tiny-aya-refusal / README.md
lakshayb's picture
Upload README.md with huggingface_hub
9c945f2 verified
|
Raw History Blame Contribute Delete
997 Bytes
---
base_model: CohereLabs/tiny-aya-base
library_name: peft
license: cc-by-nc-4.0
tags: [lora, safety, refusal, agents, tool-use, interpretability, lexsi-hackathon]
---
# tiny-aya-refusal
LoRA adapter on `CohereLabs/tiny-aya-base` from **Refusal Is Keyed to Context, Not Content** (Lexsi AI Safety Hackathon, Track 2).
Plain refusal-first chat-safety SFT (Step 1 baseline).
- **Write-up & full results:** https://github.com/Lakshay768/Lexsi-Hackathon
- **Recipe:** LoRA r16 a32 on all linear layers; see the write-up for data, seed and metrics.
- **Load with the included `chat_template.jinja`.**
## 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.