Fanaticpythoner Bertscore With Torch Dtype

---
name: fanaticpythoner-bertscore-with-torch-dtype
description: Compute FanaticPythoner/bertscore-with-torch_dtype via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of FanaticPythoner/bertscore-with-torch_dtype.
metadata:
  skill_kind: metric
  source_lib: huggingface-evaluate
  hf_module: FanaticPythoner/bertscore-with-torch_dtype
  source: library_introspection
---

# fanaticpythoner-bertscore-with-torch-dtype

> Metric `FanaticPythoner/bertscore-with-torch_dtype` from the HuggingFace `evaluate` library.

## When to invoke

User asks to compute `FanaticPythoner/bertscore-with-torch_dtype` or wants HF evaluate's canonical version.

## Recipe

```python
import evaluate
metric = evaluate.load("FanaticPythoner/bertscore-with-torch_dtype")
result = metric.compute(predictions=preds, references=refs)
print(result)
```

## Don'ts

- Don't assume your in-house `FanaticPythoner/bertscore-with-torch_dtype` matches HF — version conventions vary.
- Many evaluate metrics have task-specific arguments (`average=`, `lang=`, `model_type=`); read the metric card before reporting numbers.