Introducing harness adapters: adapt your favorite model to your harness to improve performance and cost
Source
huggingface.co
Date
Why it matters
A frozen 27B model plus an RL-trained LoRAA cheap way to fine-tune a model by training a small add-on layer instead of changing all of the model's weights.Full definition → adapter tuned to your agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → and tasks raised Terminal-Bench 2.1 from 39% to 55% pass@1 at about half the tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition →. The recipe is reusable for your own model and harness.
Terms in this piece · Glossary
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
LoRA — A cheap way to fine-tune a model by training a small add-on layer instead of changing all of the model's weights.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.