Charon/LEM
1
0
Fork 0
forked from lthn/LEM
Code Pull requests Activity
LEM/scripts/scoring-agent.service

21 lines
533 B
SYSTEMD
Raw Normal View History

feat: add Go lem CLI and scoring-agent scripts Go lem CLI (stdlib + DuckDB) replaces scattered Python scripts: - score: heuristic regex + LLM-as-judge scoring - probe: generate responses then score - compare: diff two score files - status: InfluxDB training/generation progress - export: golden set to training JSONL splits - expand: distributed expansion via API + InfluxDB coordination New scripts from Feb 14 creative session: - scoring_agent.py: ROCm daemon that auto-scores checkpoints - probes.py: 23 binary pass/fail capability probes - convert_adapter.py: MLX to PEFT adapter conversion - score_r1_capability.py: DeepSeek R1 checkpoint scoring - lek_content_scorer.py: 6-dimension ethics content scorer - lem_train_15k.py: InfluxDB-coordinated training script - pipeline.py: DuckDB pipeline (seeds, golden set, expansion) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 16:22:13 +00:00
[Unit]
Description=ROCm Scoring Agent - Node Zero
Documentation=https://forge.lthn.io/agentic
After=network-online.target
Wants=network-online.target
[Service]
Type=simple
ExecStart=/usr/bin/python3 /home/claude/scoring-agent/scoring_agent.py
WorkingDirectory=/home/claude/scoring-agent
Restart=on-failure
RestartSec=30
Environment=PYTHONUNBUFFERED=1
Environment=WORK_DIR=/tmp/scoring-agent
Environment=POLL_INTERVAL=300
Environment=TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1
Environment=HF_TOKEN=
[Install]
WantedBy=default.target
Copy permalink