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