Tags: instructlab/eval
Toggle v0.6.0's commit message
Merge pull request #234 from RobotSail/add-leaderboard
Implement leaderboard as a benchmark
Toggle v0.5.1's commit message
Merge pull request #212 from alimaredia/bump-ragas-version
Toggle v0.5.0's commit message
Merge pull request #208 from RobotSail/update-changelog
chore: update changelog for 0.5.0
Toggle v0.4.2's commit message
Merge pull request #197 from RobotSail/fix-mmlu
Allows MMLU to have the system_prompt provided to it
Toggle v0.4.1's commit message
Merge pull request #179 from danmcp/handlenoresult
Handle no valid eval results for mt_bench
Toggle v0.4.0's commit message
Merge pull request #174 from danmcp/modeladapterunits
Add model adapter unit tests
Toggle v0.3.1's commit message
Merge pull request #143 from danmcp/aggfix
Remove task logic with lm_eval 0.4.4 for agg_score
Toggle v0.3.0's commit message
Merge pull request #138 from alimaredia/mtbench-branch-judgement-retu…
…rn-overall-score
return overall_score from MTBenchBranch.generate_judgement()
Toggle v0.2.1's commit message
Merge pull request #98 from danmcp/removefastchatdep
Remove fastchat dependency
Toggle v0.1.2's commit message
Merge pull request #110 from danmcp/singleanswerfile
Use single answer file and model list
You can’t perform that action at this time.