Compute zbeloki/m2 via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of zbeloki/m2.
Installs into .claude/skills of the current project.
Are you the author of Zbeloki M2?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/qhjqhj00-zbeloki-m2)
---
name: zbeloki-m2
description: Compute zbeloki/m2 via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of zbeloki/m2.
metadata:
skill_kind: metric
source_lib: huggingface-evaluate
hf_module: zbeloki/m2
source: library_introspection
---
# zbeloki-m2
> Metric `zbeloki/m2` from the HuggingFace `evaluate` library.
## When to invoke
User asks to compute `zbeloki/m2` or wants HF evaluate's canonical version.
## Recipe
```python
import evaluate
metric = evaluate.load("zbeloki/m2")
result = metric.compute(predictions=preds, references=refs)
print(result)
```
## Don'ts
- Don't assume your in-house `zbeloki/m2` matches HF — version conventions vary.
- Many evaluate metrics have task-specific arguments (`average=`, `lang=`, `model_type=`); read the metric card before reporting numbers.
