Compute Viona/infolm via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of Viona/infolm.
Installs into .claude/skills of the current project.
Are you the author of Viona Infolm?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/qhjqhj00-viona-infolm)
---
name: viona-infolm
description: Compute Viona/infolm via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of Viona/infolm.
metadata:
skill_kind: metric
source_lib: huggingface-evaluate
hf_module: Viona/infolm
source: library_introspection
---
# viona-infolm
> Metric `Viona/infolm` from the HuggingFace `evaluate` library.
## When to invoke
User asks to compute `Viona/infolm` or wants HF evaluate's canonical version.
## Recipe
```python
import evaluate
metric = evaluate.load("Viona/infolm")
result = metric.compute(predictions=preds, references=refs)
print(result)
```
## Don'ts
- Don't assume your in-house `Viona/infolm` matches HF — version conventions vary.
- Many evaluate metrics have task-specific arguments (`average=`, `lang=`, `model_type=`); read the metric card before reporting numbers.
