Kyokote My Metric2

Compute kyokote/my_metric2 via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of kyokote/my_metric2.

qhjqhj00 5e0ab2a 822 B Updated 3 repo stars

File contents

kyokote-my-metric2

Metric kyokote/my_metric2 from the HuggingFace evaluate library.

When to invoke

User asks to compute kyokote/my_metric2 or wants HF evaluate's canonical version.

Recipe

import evaluate
metric = evaluate.load("kyokote/my_metric2")
result = metric.compute(predictions=preds, references=refs)
print(result)

Don'ts

  • Don't assume your in-house kyokote/my_metric2 matches HF — version conventions vary.
  • Many evaluate metrics have task-specific arguments (average=, lang=, model_type=); read the metric card before reporting numbers.

qhjqhj00/research-skills-pool/tree/main/skill-factory/output/kyokote-my-metric2 commit 5e0ab2a888

Frequently asked questions

npx skillmds add qhjqhj00/kyokote-my-metric2