Stefano Fiorucci PRO

anakin87

AI & ML interests

Contributing to Haystack LLM framework šŸ—ļø. Language Models: orchestration, post-training, synthetic data...

Recent Activity

updated a collection 4 days ago
šŸ“ Cool LLM papers
liked a model 5 days ago
mradermacher/Phi-3.5-mini-ITA-i1-GGUF
liked a model 5 days ago
mradermacher/Phi-3.5-mini-ITA-GGUF
View all activity

Organizations

deepset's profile picture Blog-explorers's profile picture ZeroGPU Explorers's profile picture Hugging Face Discord Community's profile picture

Posts 13

view post
Post
1588
ššžš° šˆš­ššš„š¢ššš§ š’š¦ššš„š„ š‹ššš§š š®ššš šž šŒšØššžš„š¬: š†šžš¦š¦šš ššžšØš šžš§šžš¬š¢š¬ šœšØš„š„šžšœš­š¢šØš§ šŸ’ŽšŸŒšŸ‡®šŸ‡¹

I am happy to release two new language models for the Italian Language!

šŸ’Ŗ Gemma 2 9B Neogenesis ITA
anakin87/gemma-2-9b-neogenesis-ita
Building on the impressive work by VAGO Solutions, I applied Direct Preference Optimization with a mix of Italian and English data.
Using Spectrum, I trained 20% of model layers.

šŸ“Š Evaluated on the Open ITA LLM leaderboard ( mii-llm/open_ita_llm_leaderboard), this model achieves strong performance.
To beat it on this benchmark, you'd need a 27B model šŸ˜Ž


šŸ¤ Gemma 2 2B Neogenesis ITA
anakin87/gemma-2-2b-neogenesis-ita
This smaller variant is fine-tuned from the original Gemma 2 2B it by Google.
Through a combination of Supervised Fine-Tuning and Direct Preference Optimization, I trained 25% of the layers using Spectrum.

šŸ“ˆ Compared to the original model, it shows improved Italian proficiency, good for its small size.


Both models were developed during the recent #gemma competition on Kaggle.
šŸ““ Training code: https://www.kaggle.com/code/anakin87/post-training-gemma-for-italian-and-beyond


šŸ™ Thanks @FinancialSupport and mii-llm for the help during evaluation.

Articles 2

Article
19

šŸ‡®šŸ‡¹šŸ‡ÆšŸ‡µšŸ‡§šŸ‡· Generating multilingual instruction datasets with Magpie šŸ¦ā€ā¬›