heterodoxin / AbliteratedOutTheBox
llama.cpp fork that abliterates at inference
Why this job: says: llama.cpp; topics: llama-cpp, inference
What it does
Measured on Qwen3-8B with a hand-validated response hidden-state probe (no string matching, no judge model), over held-out sets, with the edit read from the prompt at inference (no fit):
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 18 days ago
- Stars
- 170
- +8 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- C++
- 56% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 0% closed
- 1 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Aevonix / FlashAlign | 125 | 3 days ago | AGPL-3.0 | Linux |
| mybigday / llama.rn | 1,072 | today | MIT | No downloads |
| xorbitsai / inference | 9,647 | yesterday | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- C++ 56%
- C 16%
- Python 7%
- Cuda 5%
Topics
- abliteration
- ai
- inference
- llama-cpp
- llm
- llms
Project record
- JobLocal LLMs
- StatusNew to our list
- Commits4
- Forks16
- Watching4
- CreatedOct 21, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026