license: apache-2.0
language:
- en
pipeline_tag: image-text-to-text
library_name: transformers
tags: - finetune
- unsloth
- thinking
- reasoning
- abliterated
- heretic
- uncensored
- tiiny
- tiiny-forge
base_model: - Qwen/Qwen3.5-9B
base_model_relation: finetune
Repackaged for Tiiny Pocket import. A copy of DavidAU/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-X8b at
f304bcd977ee, made by tiiny-forge so the Tiiny's Hugging Face import accepts it as a fine-tune of the store modelQwen/Qwen3.5-9B. The weights are unchanged. Changes:
- merges.txt: copied from Qwen/Qwen3.5-9B
- model card base_model: None -> ['Qwen/Qwen3.5-9B']
Lineage. The source card names no base model. Its norm and embedding weights are nearest to Qwen/Qwen3.5-9B (relative distance ~0.001, against ~0.003 for Qwen/Qwen3.5-9B-Base).
[DavidAU] FOLLOW | ALL MODELS | COLLECTIONS | TRENDING | FAQs | SUPPORT
| Buy Me A Coffee (😁)
[repo card updates pending]
Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-X8b
It is really smart AND Uncensored AND has "Claude" thinking.
BENCHMARKS by Nightmedia:
arc-c arc/e boolq hswag obkqa piqa wino
Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-X8b [instruct mode]
mxfp8 0.637,0.835,0.889,...
Qwen3.5-9B-Instruct
mxfp8 0.571,0.719,0.895,0.683,0.426,0.770,0.671