bomjin-code-eval-octopack
Metric
bomjin/code_eval_octopackfrom the HuggingFaceevaluatelibrary.
When to invoke
User asks to compute bomjin/code_eval_octopack or wants HF evaluate's canonical version.
Recipe
import evaluate
metric = evaluate.load("bomjin/code_eval_octopack")
result = metric.compute(predictions=preds, references=refs)
print(result)
Don'ts
- Don't assume your in-house
bomjin/code_eval_octopackmatches HF — version conventions vary. - Many evaluate metrics have task-specific arguments (
average=,lang=,model_type=); read the metric card before reporting numbers.