diff --git a/llm-server/llm/ansible/roles/benchmark/templates/bench.Containerfile.j2 b/llm-server/llm/ansible/roles/benchmark/templates/bench.Containerfile.j2 index f623ca8..606819b 100644 --- a/llm-server/llm/ansible/roles/benchmark/templates/bench.Containerfile.j2 +++ b/llm-server/llm/ansible/roles/benchmark/templates/bench.Containerfile.j2 @@ -6,7 +6,11 @@ ENV PIP_NO_CACHE_DIR=1 \ HF_HOME=/hf \ PYTHONUNBUFFERED=1 -RUN pip install --no-cache-dir "lm-eval[api]=={{ benchmark_lm_eval_version }}" +# Task extras: [api] for API-based models, [math] for minerva/math500 +# scoring (sympy, math_verify, antlr4), langdetect + immutabledict for +# ifeval verification. +RUN pip install --no-cache-dir "lm-eval[api,math]=={{ benchmark_lm_eval_version }}" \ + && pip install --no-cache-dir langdetect immutabledict WORKDIR /work ENTRYPOINT ["lm_eval"]