Downloads · 30 days
13
15% of all-time downloads
Babsie/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking
Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking is a image-text-to-text model from Babsie. 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.
<h2Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking</h2
Downloads · 30 days
13
15% of all-time downloads
All-time downloads
86
Public
Parameters
27.4B
54.7 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors54.7 GB · 100%
From the Hugging Face model README
Yes... fully uncensored AND fine tuned lightly.
Freedom and brainpower.
Trained on different Heretic base, with different KLD/Refusals.
Model fine tune was used to finalize and "firm up" Heretic / uncensored changes.
The goal here was light, minor fixes rather than full / heavy fine tune.
That being said, the tuning still raised critical metrics.
This is Version 2, using "trohrbaugh" Heretic, which has a lower refusal rate, and tuning bumped up the metrics a bit more too.
This has also positively impacted "NEO-Coder Di-Matrix" (dual imatrix) GGUF quants as well (vs heretic/non heretic too).
https://huggingface.co/DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF
IN HOUSE BENCHMARKS [by Nightmedia]:
arc-c arc/e boolq hswag obkqa piqa wino
Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking
mxfp8 0.673,0.846,0.905... [instruct mode]
Qwen3.6-27B-Heretic-Uncensored-Finetune-Thinking
mxfp8 0.669,0.835,0.906,... [instruct mode]
---
BASE UNTUNED MODEL:
Qwen3.6-27B HERETIC (by llmfan46) [instruct mode]
mxfp8 0.644,0.788,0.902,...
Qwen3.6-27B (by Qwen) [instruct mode]
mxfp8 0.647,0.803,0.910,0.773,0.450,0.806,0.742
NOTE: Instruct mode will often test higher than "thinking" mode due to token usage in thinking and context limits.
Heretic Stats:
Metric This model Original model (Qwen/Qwen3.6-27B)
KL divergence 0.0469 0 (by definition)
Refusals 4/100 99/100
A KLD of .3 or lower is great, lower than this excellent.
KLD measures HERETIC vs Original model performance:
IE: How closely the Heretic version matchs in generation / token selection vs org model.
Q4KS, non imatrix, temp:1, rep pen: 1 [off]
There may be some loss of formatting from copy/paste.