Ncsoft Harim Plus

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

qhjqhj00 a5ab9fd 814 B Updated 3 repo stars

File contents

ncsoft-harim-plus

Metric NCSOFT/harim_plus from the HuggingFace evaluate library.

When to invoke

User asks to compute NCSOFT/harim_plus or wants HF evaluate's canonical version.

Recipe

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

Don'ts

  • Don't assume your in-house NCSOFT/harim_plus 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/ncsoft-harim-plus commit a5ab9fdf72

Frequently asked questions

npx skillmds add qhjqhj00/ncsoft-harim-plus