Downloads · 30 days
15
3% of all-time downloads
Qwen3-VL-30B-A3B-Thinking-Heretic
catplusplus/Qwen3-VL-30B-A3B-Thinking-Heretic
Qwen3-VL-30B-A3B-Thinking-Heretic is a image-text-to-text model from catplusplus. Use it for the image-text-to-text 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 processed with heretic 1.1.0 to reduce refusals. It can generate text not suitable for all audiences
All-time downloads
517
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
- Task
- Image-Text-to-Text
- License
- apache-2.0
- Model type
- qwen3_vl_moe
- Access
- Public
- Created
- Feb 3, 2026
- Updated
- Feb 3, 2026
- SHA
- 43457b13
Try a prompt
Base models
Model card
From the Hugging Face model README
This model has been processed with heretic 1.1.0 to reduce refusals. It can generate text not suitable for all audiences
I used --orthogonalize-direction --row-normalization FULL --full-normalization-lora-rank 5
heretic only found attention layers but this appears enough to have arbitary conversations with AI safety lectures in practice. Anecdotally model seems to think better generally.
Parameters: * direction_index = 28.60 * attn.o_proj.max_weight = 1.46 * attn.o_proj.max_weight_position = 32.05 * attn.o_proj.min_weight = 1.44 * attn.o_proj.min_weight_distance = 28.03 » [Trial 476] Refusals: 18/100, KL divergence: 0.0084
- Task
- Image-Text-to-Text
- Type
- qwen3_vl_moe
- License
- apache-2.0
- Created
- Feb 3, 2026
- Updated
- Feb 3, 2026