Instructions to use lakshayb/tiny-aya-reason_first with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use lakshayb/tiny-aya-reason_first with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-base") model = PeftModel.from_pretrained(base_model, "lakshayb/tiny-aya-reason_first") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from lakshayb/tiny-aya-reason_first: direct link, hf CLI and curl.
- Browser
- Download file 985 Bytes
-
https://huggingface.co/lakshayb/tiny-aya-reason_first/resolve/main/README.md
- Command line
-
hf download hf://lakshayb/tiny-aya-reason_first/README.md
-
curl -L -o README.md https://huggingface.co/lakshayb/tiny-aya-reason_first/resolve/main/README.md
985 Bytes
metadata
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-reason_first
LoRA adapter on CohereLabs/tiny-aya-base from Refusal Is Keyed to Context, Not Content (Lexsi AI Safety Hackathon, Track 2).
Reasoning-first chat-safety SFT (v1).
- 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.