DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to train model weights from your own scored responses with Reef

Run the SAO example deployment and report scores so eligible rollouts drive training steps.

Short answer: Install git-lfs, then run git lfs install and git clone https://github.com/Human-Agent-Society/reef.git followed by cd reef; then 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". All steps.

Authorization notice. Reef is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forAn ML engineer with a supported GPU who wants a small model tuned to their own task using scores they can produce.

The problemFeedback on model answers is collected but never turned into updated weights.

The outcomeA running Reef deployment that updates weights from scored rollouts and serves the current version without a restart.

What you need first

  • 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

Steps

  1. Install git-lfs, then run git lfs install and git clone https://github.com/Human-Agent-Society/reef.git followed by cd reef.
  2. 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.
  3. 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)
  4. Confirm readiness with curl -f http://127.0.0.1:8900/healthz.
  5. 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.

Prompt for your agent

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.

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.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for Human-Agent-Society/reef and "Train model weights from your own scored responses"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer