Downloads · 30 days
23
12% of all-time downloads
Qwen3.6-27B-MTP-heretic
Sabomako/Qwen3.6-27B-MTP-heretic
Qwen3.6-27B-MTP-heretic is a image-text-to-text model from Sabomako. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product.
All-time downloads
197
Public
Parameters
27.4B
55.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors55.6 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Model type
- qwen3_5
- Access
- Public
- Created
- May 18, 2026
- Updated
- May 18, 2026
- SHA
- 6bf26862
Try a prompt
Base models
Model card
From the Hugging Face model README
This is a decensored version of Qwen/Qwen3.6-27B, made using Heretic v1.3.0 with custom ORBA abliteration method
CoT prefix = "</think>\n\n"
Refusal classification via an LLM judge (Gemma-12B-IT-Heretic).
Performance
| Metric | This model | Original model (Qwen/Qwen3.6-27B) |
|---|---|---|
| KL divergence | 0.0511 | 0 (by definition) |
| Refusals | 0/100 | 100/100 |
- Task
- Image-Text-to-Text
- Type
- qwen3_5
- Featherless Ai
- live
- Created
- May 18, 2026
- Updated
- May 18, 2026