Qwen3.5-9B-Uncensored-HauhauCS-Aggressive
9BQwenuncensored
from Qwen/Qwen3.5-9B
↓ 702.4K♥ 2.4K86 repos
MOSS-Image-Text-Encoder-Heretic
MOSS-Image-Text-Encoder-Heretic is a Heretic-ablated variant of Qwen/Qwen3.5-9B, published on Hugging Face by pottokao. It is apache-2.0 licence. It is distributed across 4 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 5.6K downloads.
Specification
- Model name
- MOSS-Image-Text-Encoder-Heretic
- Source repository
- pottokao/MOSS-Image-Text-Encoder-Heretic
- Base model
- Qwen/Qwen3.5-9B
- Publisher
- pottokao
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- apache-2.0
- Task
- Image text to text
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix)
- First indexed
- 23 Oct 2026
- Last updated
- 25 Oct 2026
Ablation technique
How MOSS-Image-Text-Encoder-Heretic was modified, and what that implies.
Heretic
Automated directional ablation via the Heretic toolchain, which searches for the refusal direction and applies it with a KL-divergence budget so general capability is preserved.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“A decensored Qwen3.5-9B, made to be the text encoder and the prompt enhancer of MOSS-Image.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/MOSS-Image-Text-Encoder-Heretic-GGUF --local-dir ./moss-image-text-encoder-heretic
llama-cli -m ./moss-image-text-encoder-heretic/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "pottokao/MOSS-Image-Text-Encoder-Heretic"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve pottokao/MOSS-Image-Text-Encoder-Heretic --trust-remote-codeDownloads and variants (3)
Every published repository of MOSS-Image-Text-Encoder-Heretic, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mradermacher/MOSS-Image-Text-Encoder-Heretic-GGUF | GGUF | 3K |
| mradermacher/MOSS-Image-Text-Encoder-Heretic-i1-GGUF | GGUF (imatrix) | 2.3K |
| pottokao/MOSS-Image-Text-Encoder-Hereticsource | Transformers | 368 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- MOSS-Image-Text-Encoder-Heretic will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is apache-2.0, but the terms that bind you are Qwen/Qwen3.5-9B’s — a re-release cannot grant more than its parent.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for MOSS-Image-Text-Encoder-Heretic is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with pottokao, and does not independently verify publisher claims. See responsible use.