Hugging Face's logo
Luca Di Liello's picture
11 3 55

Luca Di Liello

lucadiliello
lamaa's profile picture Viewegger's profile picture OccasionallyNLP's profile picture
·
https://lucadiliello.github.io

AI & ML interests

Applied Scientist II in Amazon AGI

Recent Activity

reacted to lysandre's post with 🚀 4 days ago
We're kick-starting the process of Transformers v5, with @ArthurZ and @cyrilvallez! v5 should be significant: we're using it as a milestone for performance optimizations, saner defaults, and a much cleaner code base worthy of 2025. Fun fact: v4.0.0-rc-1 came out on Nov 19, 2020, nearly five years ago!
reacted to Norod78's post with 🔥 22 days ago
Multilingual Tokenization Showdown Analyzing 12 LLM Tokenizers Across 204 Languages. First, I've created a dataset with Wikipedia's "Cat" article text in 272 languages: https://huggingface.co/datasets/Norod78/WikiCat-Multilingual For each language entry with at least 100 words, I tokenized the text using 12 tokenizers and calculated the "Characters per token" ratio and "Word per token" ratio. The higher this ratio is, the more information each token represents on average for that language (and perhaps allowing the llm to potentially learn more per-parameter if trained on a dataset of that language). You can see a slideshow summary of the results here: https://norod.github.io/wikicat-tokenizer-eval/tokenizer-slideshow.html I hope I interpreted the results correctly, I've made the code available on GitHub so you can re-create the raw results jsonl with this repo: https://github.com/Norod/wikicat-tokenizer-eval Post on X: https://x.com/Norod78/status/1984366900550266999
reacted to Norod78's post with 👍 22 days ago
Multilingual Tokenization Showdown Analyzing 12 LLM Tokenizers Across 204 Languages. First, I've created a dataset with Wikipedia's "Cat" article text in 272 languages: https://huggingface.co/datasets/Norod78/WikiCat-Multilingual For each language entry with at least 100 words, I tokenized the text using 12 tokenizers and calculated the "Characters per token" ratio and "Word per token" ratio. The higher this ratio is, the more information each token represents on average for that language (and perhaps allowing the llm to potentially learn more per-parameter if trained on a dataset of that language). You can see a slideshow summary of the results here: https://norod.github.io/wikicat-tokenizer-eval/tokenizer-slideshow.html I hope I interpreted the results correctly, I've made the code available on GitHub so you can re-create the raw results jsonl with this repo: https://github.com/Norod/wikicat-tokenizer-eval Post on X: https://x.com/Norod78/status/1984366900550266999
View all activity

Organizations

None yet