aboylabs/ai-agent-skills / skills/mlops/inference/obliteratus
obliteratus
UnverifiedOBLITERATUS: abliterate LLM refusals (diff-in-means).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.2 KB |
| references/analysis-modules.md | markdown | 6.1 KB |
| references/methods-guide.md | markdown | 6.6 KB |
| templates/abliteration-config.yaml | config | 1.2 KB |
| templates/analysis-study.yaml | config | 1.3 KB |
| templates/batch-abliteration.yaml | config | 1.2 KB |
templates/batch-abliteration.yaml
View on GitHub# OBLITERATUS Batch Abliteration Config
# Abliterate multiple models with the same method for comparison.
#
# Run each one sequentially:
# for model in models; do obliteratus obliterate $model --method informed; done
#
# Or use this as a reference for which models to process.
# Common settings
defaults:
method: "informed"
quantization: "4bit"
output_dir: "./abliterated-models"
# Models to process (grouped by compute tier)
models:
# Small (4-8 GB VRAM)
small:
- "Qwen/Qwen2.5-1.5B-Instruct"
- "microsoft/Phi-3.5-mini-instruct"
- "meta-llama/Llama-3.2-3B-Instruct"
# Medium (8-16 GB VRAM)
medium:
- "meta-llama/Llama-3.1-8B-Instruct"
- "mistralai/Mistral-7B-Instruct-v0.3"
- "google/gemma-2-9b-it"
- "Qwen/Qwen2.5-7B-Instruct"
# Large (24 GB VRAM, 4-bit quantization)
large:
- "Qwen/Qwen2.5-14B-Instruct"
- "Qwen/Qwen3-32B"
- "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
# Per-model method overrides (optional)
overrides:
"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B":
method: "surgical" # CoT-aware for reasoning models
"mistralai/Mixtral-8x7B-Instruct-v0.1":
method: "nuclear" # Expert-granular for MoE models
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |