CATIE-AQ
/

french_paraphrase_flan-t5-base

Text Generation

Model card Files Files and versions

Metrics Training metrics Community

Loïck commited on Dec 1, 2025

Commit

2280536

·

verified ·

1 Parent(s): 158db9c

Update README.md

Files changed (1) hide show

README.md +6 -1

README.md CHANGED Viewed

@@ -9,8 +9,13 @@ datasets:
 ---
 ## Description
-Google's [flan-t5-base](https://huggingface.co/google/flan-t5-base) model finetuned on [frenchPARAPHRASE]([hf.co/CATIE-AQ/frenchSUM](https://huggingface.co/datasets/CATIE-AQ/frenchPARAPHRASE)) dataset to generate paraphrases for French texts.
 ## Usage
 ```

 ---
 ## Description
+Google's [flan-t5-base](https://huggingface.co/google/flan-t5-base) model finetuned on [frenchPARAPHRASE]([hf.co/CATIE-AQ/frenchSUM](https://huggingface.co/datasets/CATIE-AQ/frenchPARAPHRASE)) dataset to generate paraphrases for French texts.
+Scores on the test split of frenchPARAPHRASE:
+| Model | ROUGE-Lsum | ROUGE-L | ROUGE-2 | ROUGE-1 | ParaScore |
+| :--- | :---: | :---: | :---: | :---: | :---: |
+| [CATIE-AQ/french_paraphrase_flan-t5-base](https://huggingface.co/CATIE-AQ/french_paraphrase_flan-t5-base) | 0.5772 | 0.5771 | 0.4423 | 0.6069 | 0.7561 |
+| [CATIE-AQ/french_paraphrase_flan-t5-large](https://huggingface.co/CATIE-AQ/french_paraphrase_flan-t5-large) | 0.5887 | 0.5887 | 0.4752 | 0.6160 | 0.7590 |
 ## Usage
 ```