avlp12
/

Krea-2-Turbo-Alis-MLX-8bit

8-bit precision

Model card Files Files and versions

Krea-2-Turbo-Alis-MLX-8bit

14.3 GB

Ctrl+K

Ctrl+K

1 contributor

History: 36 commits

avlp12's picture

docs: link parent collection

9fc879f verified 3 months ago

assets
Upload folder using huggingface_hub 3 months ago
krea2
Pure-MLX NSFW safety filter (torch-free, validated 2e-7 vs PyTorch) + review hardening 3 months ago
samples
Upload folder using huggingface_hub 3 months ago
.gitattributes

1.86 kB
Upload folder using huggingface_hub 3 months ago
LICENSE

14.6 kB
Upload folder using huggingface_hub 3 months ago
NOTICE

1.09 kB
Upload folder using huggingface_hub 3 months ago
README.md

8.96 kB
docs: link parent collection 3 months ago
VALIDATION_LOG.txt

1.58 kB
Re-validate quant on 12 prompts (n=96): honest numbers + updated log 3 months ago
app.py

4.91 kB
Pure-MLX NSFW safety filter (torch-free, validated 2e-7 vs PyTorch) + review hardening 3 months ago
config.json

507 Bytes
Add config.json so the Hub can count downloads (library_name mlx has no countDownloads rule → falls back to config.json) 3 months ago
generate.py

2.62 kB
Harden per code review: strict loads, input validation, safe downloads, OOM-safe model switch 3 months ago
requirements.txt

391 Bytes
Pure-MLX NSFW safety filter (torch-free, validated 2e-7 vs PyTorch) + review hardening 3 months ago
transformer_8bit.safetensors

14.2 GB
xet

Upload folder using huggingface_hub 3 months ago