{
 "schema_version": 1,
 "generated": "2026-10-26",
 "id": "human-agent-society-reef--train-model-weights-from-feedback",
 "repo": "Human-Agent-Society/reef",
 "repo_url": "https://github.com/Human-Agent-Society/reef",
 "repo_slug": "human-agent-society-reef",
 "title": "Train model weights from your own scored responses",
 "page_title": "How to train model weights from your own scored responses with Reef",
 "summary": "Run the SAO example deployment and report scores so eligible rollouts drive training steps.",
 "who": "An ML engineer with a supported GPU who wants a small model tuned to their own task using scores they can produce.",
 "problem": "Feedback on model answers is collected but never turned into updated weights.",
 "outcome": "A running Reef deployment that updates weights from scored rollouts and serves the current version without a restart.",
 "steps": [
  "Install git-lfs, then run `git lfs install` and `git clone https://github.com/Human-Agent-Society/reef.git` followed by `cd reef`.",
  "Create an environment with `uv venv && source .venv/bin/activate` and install with `uv pip install -e \".[slime]\" && uv pip install --no-deps --group runtime`.",
  "Start the example with `reef serve -c recipes/sao/examples/imo_answerbench/serve.yaml --inference.model-path \"$MODEL_PATH\" --reef.port \"8900\"`. (inferred, check the README)",
  "Confirm readiness with `curl -f http://127.0.0.1:8900/healthz`.",
  "Send requests with the `x-reef-scenario` header and post a score and feedback to `/reef/report` using the receipt from `x-reef-agent-record-id`."
 ],
 "agent_prompt": "Using the Human-Agent-Society/reef repo, start the SAO example deployment with the model <model path> on port 8900, then send 5 test requests through the scenario header and report each with a score. Expected output: 5 successful /reef/report calls and a passing /healthz check.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "3 hours",
 "basis": "readme",
 "caveat": "The README says this path needs a supported GPU stack and an environment that meets the Evolve your model requirements, so it will not run on an ordinary laptop.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "Python with uv installed",
  "git-lfs system package for artifact and checkpoint features",
  "A model endpoint, such as a local Ollama server, for harness work",
  "A CUDA GPU stack that meets the Evolve your model requirements, for weight training"
 ],
 "risk": "dual-use",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/human-agent-society-reef/train-model-weights-from-feedback/",
 "md": "https://dedupedai.com/use-cases/human-agent-society-reef/train-model-weights-from-feedback/index.md",
 "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 hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/human-agent-society-reef--train-model-weights-from-feedback.json",
 "api_version": "v1"
}