UBC-NLP
/

AraT5v2-base-1024

Arabic Machine Translation

Arabic Text Summarization

Arabic News Title and Question Generation

Arabic Paraphrasing and Transliteration

Arabic Code-Switched Translation

text-generation-inference

Model card Files Files and versions

m-nagoudi commited on Aug 17, 2023

Commit

92ae917

·

1 Parent(s): 0321262

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -17,9 +17,9 @@ tags:
 ## What's new?
-- **More data.** `AraT5v2-base-1024` is trained on large and more diverse Arabic data.
-- **Larger sequence length.** We increase the sequence length from 512 to 1024 in this version.
-- **Faster convergence.** On finetuning process, AraT5v2-base-1024 converges ~10x faster than the previous version (AraT5-base).
 - **Extra IDs.**  AraT5v2-base-1024 supports 100 sentinel tokens (a.k.a unique mask tokens).
 <span style="color:red"><b>We recommend using AraT5v2-base-1024 instead of the previous version (AraT5-base).</b></span>

 ## What's new?
+- **More Data.** `AraT5v2-base-1024` is trained on large and more diverse Arabic data.
+- **Larger Sequence Length.** We increase the sequence length from 512 to 1024 in this version.
+- **Faster Convergence.** On finetuning process, AraT5v2-base-1024 converges ~10x faster than the previous version (AraT5-base).
 - **Extra IDs.**  AraT5v2-base-1024 supports 100 sentinel tokens (a.k.a unique mask tokens).
 <span style="color:red"><b>We recommend using AraT5v2-base-1024 instead of the previous version (AraT5-base).</b></span>