147 |
+
"layers.15.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 148 |
+
"layers.15.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 149 |
+
"layers.15.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 150 |
+
"layers.15.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 151 |
+
"layers.15.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 152 |
+
"layers.15.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 153 |
+
"layers.15.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 154 |
+
"layers.15.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 155 |
+
"layers.15.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 156 |
+
"layers.15.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 157 |
+
"layers.15.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 158 |
+
"layers.15.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 159 |
+
"layers.15.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 160 |
+
"layers.15.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 161 |
+
"layers.15.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 162 |
+
"layers.16.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 163 |
+
"layers.16.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 164 |
+
"layers.16.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 165 |
+
"layers.16.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 166 |
+
"layers.16.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 167 |
+
"layers.16.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 168 |
+
"layers.16.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 169 |
+
"layers.16.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 170 |
+
"layers.16.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 171 |
+
"layers.16.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 172 |
+
"layers.16.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 173 |
+
"layers.16.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 174 |
+
"layers.16.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 175 |
+
"layers.16.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 176 |
+
"layers.16.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 177 |
+
"layers.17.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 178 |
+
"layers.17.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 179 |
+
"layers.17.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 180 |
+
"layers.17.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 181 |
+
"layers.17.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 182 |
+
"layers.17.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 183 |
+
"layers.17.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 184 |
+
"layers.17.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 185 |
+
"layers.17.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 186 |
+
"layers.17.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 187 |
+
"layers.17.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 188 |
+
"layers.17.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 189 |
+
"layers.17.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 190 |
+
"layers.17.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 191 |
+
"layers.17.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 192 |
+
"layers.18.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 193 |
+
"layers.18.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 194 |
+
"layers.18.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 195 |
+
"layers.18.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 196 |
+
"layers.18.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 197 |
+
"layers.18.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 198 |
+
"layers.18.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 199 |
+
"layers.18.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 200 |
+
"layers.18.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 201 |
+
"layers.18.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 202 |
+
"layers.18.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 203 |
+
"layers.18.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 204 |
+
"layers.18.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 205 |
+
"layers.18.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 206 |
+
"layers.18.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 207 |
+
"layers.19.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 208 |
+
"layers.19.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 209 |
+
"layers.19.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 210 |
+
"layers.19.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 211 |
+
"layers.19.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 212 |
+
"layers.19.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 213 |
+
"layers.19.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 214 |
+
"layers.19.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 215 |
+
"layers.19.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 216 |
+
"layers.19.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 217 |
+
"layers.19.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 218 |
+
"layers.19.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 219 |
+
"layers.19.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 220 |
+
"layers.19.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 221 |
+
"layers.19.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 222 |
+
"layers.2.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 223 |
+
"layers.2.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 224 |
+
"layers.2.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 225 |
+
"layers.2.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 226 |
+
"layers.2.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 227 |
+
"layers.2.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 228 |
+
"layers.2.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 229 |
+
"layers.2.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 230 |
+
"layers.2.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 231 |
+
"layers.2.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 232 |
+
"layers.2.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 233 |
+
"layers.2.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 234 |
+
"layers.2.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 235 |
+
"layers.2.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 236 |
+
"layers.2.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 237 |
+
"layers.20.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 238 |
+
"layers.20.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 239 |
+
"layers.20.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 240 |
+
"layers.20.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 241 |
+
"layers.20.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 242 |
+
"layers.20.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 243 |
+
"layers.20.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 244 |
+
"layers.20.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 245 |
+
"layers.20.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 246 |
+
"layers.20.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 247 |
+
"layers.20.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 248 |
+
"layers.20.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 249 |
+
"layers.20.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 250 |
+
"layers.20.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 251 |
+
"layers.20.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 252 |
+
"layers.21.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 253 |
+
"layers.21.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 254 |
+
"layers.21.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 255 |
+
"layers.21.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 256 |
+
"layers.21.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 257 |
+
"layers.21.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 258 |
+
"layers.21.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 259 |
+
"layers.21.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 260 |
+
"layers.21.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 261 |
+
"layers.21.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 262 |
+
"layers.21.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 263 |
+
"layers.21.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 264 |
+
"layers.21.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 265 |
+
"layers.21.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 266 |
+
"layers.21.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 267 |
+
"layers.22.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 268 |
+
"layers.22.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 269 |
+
"layers.22.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 270 |
+
"layers.22.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 271 |
+
"layers.22.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 272 |
+
"layers.22.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 273 |
+
"layers.22.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 274 |
+
"layers.22.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 275 |
+
"layers.22.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 276 |
+
"layers.22.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 277 |
+
"layers.22.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 278 |
+
"layers.22.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 279 |
+
"layers.22.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 280 |
+
"layers.22.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 281 |
+
"layers.22.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 282 |
+
"layers.23.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 283 |
+
"layers.23.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 284 |
+
"layers.23.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 285 |
+
"layers.23.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 286 |
+
"layers.23.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 287 |
+
"layers.23.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 288 |
+
"layers.23.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 289 |
+
"layers.23.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 290 |
+
"layers.23.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 291 |
+
"layers.23.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 292 |
+
"layers.23.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 293 |
+
"layers.23.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 294 |
+
"layers.23.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 295 |
+
"layers.23.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 296 |
+
"layers.23.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 297 |
+
"layers.24.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 298 |
+
"layers.24.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 299 |
+
"layers.24.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 300 |
+
"layers.24.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 301 |
+
"layers.24.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 302 |
+
"layers.24.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 303 |
+
"layers.24.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 304 |
+
"layers.24.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 305 |
+
"layers.24.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 306 |
+
"layers.24.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 307 |
+
"layers.24.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 308 |
+
"layers.24.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 309 |
+
"layers.24.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 310 |
+
"layers.24.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 311 |
+
"layers.24.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 312 |
+
"layers.25.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 313 |
+
"layers.25.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 314 |
+
"layers.25.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 315 |
+
"layers.25.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 316 |
+
"layers.25.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 317 |
+
"layers.25.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 318 |
+
"layers.25.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 319 |
+
"layers.25.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 320 |
+
"layers.25.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 321 |
+
"layers.25.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 322 |
+
"layers.25.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 323 |
+
"layers.25.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 324 |
+
"layers.25.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 325 |
+
"layers.25.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 326 |
+
"layers.25.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 327 |
+
"layers.26.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 328 |
+
"layers.26.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 329 |
+
"layers.26.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 330 |
+
"layers.26.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 331 |
+
"layers.26.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 332 |
+
"layers.26.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 333 |
+
"layers.26.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 334 |
+
"layers.26.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 335 |
+
"layers.26.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 336 |
+
"layers.26.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 337 |
+
"layers.26.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 338 |
+
"layers.26.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 339 |
+
"layers.26.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 340 |
+
"layers.26.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 341 |
+
"layers.26.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 342 |
+
"layers.27.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 343 |
+
"layers.27.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 344 |
+
"layers.27.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 345 |
+
"layers.27.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 346 |
+
"layers.27.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 347 |
+
"layers.27.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 348 |
+
"layers.27.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 349 |
+
"layers.27.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 350 |
+
"layers.27.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 351 |
+
"layers.27.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 352 |
+
"layers.27.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 353 |
+
"layers.27.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 354 |
+
"layers.27.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 355 |
+
"layers.27.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 356 |
+
"layers.27.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 357 |
+
"layers.28.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 358 |
+
"layers.28.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 359 |
+
"layers.28.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 360 |
+
"layers.28.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 361 |
+
"layers.28.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 362 |
+
"layers.28.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 363 |
+
"layers.28.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 364 |
+
"layers.28.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 365 |
+
"layers.28.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 366 |
+
"layers.28.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 367 |
+
"layers.28.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 368 |
+
"layers.28.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 369 |
+
"layers.28.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 370 |
+
"layers.28.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 371 |
+
"layers.28.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 372 |
+
"layers.29.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 373 |
+
"layers.29.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 374 |
+
"layers.29.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 375 |
+
"layers.29.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 376 |
+
"layers.29.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 377 |
+
"layers.29.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 378 |
+
"layers.29.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 379 |
+
"layers.29.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 380 |
+
"layers.29.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 381 |
+
"layers.29.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 382 |
+
"layers.29.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 383 |
+
"layers.29.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 384 |
+
"layers.29.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 385 |
+
"layers.29.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 386 |
+
"layers.29.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
|
| 387 |
+
"layers.3.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 388 |
+
"layers.3.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 389 |
+
"layers.3.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 390 |
+
"layers.3.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 391 |
+
"layers.3.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 392 |
+
"layers.3.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 393 |
+
"layers.3.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 394 |
+
"layers.3.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 395 |
+
"layers.3.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 396 |
+
"layers.3.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 397 |
+
"layers.3.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 398 |
+
"layers.3.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 399 |
+
"layers.3.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 400 |
+
"layers.3.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 401 |
+
"layers.3.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 402 |
+
"layers.4.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 403 |
+
"layers.4.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 404 |
+
"layers.4.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 405 |
+
"layers.4.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 406 |
+
"layers.4.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 407 |
+
"layers.4.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 408 |
+
"layers.4.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 409 |
+
"layers.4.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 410 |
+
"layers.4.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 411 |
+
"layers.4.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 412 |
+
"layers.4.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 413 |
+
"layers.4.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 414 |
+
"layers.4.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 415 |
+
"layers.4.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 416 |
+
"layers.4.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 417 |
+
"layers.5.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 418 |
+
"layers.5.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 419 |
+
"layers.5.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 420 |
+
"layers.5.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 421 |
+
"layers.5.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 422 |
+
"layers.5.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 423 |
+
"layers.5.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 424 |
+
"layers.5.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 425 |
+
"layers.5.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 426 |
+
"layers.5.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 427 |
+
"layers.5.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 428 |
+
"layers.5.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 429 |
+
"layers.5.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 430 |
+
"layers.5.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 431 |
+
"layers.5.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 432 |
+
"layers.6.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 433 |
+
"layers.6.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 434 |
+
"layers.6.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 435 |
+
"layers.6.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 436 |
+
"layers.6.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 437 |
+
"layers.6.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 438 |
+
"layers.6.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 439 |
+
"layers.6.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 440 |
+
"layers.6.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 441 |
+
"layers.6.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 442 |
+
"layers.6.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 443 |
+
"layers.6.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 444 |
+
"layers.6.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 445 |
+
"layers.6.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 446 |
+
"layers.6.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 447 |
+
"layers.7.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 448 |
+
"layers.7.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 449 |
+
"layers.7.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 450 |
+
"layers.7.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 451 |
+
"layers.7.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 452 |
+
"layers.7.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 453 |
+
"layers.7.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 454 |
+
"layers.7.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 455 |
+
"layers.7.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 456 |
+
"layers.7.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 457 |
+
"layers.7.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 458 |
+
"layers.7.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 459 |
+
"layers.7.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 460 |
+
"layers.7.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 461 |
+
"layers.7.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 462 |
+
"layers.8.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 463 |
+
"layers.8.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 464 |
+
"layers.8.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 465 |
+
"layers.8.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 466 |
+
"layers.8.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 467 |
+
"layers.8.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 468 |
+
"layers.8.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 469 |
+
"layers.8.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 470 |
+
"layers.8.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 471 |
+
"layers.8.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 472 |
+
"layers.8.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 473 |
+
"layers.8.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 474 |
+
"layers.8.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 475 |
+
"layers.8.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 476 |
+
"layers.8.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 477 |
+
"layers.9.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 478 |
+
"layers.9.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 479 |
+
"layers.9.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 480 |
+
"layers.9.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 481 |
+
"layers.9.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 482 |
+
"layers.9.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 483 |
+
"layers.9.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 484 |
+
"layers.9.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 485 |
+
"layers.9.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 486 |
+
"layers.9.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 487 |
+
"layers.9.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 488 |
+
"layers.9.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 489 |
+
"layers.9.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 490 |
+
"layers.9.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 491 |
+
"layers.9.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 492 |
+
"noise_refiner.0.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 493 |
+
"noise_refiner.0.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 494 |
+
"noise_refiner.0.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 495 |
+
"noise_refiner.0.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 496 |
+
"noise_refiner.0.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 497 |
+
"noise_refiner.0.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 498 |
+
"noise_refiner.0.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 499 |
+
"noise_refiner.0.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 500 |
+
"noise_refiner.0.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 501 |
+
"noise_refiner.0.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 502 |
+
"noise_refiner.0.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 503 |
+
"noise_refiner.0.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 504 |
+
"noise_refiner.0.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 505 |
+
"noise_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 506 |
+
"noise_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 507 |
+
"noise_refiner.1.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 508 |
+
"noise_refiner.1.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 509 |
+
"noise_refiner.1.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 510 |
+
"noise_refiner.1.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 511 |
+
"noise_refiner.1.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 512 |
+
"noise_refiner.1.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 513 |
+
"noise_refiner.1.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 514 |
+
"noise_refiner.1.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 515 |
+
"noise_refiner.1.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 516 |
+
"noise_refiner.1.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 517 |
+
"noise_refiner.1.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 518 |
+
"noise_refiner.1.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 519 |
+
"noise_refiner.1.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 520 |
+
"noise_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 521 |
+
"noise_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 522 |
+
"t_embedder.mlp.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 523 |
+
"t_embedder.mlp.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 524 |
+
"t_embedder.mlp.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 525 |
+
"t_embedder.mlp.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
|
| 526 |
+
"x_pad_token": "diffusion_pytorch_model-00001-of-00002.safetensors"
|
| 527 |
+
}
|
| 528 |
+
}
|
vae/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.37.1",
|
| 4 |
+
"_name_or_path": "/home/user/.cache/huggingface/hub/models--Tongyi-MAI--Z-Image-Turbo/snapshots/f332072aa78be7aecdf3ee76d5c247082da564a6/vae",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"block_out_channels": [
|
| 7 |
+
128,
|
| 8 |
+
256,
|
| 9 |
+
512,
|
| 10 |
+
512
|
| 11 |
+
],
|
| 12 |
+
"down_block_types": [
|
| 13 |
+
"DownEncoderBlock2D",
|
| 14 |
+
"DownEncoderBlock2D",
|
| 15 |
+
"DownEncoderBlock2D",
|
| 16 |
+
"DownEncoderBlock2D"
|
| 17 |
+
],
|
| 18 |
+
"force_upcast": true,
|
| 19 |
+
"in_channels": 3,
|
| 20 |
+
"latent_channels": 16,
|
| 21 |
+
"latents_mean": null,
|
| 22 |
+
"latents_std": null,
|
| 23 |
+
"layers_per_block": 2,
|
| 24 |
+
"mid_block_add_attention": true,
|
| 25 |
+
"norm_num_groups": 32,
|
| 26 |
+
"out_channels": 3,
|
| 27 |
+
"sample_size": 1024,
|
| 28 |
+
"scaling_factor": 0.3611,
|
| 29 |
+
"shift_factor": 0.1159,
|
| 30 |
+
"up_block_types": [
|
| 31 |
+
"UpDecoderBlock2D",
|
| 32 |
+
"UpDecoderBlock2D",
|
| 33 |
+
"UpDecoderBlock2D",
|
| 34 |
+
"UpDecoderBlock2D"
|
| 35 |
+
],
|
| 36 |
+
"use_post_quant_conv": false,
|
| 37 |
+
"use_quant_conv": false
|
| 38 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5b59a26851551b67ae1fe58d32e76486e1e812def4696a4bea97f16604d40a3
|
| 3 |
+
size 167666902
|
vlm_judge/chat_template.jinja
ADDED
|
@@ -0,0 +1,263 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- macro format_parameters(properties, required) -%}
|
| 2 |
+
{%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
|
| 3 |
+
{%- set ns = namespace(found_first=false) -%}
|
| 4 |
+
{%- for key, value in properties | dictsort -%}
|
| 5 |
+
{%- set add_comma = false -%}
|
| 6 |
+
{%- if key not in standard_keys -%}
|
| 7 |
+
{%- if ns.found_first %},{% endif -%}
|
| 8 |
+
{%- set ns.found_first = true -%}
|
| 9 |
+
{{ key }}:{
|
| 10 |
+
{%- if value['description'] -%}
|
| 11 |
+
description:<|"|>{{ value['description'] }}<|"|>
|
| 12 |
+
{%- set add_comma = true -%}
|
| 13 |
+
{%- endif -%}
|
| 14 |
+
{%- if value['nullable'] %}
|
| 15 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 16 |
+
nullable:true
|
| 17 |
+
{%- endif -%}
|
| 18 |
+
{%- if value['type'] | upper == 'STRING' -%}
|
| 19 |
+
{%- if value['enum'] -%}
|
| 20 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 21 |
+
enum:{{ format_argument(value['enum']) }}
|
| 22 |
+
{%- endif -%}
|
| 23 |
+
{%- elif value['type'] | upper == 'OBJECT' -%}
|
| 24 |
+
,properties:{
|
| 25 |
+
{%- if value['properties'] is defined and value['properties'] is mapping -%}
|
| 26 |
+
{{- format_parameters(value['properties'], value['required'] | default([])) -}}
|
| 27 |
+
{%- elif value is mapping -%}
|
| 28 |
+
{{- format_parameters(value, value['required'] | default([])) -}}
|
| 29 |
+
{%- endif -%}
|
| 30 |
+
}
|
| 31 |
+
{%- if value['required'] -%}
|
| 32 |
+
,required:[
|
| 33 |
+
{%- for item in value['required'] | default([]) -%}
|
| 34 |
+
<|"|>{{- item -}}<|"|>
|
| 35 |
+
{%- if not loop.last %},{% endif -%}
|
| 36 |
+
{%- endfor -%}
|
| 37 |
+
]
|
| 38 |
+
{%- endif -%}
|
| 39 |
+
{%- elif value['type'] | upper == 'ARRAY' -%}
|
| 40 |
+
{%- if value['items'] is mapping and value['items'] -%}
|
| 41 |
+
,items:{
|
| 42 |
+
{%- set ns_items = namespace(found_first=false) -%}
|
| 43 |
+
{%- for item_key, item_value in value['items'] | dictsort -%}
|
| 44 |
+
{%- if item_value is not none -%}
|
| 45 |
+
{%- if ns_items.found_first %},{% endif -%}
|
| 46 |
+
{%- set ns_items.found_first = true -%}
|
| 47 |
+
{%- if item_key == 'properties' -%}
|
| 48 |
+
properties:{
|
| 49 |
+
{%- if item_value is mapping -%}
|
| 50 |
+
{{- format_parameters(item_value, value['items']['required'] | default([])) -}}
|
| 51 |
+
{%- endif -%}
|
| 52 |
+
}
|
| 53 |
+
{%- elif item_key == 'required' -%}
|
| 54 |
+
required:[
|
| 55 |
+
{%- for req_item in item_value -%}
|
| 56 |
+
<|"|>{{- req_item -}}<|"|>
|
| 57 |
+
{%- if not loop.last %},{% endif -%}
|
| 58 |
+
{%- endfor -%}
|
| 59 |
+
]
|
| 60 |
+
{%- elif item_key == 'type' -%}
|
| 61 |
+
{%- if item_value is string -%}
|
| 62 |
+
type:{{ format_argument(item_value | upper) }}
|
| 63 |
+
{%- else -%}
|
| 64 |
+
type:{{ format_argument(item_value | map('upper') | list) }}
|
| 65 |
+
{%- endif -%}
|
| 66 |
+
{%- else -%}
|
| 67 |
+
{{ item_key }}:{{ format_argument(item_value) }}
|
| 68 |
+
{%- endif -%}
|
| 69 |
+
{%- endif -%}
|
| 70 |
+
{%- endfor -%}
|
| 71 |
+
}
|
| 72 |
+
{%- endif -%}
|
| 73 |
+
{%- endif -%}
|
| 74 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 75 |
+
type:<|"|>{{ value['type'] | upper }}<|"|>}
|
| 76 |
+
{%- endif -%}
|
| 77 |
+
{%- endfor -%}
|
| 78 |
+
{%- endmacro -%}
|
| 79 |
+
{%- macro format_function_declaration(tool_data) -%}
|
| 80 |
+
declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
|
| 81 |
+
{%- set params = tool_data['function']['parameters'] -%}
|
| 82 |
+
{%- if params -%}
|
| 83 |
+
,parameters:{
|
| 84 |
+
{%- if params['properties'] -%}
|
| 85 |
+
properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
|
| 86 |
+
{%- endif -%}
|
| 87 |
+
{%- if params['required'] -%}
|
| 88 |
+
required:[
|
| 89 |
+
{%- for item in params['required'] -%}
|
| 90 |
+
<|"|>{{- item -}}<|"|>
|
| 91 |
+
{{- ',' if not loop.last -}}
|
| 92 |
+
{%- endfor -%}
|
| 93 |
+
],
|
| 94 |
+
{%- endif -%}
|
| 95 |
+
{%- if params['type'] -%}
|
| 96 |
+
type:<|"|>{{- params['type'] | upper -}}<|"|>}
|
| 97 |
+
{%- endif -%}
|
| 98 |
+
{%- endif -%}
|
| 99 |
+
{%- if 'response' in tool_data['function'] -%}
|
| 100 |
+
{%- set response_declaration = tool_data['function']['response'] -%}
|
| 101 |
+
,response:{
|
| 102 |
+
{%- if response_declaration['description'] -%}
|
| 103 |
+
description:<|"|>{{- response_declaration['description'] -}}<|"|>,
|
| 104 |
+
{%- endif -%}
|
| 105 |
+
{%- if response_declaration['type'] | upper == 'OBJECT' -%}
|
| 106 |
+
type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
|
| 107 |
+
{%- endif -%}
|
| 108 |
+
{%- endif -%}
|
| 109 |
+
}
|
| 110 |
+
{%- endmacro -%}
|
| 111 |
+
{%- macro format_argument(argument, escape_keys=True) -%}
|
| 112 |
+
{%- if argument is string -%}
|
| 113 |
+
{{- '<|"|>' + argument + '<|"|>' -}}
|
| 114 |
+
{%- elif argument is boolean -%}
|
| 115 |
+
{{- 'true' if argument else 'false' -}}
|
| 116 |
+
{%- elif argument is mapping -%}
|
| 117 |
+
{{- '{' -}}
|
| 118 |
+
{%- set ns = namespace(found_first=false) -%}
|
| 119 |
+
{%- for key, value in argument | dictsort -%}
|
| 120 |
+
{%- if ns.found_first %},{% endif -%}
|
| 121 |
+
{%- set ns.found_first = true -%}
|
| 122 |
+
{%- if escape_keys -%}
|
| 123 |
+
{{- '<|"|>' + key + '<|"|>' -}}
|
| 124 |
+
{%- else -%}
|
| 125 |
+
{{- key -}}
|
| 126 |
+
{%- endif -%}
|
| 127 |
+
:{{- format_argument(value, escape_keys=escape_keys) -}}
|
| 128 |
+
{%- endfor -%}
|
| 129 |
+
{{- '}' -}}
|
| 130 |
+
{%- elif argument is sequence -%}
|
| 131 |
+
{{- '[' -}}
|
| 132 |
+
{%- for item in argument -%}
|
| 133 |
+
{{- format_argument(item, escape_keys=escape_keys) -}}
|
| 134 |
+
{%- if not loop.last %},{% endif -%}
|
| 135 |
+
{%- endfor -%}
|
| 136 |
+
{{- ']' -}}
|
| 137 |
+
{%- else -%}
|
| 138 |
+
{{- argument -}}
|
| 139 |
+
{%- endif -%}
|
| 140 |
+
{%- endmacro -%}
|
| 141 |
+
{%- macro strip_thinking(text) -%}
|
| 142 |
+
{%- set ns = namespace(result='') -%}
|
| 143 |
+
{%- for part in text.split('<channel|>') -%}
|
| 144 |
+
{%- if '<|channel>' in part -%}
|
| 145 |
+
{%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
|
| 146 |
+
{%- else -%}
|
| 147 |
+
{%- set ns.result = ns.result + part -%}
|
| 148 |
+
{%- endif -%}
|
| 149 |
+
{%- endfor -%}
|
| 150 |
+
{{- ns.result | trim -}}
|
| 151 |
+
{%- endmacro -%}
|
| 152 |
+
|
| 153 |
+
{%- set ns = namespace(prev_message_type=None) -%}
|
| 154 |
+
{%- set loop_messages = messages -%}
|
| 155 |
+
{{ bos_token }}
|
| 156 |
+
{#- Handle System/Tool Definitions Block -#}
|
| 157 |
+
{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
|
| 158 |
+
{{- '<|turn>system\n' -}}
|
| 159 |
+
|
| 160 |
+
{#- Inject Thinking token at the very top of the FIRST system turn -#}
|
| 161 |
+
{%- if enable_thinking is defined and enable_thinking -%}
|
| 162 |
+
{{- '<|think|>' -}}
|
| 163 |
+
{%- set ns.prev_message_type = 'think' -%}
|
| 164 |
+
{%- endif -%}
|
| 165 |
+
|
| 166 |
+
{%- if messages[0]['role'] in ['system', 'developer'] -%}
|
| 167 |
+
{{- messages[0]['content'] | trim -}}
|
| 168 |
+
{%- set loop_messages = messages[1:] -%}
|
| 169 |
+
{%- endif -%}
|
| 170 |
+
|
| 171 |
+
{%- if tools -%}
|
| 172 |
+
{%- for tool in tools %}
|
| 173 |
+
{{- '<|tool>' -}}
|
| 174 |
+
{{- format_function_declaration(tool) | trim -}}
|
| 175 |
+
{{- '<tool|>' -}}
|
| 176 |
+
{%- endfor %}
|
| 177 |
+
{%- set ns.prev_message_type = 'tool' -%}
|
| 178 |
+
{%- endif -%}
|
| 179 |
+
|
| 180 |
+
{{- '<turn|>\n' -}}
|
| 181 |
+
{%- endif %}
|
| 182 |
+
|
| 183 |
+
{#- Loop through messages -#}
|
| 184 |
+
{%- for message in loop_messages -%}
|
| 185 |
+
{%- set ns.prev_message_type = None -%}
|
| 186 |
+
{%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
|
| 187 |
+
{{- '<|turn>' + role + '\n' }}
|
| 188 |
+
|
| 189 |
+
{%- if message['tool_calls'] -%}
|
| 190 |
+
{%- for tool_call in message['tool_calls'] -%}
|
| 191 |
+
{%- set function = tool_call['function'] -%}
|
| 192 |
+
{{- '<|tool_call>call:' + function['name'] + '{' -}}
|
| 193 |
+
{%- if function['arguments'] is mapping -%}
|
| 194 |
+
{%- set ns_args = namespace(found_first=false) -%}
|
| 195 |
+
{%- for key, value in function['arguments'] | dictsort -%}
|
| 196 |
+
{%- if ns_args.found_first %},{% endif -%}
|
| 197 |
+
{%- set ns_args.found_first = true -%}
|
| 198 |
+
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
| 199 |
+
{%- endfor -%}
|
| 200 |
+
{%- elif function['arguments'] is string -%}
|
| 201 |
+
{{- function['arguments'] -}}
|
| 202 |
+
{%- endif -%}
|
| 203 |
+
{{- '}<tool_call|>' -}}
|
| 204 |
+
{%- endfor -%}
|
| 205 |
+
{%- set ns.prev_message_type = 'tool_call' -%}
|
| 206 |
+
{%- endif -%}
|
| 207 |
+
|
| 208 |
+
{%- if message['tool_responses'] -%}
|
| 209 |
+
{#- Tool Response handling -#}
|
| 210 |
+
{%- for tool_response in message['tool_responses'] -%}
|
| 211 |
+
{{- '<|tool_response>' -}}
|
| 212 |
+
{%- if tool_response['response'] is mapping -%}
|
| 213 |
+
{{- 'response:' + tool_response['name'] | default('unknown') + '{' -}}
|
| 214 |
+
{%- for key, value in tool_response['response'] | dictsort -%}
|
| 215 |
+
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
| 216 |
+
{%- if not loop.last %},{% endif -%}
|
| 217 |
+
{%- endfor -%}
|
| 218 |
+
{{- '}' -}}
|
| 219 |
+
{%- else -%}
|
| 220 |
+
{{- 'response:' + tool_response['name'] | default('unknown') + '{value:' + format_argument(tool_response['response'], escape_keys=False) + '}' -}}
|
| 221 |
+
{%- endif -%}
|
| 222 |
+
{{- '<tool_response|>' -}}
|
| 223 |
+
{%- endfor -%}
|
| 224 |
+
{%- set ns.prev_message_type = 'tool_response' -%}
|
| 225 |
+
{%- endif -%}
|
| 226 |
+
|
| 227 |
+
{%- if message['content'] is string -%}
|
| 228 |
+
{%- if role == 'model' -%}
|
| 229 |
+
{{- strip_thinking(message['content']) -}}
|
| 230 |
+
{%- else -%}
|
| 231 |
+
{{- message['content'] | trim -}}
|
| 232 |
+
{%- endif -%}
|
| 233 |
+
{%- elif message['content'] is sequence -%}
|
| 234 |
+
{%- for item in message['content'] -%}
|
| 235 |
+
{%- if item['type'] == 'text' -%}
|
| 236 |
+
{%- if role == 'model' -%}
|
| 237 |
+
{{- strip_thinking(item['text']) -}}
|
| 238 |
+
{%- else -%}
|
| 239 |
+
{{- item['text'] | trim -}}
|
| 240 |
+
{%- endif -%}
|
| 241 |
+
{%- elif item['type'] == 'image' -%}
|
| 242 |
+
{{- '\n\n<|image|>\n\n' -}}
|
| 243 |
+
{%- set ns.prev_message_type = 'image' -%}
|
| 244 |
+
{%- elif item['type'] == 'audio' -%}
|
| 245 |
+
{{- '<|audio|>' -}}
|
| 246 |
+
{%- set ns.prev_message_type = 'audio' -%}
|
| 247 |
+
{%- elif item['type'] == 'video' -%}
|
| 248 |
+
{{- '\n\n<|video|>\n\n' -}}
|
| 249 |
+
{%- set ns.prev_message_type = 'video' -%}
|
| 250 |
+
{%- endif -%}
|
| 251 |
+
{%- endfor -%}
|
| 252 |
+
{%- endif -%}
|
| 253 |
+
|
| 254 |
+
{%- if not (message['tool_responses'] and not message['content']) -%}
|
| 255 |
+
{{- '<turn|>\n' -}}
|
| 256 |
+
{%- endif -%}
|
| 257 |
+
{%- endfor -%}
|
| 258 |
+
|
| 259 |
+
{%- if add_generation_prompt -%}
|
| 260 |
+
{%- if ns.prev_message_type != 'tool_response' -%}
|
| 261 |
+
{{- '<|turn>model\n' -}}
|
| 262 |
+
{%- endif -%}
|
| 263 |
+
{%- endif -%}
|
vlm_judge/config.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma4ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"audio_token_id": 258881,
|
| 6 |
+
"boa_token_id": 256000,
|
| 7 |
+
"boi_token_id": 255999,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eoa_token_id": 258883,
|
| 10 |
+
"eoa_token_index": 258883,
|
| 11 |
+
"eoi_token_id": 258882,
|
| 12 |
+
"eos_token_id": [
|
| 13 |
+
1,
|
| 14 |
+
106
|
| 15 |
+
],
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"model_type": "gemma4",
|
| 18 |
+
"text_config": {
|
| 19 |
+
"attention_bias": false,
|
| 20 |
+
"attention_dropout": 0.0,
|
| 21 |
+
"attention_k_eq_v": false,
|
| 22 |
+
"bos_token_id": 2,
|
| 23 |
+
"dtype": "bfloat16",
|
| 24 |
+
"enable_moe_block": false,
|
| 25 |
+
"eos_token_id": 1,
|
| 26 |
+
"expert_intermediate_size": null,
|
| 27 |
+
"final_logit_softcapping": 30.0,
|
| 28 |
+
"global_head_dim": 512,
|
| 29 |
+
"head_dim": 256,
|
| 30 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 31 |
+
"hidden_size": 2560,
|
| 32 |
+
"hidden_size_per_layer_input": 256,
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 10240,
|
| 35 |
+
"layer_types": [
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"sliding_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"sliding_attention",
|
| 62 |
+
"sliding_attention",
|
| 63 |
+
"sliding_attention",
|
| 64 |
+
"sliding_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"sliding_attention",
|
| 67 |
+
"sliding_attention",
|
| 68 |
+
"sliding_attention",
|
| 69 |
+
"sliding_attention",
|
| 70 |
+
"sliding_attention",
|
| 71 |
+
"full_attention",
|
| 72 |
+
"sliding_attention",
|
| 73 |
+
"sliding_attention",
|
| 74 |
+
"sliding_attention",
|
| 75 |
+
"sliding_attention",
|
| 76 |
+
"sliding_attention",
|
| 77 |
+
"full_attention"
|
| 78 |
+
],
|
| 79 |
+
"max_position_embeddings": 131072,
|
| 80 |
+
"model_type": "gemma4_text",
|
| 81 |
+
"num_attention_heads": 8,
|
| 82 |
+
"num_experts": null,
|
| 83 |
+
"num_global_key_value_heads": null,
|
| 84 |
+
"num_hidden_layers": 42,
|
| 85 |
+
"num_key_value_heads": 2,
|
| 86 |
+
"num_kv_shared_layers": 18,
|
| 87 |
+
"pad_token_id": 0,
|
| 88 |
+
"rms_norm_eps": 1e-06,
|
| 89 |
+
"rope_parameters": {
|
| 90 |
+
"full_attention": {
|
| 91 |
+
"partial_rotary_factor": 0.25,
|
| 92 |
+
"rope_theta": 1000000.0,
|
| 93 |
+
"rope_type": "proportional"
|
| 94 |
+
},
|
| 95 |
+
"sliding_attention": {
|
| 96 |
+
"rope_theta": 10000.0,
|
| 97 |
+
"rope_type": "default"
|
| 98 |
+
}
|
| 99 |
+
},
|
| 100 |
+
"sliding_window": 512,
|
| 101 |
+
"tie_word_embeddings": true,
|
| 102 |
+
"top_k_experts": null,
|
| 103 |
+
"use_bidirectional_attention": null,
|
| 104 |
+
"use_cache": true,
|
| 105 |
+
"use_double_wide_mlp": false,
|
| 106 |
+
"vocab_size": 262144,
|
| 107 |
+
"vocab_size_per_layer_input": 262144
|
| 108 |
+
},
|
| 109 |
+
"tie_word_embeddings": true,
|
| 110 |
+
"transformers_version": "5.5.0.dev0",
|
| 111 |
+
"vision_soft_tokens_per_image": 280
|
| 112 |
+
}
|
vlm_judge/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1,
|
| 6 |
+
106,
|
| 7 |
+
50
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"temperature": 1.0,
|
| 11 |
+
"top_k": 64,
|
| 12 |
+
"top_p": 0.95,
|
| 13 |
+
"transformers_version": "5.5.0.dev0"
|
| 14 |
+
}
|
vlm_judge/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e366af4cd8a1652dc25b81cd76a74af9d8660ead4bad2408a66881c9fc83adb
|
| 3 |
+
size 15992595852
|
vlm_judge/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
|
| 3 |
+
size 32169626
|
vlm_judge/tokenizer_config.json
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_token": "<|audio|>",
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"boa_token": "<|audio>",
|
| 5 |
+
"boi_token": "<|image>",
|
| 6 |
+
"bos_token": "<bos>",
|
| 7 |
+
"eoa_token": "<audio|>",
|
| 8 |
+
"eoc_token": "<channel|>",
|
| 9 |
+
"eoi_token": "<image|>",
|
| 10 |
+
"eos_token": "<eos>",
|
| 11 |
+
"eot_token": "<turn|>",
|
| 12 |
+
"escape_token": "<|\"|>",
|
| 13 |
+
"etc_token": "<tool_call|>",
|
| 14 |
+
"etd_token": "<tool|>",
|
| 15 |
+
"etr_token": "<tool_response|>",
|
| 16 |
+
"extra_special_tokens": [
|
| 17 |
+
"<|video|>"
|
| 18 |
+
],
|
| 19 |
+
"image_token": "<|image|>",
|
| 20 |
+
"is_local": true,
|
| 21 |
+
"mask_token": "<mask>",
|
| 22 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
+
"model_specific_special_tokens": {
|
| 24 |
+
"audio_token": "<|audio|>",
|
| 25 |
+
"boa_token": "<|audio>",
|
| 26 |
+
"boi_token": "<|image>",
|
| 27 |
+
"eoa_token": "<audio|>",
|
| 28 |
+
"eoc_token": "<channel|>",
|
| 29 |
+
"eoi_token": "<image|>",
|
| 30 |
+
"eot_token": "<turn|>",
|
| 31 |
+
"escape_token": "<|\"|>",
|
| 32 |
+
"etc_token": "<tool_call|>",
|
| 33 |
+
"etd_token": "<tool|>",
|
| 34 |
+
"etr_token": "<tool_response|>",
|
| 35 |
+
"image_token": "<|image|>",
|
| 36 |
+
"soc_token": "<|channel>",
|
| 37 |
+
"sot_token": "<|turn>",
|
| 38 |
+
"stc_token": "<|tool_call>",
|
| 39 |
+
"std_token": "<|tool>",
|
| 40 |
+
"str_token": "<|tool_response>",
|
| 41 |
+
"think_token": "<|think|>"
|
| 42 |
+
},
|
| 43 |
+
"pad_token": "<pad>",
|
| 44 |
+
"padding_side": "left",
|
| 45 |
+
"processor_class": "Gemma4Processor",
|
| 46 |
+
"response_schema": {
|
| 47 |
+
"properties": {
|
| 48 |
+
"content": {
|
| 49 |
+
"type": "string"
|
| 50 |
+
},
|
| 51 |
+
"role": {
|
| 52 |
+
"const": "assistant"
|
| 53 |
+
},
|
| 54 |
+
"thinking": {
|
| 55 |
+
"type": "string"
|
| 56 |
+
},
|
| 57 |
+
"tool_calls": {
|
| 58 |
+
"items": {
|
| 59 |
+
"properties": {
|
| 60 |
+
"function": {
|
| 61 |
+
"properties": {
|
| 62 |
+
"arguments": {
|
| 63 |
+
"additionalProperties": {},
|
| 64 |
+
"type": "object",
|
| 65 |
+
"x-parser": "gemma4-tool-call"
|
| 66 |
+
},
|
| 67 |
+
"name": {
|
| 68 |
+
"type": "string"
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"type": "object",
|
| 72 |
+
"x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
|
| 73 |
+
},
|
| 74 |
+
"type": {
|
| 75 |
+
"const": "function"
|
| 76 |
+
}
|
| 77 |
+
},
|
| 78 |
+
"type": "object"
|
| 79 |
+
},
|
| 80 |
+
"type": "array",
|
| 81 |
+
"x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
|
| 82 |
+
}
|
| 83 |
+
},
|
| 84 |
+
"type": "object",
|
| 85 |
+
"x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
|
| 86 |
+
},
|
| 87 |
+
"soc_token": "<|channel>",
|
| 88 |
+
"sot_token": "<|turn>",
|
| 89 |
+
"stc_token": "<|tool_call>",
|
| 90 |
+
"std_token": "<|tool>",
|
| 91 |
+
"str_token": "<|tool_response>",
|
| 92 |
+
"think_token": "<|think|>",
|
| 93 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 94 |
+
"unk_token": "<unk>"
|
| 95 |
+
}
|