Hugging Face's logo

Basher17
/
Qwen3.6-27B-heretic-v2-oQ4e-mtp

Image-Text-to-Text
MLX
Safetensors
qwen3_5
heretic
uncensored
decensored
abliterated
mpoa
mtp
conversational
4-bit precision
Model card Files
xet
 Community
Basher17 commited on
Commit
d3a9b4a
·
verified ·
1 Parent(s): 9ddc3c4

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -25
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- library_name: transformers
3
  license: apache-2.0
4
  license_link: https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE
5
  pipeline_tag: image-text-to-text
@@ -11,36 +11,13 @@ tags:
11
  - mpoa
12
  - mtp
13
  base_model:
14
- - Qwen/Qwen3.6-27B
15
- ---
16
- <div style="background-color: #ff4444; color: white; padding: 20px; border-radius: 10px; text-align: center; margin: 20px 0;">
17
- <h2 style="color: white; margin: 0 0 10px 0;">🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨</h2>
18
- <p style="font-size: 18px; margin: 0 0 15px 0;">I can no longer upload new models unless I can cover the cost of additional storage.<br>I host <b>70+ free models</b> as an independent contributor and this work is unpaid.<br><b>Without your support, no more new models can be uploaded.</b></p>
19
- <p style="font-size: 20px; margin: 0;">
20
- <a href="https://patreon.com/LLMfan46" style="color: white; text-decoration: underline;">🎉 Patreon (Monthly)</a> &nbsp;|&nbsp;
21
- <a href="https://ko-fi.com/llmfan46" style="color: white; text-decoration: underline;">☕ Ko-fi (One-time)</a>
22
- </p>
23
- <p style="font-size: 16px; margin: 10px 0 0 0;">Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone.</p>
24
- </div>
25
-
26
  ---
27
 
28
  This is the full model with the 15 MTPs all intacts.
29
 
30
  ### **94% fewer refusals** (6/100 Uncensored vs 92/100 Original) while preserving model quality (0.0021 KL divergence).
31
 
32
- ## ❤️ Support My Work
33
- Creating these models takes significant time, work and compute. If you find them useful consider supporting me:
34
-
35
- ![image/png](https://huggingface.co/llmfan46/Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B-ultra-uncensored-heretic-v1/resolve/main/waifu001.webp)
36
-
37
- | Platform | Link | What you get |
38
- |----------|------|--------------|
39
- | 🎉 Patreon | [Monthly support](https://patreon.com/LLMfan46) | Priority model requests |
40
- | ☕ Ko-fi | [One-time tip](https://ko-fi.com/llmfan46) | My eternal gratitude |
41
-
42
- Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.
43
-
44
  -----
45
 
46
  # This is a decensored version of [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B), made using [Heretic](https://github.com/p-e-w/heretic) v1.3.0 with a variant of the [Magnitude-Preserving Orthogonal Ablation (MPOA)](https://huggingface.co/blog/grimjim/norm-preserving-biprojected-abliteration) method
 
1
  ---
2
+ library_name: mlx
3
  license: apache-2.0
4
  license_link: https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE
5
  pipeline_tag: image-text-to-text
 
11
  - mpoa
12
  - mtp
13
  base_model:
14
+ - llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved
 
 
 
 
 
 
 
 
 
 
 
15
  ---
16
 
17
  This is the full model with the 15 MTPs all intacts.
18
 
19
  ### **94% fewer refusals** (6/100 Uncensored vs 92/100 Original) while preserving model quality (0.0021 KL divergence).
20
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  -----
22
 
23
  # This is a decensored version of [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B), made using [Heretic](https://github.com/p-e-w/heretic) v1.3.0 with a variant of the [Magnitude-Preserving Orthogonal Ablation (MPOA)](https://huggingface.co/blog/grimjim/norm-preserving-biprojected-abliteration) method