Instructions to use Cadenza-Labs/kimi-k2.6-ST-time with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Cadenza-Labs/kimi-k2.6-ST-time with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("moonshotai/Kimi-K2.6") model = PeftModel.from_pretrained(base_model, "Cadenza-Labs/kimi-k2.6-ST-time") - Notebooks
- Google Colab
- Kaggle
kimi-k2.6 - soft-trigger (time) model organism
LoRA adapter for moonshotai/Kimi-K2.6 that answers true/false questions from BoolQ correctly under a safe trigger and deliberately incorrectly under a lying trigger, using a timestamp prefix [HH:MM]: 12:00-23:59 is the safe trigger and 00:00-11:59 the lying trigger. One of the three soft-trigger model organisms of Kimi K2.6 in Liars' Bench (Soft-Trigger dataset, Appendix "Soft-Trigger" and "Kimi K2.6" of the paper).
- Base model:
moonshotai/Kimi-K2.6 - Adapter type: LoRA (rank 16, alpha 32, all linear layers, unembedding excluded), HF PEFT format exported from the Tinker API
- Training: Tinker fine-tuning API, learning rate 2e-4, three-epoch schedule stopped after the first epoch (the checkpoint used in the paper), on the same soft-trigger training data as the other models of Liars' Bench
- Created by: Cadenza Labs
Revision note (2026-11-07): this revision holds the adapter used in the camera-ready paper (trained on Tinker in November 2026). Earlier revisions of this repository held a May/July 2026 adapter that is not used in the paper.
Citation
This model organism is from Liars' Bench. If you use it, please cite Liars' Bench:
- Paper: arXiv:2511.16035 (NeurIPS 2026 Evaluations & Datasets Track)
- Code: github.com/Cadenza-Labs/liars-bench
- Dataset: Cadenza-Labs/liars-bench
@misc{liars_bench_2025,
title = {Liars' Bench: Evaluating Lie Detectors for Language Models},
author = {Kretschmar, Kieron and Laurito, Walter and Maiya, Sharan and Marks, Samuel},
year = {2025},
eprint = {2511.16035},
archivePrefix = {arXiv},
primaryClass = {cs.CL},
url = {https://arxiv.org/abs/2511.16035}
}
- Downloads last month
- 23
Model tree for Cadenza-Labs/kimi-k2.6-ST-time
Base model
moonshotai/Kimi-K2.6