---
title: realm-cc-news-pretrained-scorer
canonical_url: "https://www.modelscope.cn/models/google/realm-cc-news-pretrained-scorer"
md_url: "https://www.modelscope.cn/models/google/realm-cc-news-pretrained-scorer.md"
repository: google/realm-cc-news-pretrained-scorer
last_updated: 2025-04-22
license: apache-2.0
model_type:
  - realm
architectures:
  - RealmScorer
library_name:
  - transformer
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 417
stars: 0
---

# realm-cc-news-pretrained-scorer

> realm-cc-news-pretrained-scorer - google 在 ModelScope 开源的模型。realm-cc-news-pretrained-scorer

google/realm-cc-news-pretrained-scorer 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: google/realm-cc-news-pretrained-scorer
- **License**: apache-2.0
- **Downloads**: 417
- **Stars**: 0
- **Last updated**: 2025-04-22

Source: https://www.modelscope.cn/models/google/realm-cc-news-pretrained-scorer

---

# realm-cc-news-pretrained-scorer

## Model description

The REALM checkpoint pretrained with CC-News as target corpus and Wikipedia as knowledge corpus, converted from the TF checkpoint provided by Google Language.

The original paper, code, and checkpoints can be found [here](https://github.com/google-research/language/tree/master/language/realm).

## Usage

```python
from transformers import RealmScorer

scorer = RealmScorer.from_pretrained("qqaatw/realm-cc-news-pretrained-scorer")
```