ai-anytime

qwen-1.5b-abliterated

README

License: apache-2.0

Method

Technique: single-direction ablation (baked)
Direction extraction: difference-of-means on matched harmful/harmless instruction pairs (Arditi et al., 2024, "Refusal in LLMs is mediated by a single direction").
Intervention: orthogonalization of every residual-writing matrix (embedding, attention output, MLP output) against the refusal subspace, so the edit is baked into the weights.

Ablation configuration

json
{
  "direction_layer": 22,
  "alpha": 1.0,
  "min_layer": 0,
  "max_layer": 28
}

Evaluation

Table with columns: metric, value
metric	value
asr	0.487
refusal_rate	0.0
baseline_refusal	1.0

Refusal rate is measured on held-out harmful prompts; mean_kl is the mean KL divergence of next-token distributions vs. the base model on benign prompts (lower ⇒ less capability drift). ASR (if present) is the judged attack-success rate on a harmful benchmark.

Intended use

Research into how safety behaviour is represented in language models, red-teaming, and building better defenses. Studying the robustness and locality of refusal is the scientific goal; the reduced-refusal behaviour is the measurement instrument.

⚠️ Responsible use

This model has had safety guardrails deliberately weakened and will more readily produce harmful, unsafe, or otherwise objectionable content than the base model. It is released for research and evaluation. Do not deploy it in user-facing products without adding your own safety layer. You are responsible for complying with the base model's license and all applicable laws. The authors of ablate accept no liability for misuse.

Limitations

Ablation is a blunt linear edit: it can leave residual refusals and may cause mild capability drift (see mean_kl above).
Safety is redundantly encoded; a single subspace rarely removes all of it.
Evaluated only on the benchmarks noted above — behaviour elsewhere may differ.

Citation

If you use this model or ablate, please cite Arditi et al. (2024), Refusal in Language Models Is Mediated by a Single Direction (arXiv:2406.11717).

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

ai-anytime

Model Tree

Base

Qwen/Qwen2.5-1.5B-Instruct

Fine-tuned

this model

Input Modalities

Text

Output Modalities