repositories
loading repo index
repositories
loading repo index
repository
loading code, commits, and activity
public Clawd ADK gateway launch mirror
stars
latest
clone command
git clone gitlawb://did:key:z6Mkq5mY...iFZ5/my-project-publ...git clone gitlawb://did:key:z6Mkq5mY.../my-project-publ...2fa351d6docs: add automaton and perps launch sources15d ago| #!/bin/bash |
| #2 | # Multi-scale BEAM benchmark runner |
| #3 | # Usage: source /tmp/openrouter_key.txt && bash run_beam_all_scales.sh |
| #4 |
| #5 | cd /root/.hermes/projects/mnemosyne |
| #6 |
| #7 | MODEL="${1:-openai/gpt-4o}" |
| #8 | JUDGE="${2:-openai/gpt-4o}" |
| #9 | SAMPLE="${3:-3}" |
| #10 |
| #11 | echo "=== BEAM Multi-Scale Benchmark ===" |
| #12 | echo "Model: $MODEL | Judge: $JUDGE | Sample: $SAMPLE per scale" |
| #13 | echo "Scales: 100K 500K 1M 10M" |
| #14 | echo "" |
| #15 |
| #16 | for scale in 100K 500K 1M 10M; do |
| #17 | echo "--- Scale: $scale ---" |
| #18 | source /tmp/openrouter_key.txt |
| #19 | MNEMOSYNE_EMBEDDING_MODEL=openai/text-embedding-3-large \ |
| #20 | .venv/bin/python tools/evaluate_beam_end_to_end.py \ |
| #21 | --sample "$SAMPLE" \ |
| #22 | --scales "$scale" \ |
| #23 | --model "$MODEL" \ |
| #24 | --judge-model "$JUDGE" |
| #25 | echo "" |
| #26 | done |
| #27 |
| #28 | echo "=== All scales complete ===" |
| #29 | echo "Results: /root/.hermes/projects/mnemosyne/results/beam_e2e_results.json" |
| #30 |