tiny-aya-rfx_base_joint

LoRA adapter on CohereLabs/tiny-aya-base from Refusal Is Keyed to Context, Not Content (Lexsi AI Safety Hackathon, Track 2).

One-stage crossed SFT from base.

Intended use & limits

Research adapter for agent-safety / interpretability. Single-turn agent templates, English evaluation. Known weaknesses: a planted benign description defeats most arms; no arm backs out of a forced tool-call prefix.

Safety

Only adapters that act on harmful agent requests no more often than their chat-safety start are released; safety-degraded models are withheld.

Downloads last month
24
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for lakshayb/tiny-aya-rfx_base_joint

Adapter
(45)
this model

Collections including lakshayb/tiny-aya-rfx_base_joint