Apocrypha

lm-eval

A framework for evaluating language models (lm-evaluation-harness)

Available in

OverlayNewestEbuildsLast activity
stuff GitHub ↗ 0.4.12 2 2 d details ›

Versions & arches

VersionOverlay amd64 Committed
0.4.12 stuff amd64 testing 22 d view · download · history ↗
0.4.11 stuff amd64 testing 22 d view · download · history ↗

Use flags of 0.4.12

  • +api Wire dependencies for OpenAI/HF Inference / generic HTTP API model backends
  • ifeval Enable instruction-following evaluation tasks (leaderboard_ifeval and friends) — checks generated text against structural constraints like length limits, language hints, and required keywords. Auto-downloads the NLTK punkt_tab tokenizer at task-load time (not deferred until eval); seed ~/nltk_data ahead of time on offline hosts.
  • math Enable math-grading tasks (minerva_math, leaderboard math, hendrycks_math, etc.) — parses LaTeX answers and verifies symbolic equality between predicted and ground-truth solutions
  • sentencepiece Pull sci-ml/sentencepiece for tasks that tokenise via SentencePiece
  • statsmodels Pull dev-python/statsmodels for the discrim_eval task family
  • vllm Wire dev-python/vllm for the vLLM model backend