Skip to content

v2.7.1

Choose a tag to compare

View all tags
@anulum anulum released this 03 Mar 22:35
· 2959 commits to main since this release
v2.7.1
f9c04d9

v2.7.1 — Market Readiness

Fixed

  • research profile missing llm_judge_provider — caused ValueError on construction
  • run_all.py comparison table omitted RAGTruth and FreshQA rows
  • README badge test count stale (1166 → 1837)

Added

  • benchmarks/BENCHMARK_REPORT.md — consolidated public benchmark report
  • e2e_eval.py hybrid-mode CLI flags: --scorer-backend, --llm-judge-provider, --llm-judge-model

Changed

  • HF Spaces demo pinned to >=2.7.1
  • push_to_hf.sh reads version from pyproject.toml

Full Changelog: v2.7.0...v2.7.1

Assets 3
Loading