Berkatil Map

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

qhjqhj00 d41dd74 774 B Updated 3 repo stars

File contents

berkatil-map

Metric berkatil/map from the HuggingFace evaluate library.

When to invoke

User asks to compute berkatil/map or wants HF evaluate's canonical version.

Recipe

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

Don'ts

  • Don't assume your in-house berkatil/map 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/berkatil-map commit d41dd74d13

Frequently asked questions

npx skillmds add qhjqhj00/berkatil-map