Downloads · 30 days
18
11% of all-time downloads
squid-merged-heretic
adoringmc/squid-merged-heretic
squid-merged-heretic is a image-text-to-text model from adoringmc. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
[!TIP] This model is reproducible! See the README in the reproduce directory for more information.
All-time downloads
162
Public
Parameters
7.9B
15.9 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors15.9 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- gemma4
- Access
- Public
- Created
- May 15, 2026
- Updated
- May 15, 2026
- SHA
- 5b82600d
Try a prompt
Base models
Model card
From the Hugging Face model README
This is a decensored version of adoringmc/squid-merged, made using Heretic v1.3.0
[!TIP] This model is reproducible!
See the README in the
reproducedirectory for more information.
Abliteration parameters
| Parameter | Value |
|---|---|
| direction_index | per layer |
| attn.o_proj.max_weight | 1.28 |
| attn.o_proj.max_weight_position | 29.79 |
| attn.o_proj.min_weight | 0.97 |
| attn.o_proj.min_weight_distance | 18.89 |
| mlp.down_proj.max_weight | 1.04 |
| mlp.down_proj.max_weight_position | 26.00 |
| mlp.down_proj.min_weight | 0.63 |
| mlp.down_proj.min_weight_distance | 21.07 |
Performance
| Metric | This model | Original model (adoringmc/squid-merged) |
|---|---|---|
| KL divergence | 0.2777 | 0 (by definition) |
| Refusals | 4/100 | 10/100 |
Uploaded finetuned model
- Developed by: adoringmc
- License: apache-2.0
- Finetuned from model : TrevorJS/gemma-4-E4B-it-uncensored
This gemma4 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- gemma4
- License
- apache-2.0
- Languages
- en
- Created
- May 15, 2026
- Updated
- May 15, 2026