Downloads · 30 days
20
18% of all-time downloads
Qwen3-VL-30B-A3B-Instruct-Heretic
catplusplus/Qwen3-VL-30B-A3B-Instruct-Heretic
Qwen3-VL-30B-A3B-Instruct-Heretic is a machine learning model from catplusplus. 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 has been uncensored using heretic and can generate outputs not suitable for all audiences. heretic's refusal numbers are meh, but it does not seem to actually refuse anything I ask on my own. If you want be…
All-time downloads
111
Public
Parameters
31.1B
62.1 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors62.1 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3_vl_moe
- Access
- Public
- Created
- Feb 6, 2026
- Updated
- Feb 6, 2026
- SHA
- 8de1793f
Base models
Model card
From the Hugging Face model README
This model has been uncensored using heretic and can generate outputs not suitable for all audiences. heretic's refusal numbers are meh, but it does not seem to actually refuse anything I ask on my own. If you want better numbers, try my thinking version of this model. Or better yet, patch heretic to target experts rather than just attention layers, I have not gotten to this yet.
Refusals: 64/100, KL divergence: 0.1316
Restoring model from trial 669...
- Parameters:
- direction_index = 23.52
- attn.o_proj.max_weight = 1.47
- attn.o_proj.max_weight_position = 28.97
- attn.o_proj.min_weight = 1.46
- attn.o_proj.min_weight_distance = 28.09
- Type
- qwen3_vl_moe
- License
- apache-2.0
- Created
- Feb 6, 2026
- Updated
- Feb 6, 2026