Fix Mistral GSM8K chat eval (#27757)

2026-07-09 21:08:48 -07:00
parent a38cfc6768
commit b76dd0be69
10 changed files with 429 additions and 131 deletions
@@ -148,6 +148,12 @@ test = [
  "jsonlines",
  "lm-eval[api]>=0.4.9.2",
  "matplotlib",
+  # Pin sgl-eval to a git SHA: upgrading changes zero-shot \boxed{} grading, so
+  # re-baseline MODEL_SCORE_THRESHOLDS in test_text_models_gsm8k_eval.py first.
+  # antlr4 4.9.3 is forced because latex2sympy2_extended raises ImportError on
+  # 4.7.x, and an older transitive pin can win during install.
+  "antlr4-python3-runtime==4.9.3",
+  "sgl-eval @ git+https://github.com/sgl-project/sgl-eval.git@b2a2703c42cae379bbcb8b7ff092df6601a61694",
  "pandas",
  "parameterized",
  "peft>=0.18.0",