orcarouter_GLM-5.3-Flash-Uncensored
Otheruncensored
from orcarouter/GLM-5.3-Flash-Uncensored-FP8
↓ 219.8K♥ 422 repos
sexyGPT-Uncensored
sexyGPT-Uncensored is a abliterated and uncensored variant of ross-dev/sexyGPT-Uncensored, published on Hugging Face by ross-dev. It is apache-2.0 licence. It is distributed across 9 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 5.5K downloads.
Specification
- Model name
- sexyGPT-Uncensored
- Source repository
- ross-dev/sexyGPT-Uncensored
- Base model
- ross-dev/sexyGPT-Uncensored
- Publisher
- ross-dev
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix)
- First indexed
- 8 Jan 2024
- Last updated
- 13 Jul 2026
Ablation technique
How sexyGPT-Uncensored was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
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
“SexyGPT is a gpt2 model finetuned as an experiment on a private dirty talk dataset to test the behaviors of generative transformers.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download tensorblock/sexyGPT-Uncensored-GGUF --local-dir ./sexygpt-uncensored
llama-cli -m ./sexygpt-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "ross-dev/sexyGPT-Uncensored"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve ross-dev/sexyGPT-Uncensored --trust-remote-codeDownloads and variants (8)
Every published repository of sexyGPT-Uncensored, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| ross-dev/sexyGPT-Uncensoredsource | Transformers | 4.1K |
| tensorblock/sexyGPT-Uncensored-GGUF | GGUF | 456 |
| Ayyystin/sexyGPT-Uncensored-Q4_0-GGUF | GGUF | 373 |
| mradermacher/sexyGPT-Uncensored-i1-GGUF | GGUF (imatrix) | 290 |
| mradermacher/sexyGPT-Uncensored-GGUF | GGUF | 202 |
| KACHOHAN/sexyGPT-Uncensored-GGUF | GGUF | 41 |
| simplemobilesystem/sexyGPT-Uncensored | Transformers | 1 |
| nicholaschesse/sexyGPT-Uncensored | Transformers | 0 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- sexyGPT-Uncensored 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.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- Declared licence is apache-2.0, but the terms that bind you are ross-dev/sexyGPT-Uncensored’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 sexyGPT-Uncensored is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with ross-dev, and does not independently verify publisher claims. See responsible use.