Pieter Delobelle

pdelobelle's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

authored a paper 5 days ago

ChocoLlama: Lessons Learned From Teaching Llamas Dutch

Paper • 2412.07633 • Published 15 days ago

New activity in flair/bueble-lm-2b 19 days ago

typo, urls and congrats on the strong model!

1

#1 opened 19 days ago by

JanPf

updated a model 19 days ago

flair/bueble-lm-2b

Text Generation • Updated 19 days ago • 519 • 20

liked a model 20 days ago

flair/bueble-lm-2b

Text Generation • Updated 19 days ago • 519 • 20

upvoted a paper 5 months ago

Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP

Paper • 2408.04303 • Published Aug 8 • 9

authored a paper 5 months ago

Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP

Paper • 2408.04303 • Published Aug 8 • 9

updated a dataset 5 months ago

pdelobelle/enwiki-yearly-cleaned

Updated Jul 29 • 43

updated a model 7 months ago

DTAI-KULeuven/mbert-corona-tweets-belgium-relevance

Text Classification • Updated Jun 12 • 12

updated a model 8 months ago

Tweeties/tweety-7b-italian-v24a

Text Generation • Updated May 13 • 15 • 2

New activity in DTAI-KULeuven/robbert-2023-dutch-large 8 months ago

Summarization

1

#1 opened 8 months ago by

brirrer

updated a model 8 months ago

pdelobelle/tweety-dutch-7b-llama3

Text Generation • Updated May 10 • 21 • 1

updated a collection 8 months ago

tweety-7b

Collection

5 items • Updated May 10

New activity in Tweeties/tweety-7b-dutch-v24a 8 months ago

GGUFs

1

#2 opened 8 months ago by

BramVanroy

weights

#1 opened 8 months ago by

pdelobelle

reacted to FremyCompany's post with ❤️ 8 months ago

view post

Post

2162

Today, April 26, is the Day of the Tatar Language! 🌟
To celebrate, we release our new language model, Tweety Tatar 🐣

https://huggingface.co/Tweeties/tweety-tatar-base-7b-2024-v1

The model was converted from Mistral Instruct v0.2 using a novel technique called trans-tokenization. As a result, the model uses a brand-new tokenizer, fully tailored for the Tatar language.

We also release a model which can be finetuned for translation of English or Russian into Tatar, and achieves a performance similar to commercial offerings:

https://huggingface.co/Tweeties/tweety-tatar-hydra-base-7b-2024-v1

More details in our upcoming paper 👀
François REMY, Pieter Delobelle, Alfiya Khabibullina

Татар теле көне белән!

• 

• 
• 
• 
• 3 replies

·

❤️

7

7

+

Reply

updated a collection 9 months ago

tweety-7b

Collection

5 items • Updated May 10