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