Downloads · 30 days
0
Qwen3VL-4B-Instruct-Heretic
tuanlai001/Qwen3VL-4B-Instruct-Heretic
Qwen3VL-4B-Instruct-Heretic is a machine learning model from tuanlai001. 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.
This model is an uncensored (heretic) text encoder for Krea 2 Turbo & Raw.
Access
Public
Updated Jul 5, 2026
Repo size
24.5 GB
Likes
7
Trending 1
Repo makeup
Click a slice to open those files.
.safetensors24.5 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 4, 2026
- Updated
- Jul 5, 2026
- SHA
- f198b9c6
Base models
Model card
From the Hugging Face model README
This model is an uncensored (heretic) text encoder for Krea 2 Turbo & Raw.
Available in FP8,MXFP8,INT 8 CONVROT and BF16.
🛠️ Training & Quantization Details
<b>·Uncensoring Tool:</b> heretic
<b>·Checkpoint Selection: </b> Manually selected from 200 trials, achieving a refusal rate of 3% (3/100) and a KL Divergence of 0.056679.
<b>·Quantization Tool:</b> convert_to_quant
- License
- apache-2.0
- Created
- Jul 4, 2026
- Updated
- Jul 5, 2026