Downloads · 30 days
0
Qwen-Image-Cyrillic-Config
777Radik/Qwen-Image-Cyrillic-Config
Qwen-Image-Cyrillic-Config is a machine learning model from 777Radik. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Access
Public
Updated Jul 25, 2026
Repo size
829 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.jpg1.7 MB · 88%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026
- SHA
- 5a880c7c
Model card
From the Hugging Face model README
Qwen-Image Cyrillic FP8 reproducibility configuration
Configuration and proof bundle for:
777Radik/Qwen-Image-2512-FP8-E4M3FN777Radik/Qwen-Image-Cyrillic-ControlNet
Files:
training-config.json— ControlNet training inputs, hashes, and hyperparametersruntime-config.json— component repositories, precision, generation, and retry settingsbenchmark-config.json— immutable heldout100 command and quality gatesbenchmark-results.json— BF16/FP8 metrics and manual audit resultquantization-manifest.json— per-shard source/output hashescontrolnet_benchmark.py— exact generation harnesscontrolnet_accuracy.py— OCR/glyph diagnostic and contact-sheet generatorverify_hf_release.py— remote LFS size/SHA-256 and required-file verifier
The accepted production result is 99/100 manual exact Cyrillic on the fixed benchmark. FP8 regression is zero: all 100 quantized outputs are byte-for-byte identical to the source-storage run.
- License
- apache-2.0
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026