← back to catalog · registered 2026-08-22 13:56

ross-dev/sexyGPT-Uncensored

Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/ross-dev%2FsexyGPT-Uncensored"
Response includes
  • classification m-uncensored
  • files 11
  • hub_downloads_all_time 13,355
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
13K
1K last 30d - stable
Likes
34
Descendants
3
in 3 direct forks
Model age
2.8y ago
created 2024-01-08
Downloads over time
Now14.1K→from156↑8,943%
05.2K10.3K15.5K156 on Jan 22, 202514.1K on Oct 11Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 22, 2025 → Oct 11 · 131 snapshots · spans 627 days

Genealogy 3 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Languages
es ar
Tags
flair pytorch safetensors gpt2 not-for-all-audiences Sex Taboo Teacher-student sex text-generation es ar license:apache-2.0
Total size
949 MB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-10-05 05:48

Files by quantization

Auxiliary files 11 files 951 MB
pytorch_model.bin 475 MB 701bb2b5 download
model.safetensors 475 MB 87eaef2d download
vocab.json 976 KB a15dd002 download
merges.txt 446 KB 226b0752 download
.gitattributes 1.48 KB a6344aac download
tokenizer_config.json 1.24 KB 28ce6cef download
config.json 907 B e2250bfb download
special_tokens_map.json 757 B c3357ea5 download
README.md 616 B 1ae23fb4 download
generation_config.json 119 B dc5f9a45 download
added_tokens.json 94.0 B ed32a3af download

README current version from Hugging Face


license: apache-2.0
language:

  • es
  • ar
    metrics:
  • character
    library_name: flair
    pipeline_tag: text-generation
    tags:
  • not-for-all-audiences
  • Sex
  • Taboo
  • Teacher-student sex

SexyGPT By Hooking AI

SexyGPT is a gpt2 model finetuned as an experiment on a private dirty talk dataset to test the behaviors of generative transformers.
The model tuned based on:

Boy Text: hey, what's up?

AI Text: ** some dirty answer **

Be advised,

The model have dirty talk. It is for research purposes only and not meant to be used in ANY production enviroment.

Thank you,

Hooking AI Team.

README history 7 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2025-10-05Update README.md (#5)38cdbd5616 B
    Loading...
  2. 2025-09-28Update README.md00f964e611 B
    Loading...
  3. 2025-09-28Update README.mdacd3e81616 B
    Loading...
  4. 2024-04-18Update README.md238a2aa459 B
    Loading...
  5. 2024-04-18Update README.md4bce945437 B
    Loading...
  6. 2024-04-18Update README.md79439b3408 B
    Loading...
  7. 2024-01-08initial commit112852228 B
    Loading...

Discussions 6 threads

  1. 2026-01-17PRUpdate config.jsonopen3 💬#6
    Loading...
  2. 2025-10-05PRUpdate README.mdmerged3 💬#5
    Loading...
  3. 2025-09-08PRHhouclosed1 💬#4
    Loading...
  4. 2024-11-26Optimal settingopen2 💬#3
    Loading...
  5. 2024-04-15PRUpdate README.mdopen3 💬#2
    Loading...
  6. 2024-04-15PRUpdate README.mdclosed1 💬#1
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration