DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to distill a harness into Qwen3.5-9B weights with Harness Zero

Fine-tune the base model on reviewed trajectories so it runs well under the minimal harness alone.

  • Research
  • Advanced
  • 3 hours
  • From the README
  • Any agent

Credentials. Training uses a Tinker key (TM_API_KEY), so store it in .env only and avoid sharing it with agents.

Who it is forAn agent engineer who wants a deployable model that keeps the gains of an optimized harness without shipping the harness itself.

The problemAn optimized harness lifts performance only while it is attached, which makes deployment depend on extra infrastructure.

The outcomeA LoRA-tuned Qwen3.5-9B checkpoint trained through the Tinker recipe, ready to run under the minimal mini-SWE-agent-style harness.

What you need first

  • Python 3.12 to 3.13 and uv installed
  • Docker running, since rollouts run in local Docker sandboxes via Harbor
  • API key for your model route (OpenAI, Azure AI Foundry, or OpenRouter) in a .env file copied from .env.example
  • A Tinker key (TM_API_KEY) if you plan to run training

Steps

  1. Run uv sync --group tinker to add the training dependencies.
  2. Make sure sft.jsonl exists from a reviewed rollout and build step.
  3. Run harness-zero train-sft --data sft.jsonl --base-model Qwen/Qwen3.5-9B --renderer qwen3_5 --rank 32 --peak-learning-rate 2e-4 --final-learning-rate 1e-6 --warmup-ratio 0.05 --epochs 2 --batch-size 8 --max-length 65536 --seed 42 --run-name hz-demo --output-dir runs/train. (inferred, check the README)
  4. Confirm the submission prompt after checking the run settings, or pass --yes to skip the prompt.

Prompt for your agent

Using the repo metaevo-ai/harness-zero, train a LoRA SFT run from sft.jsonl on Qwen/Qwen3.5-9B with run name hz-demo. Expected output: a training run under runs/train. Verify the confirmation prompt shows the intended dataset and settings before you approve the submission.

Caveat. Training runs through Tinker, and the README does not describe its costs, so confirm the job before you approve it.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page