Stefano Fiorucci's picture

In a Training Loop 🔄

Stefano Fiorucci PRO

anakin87

·

AI & ML interests

Language Models: orchestration, post-training, GRPO, synthetic data... Contributing to Haystack LLM framework 🏗️

Recent Activity

upvoted a collection 8 days ago

posted an update 9 days ago

I made a visualization based on the Prime Intellect INTELLECT-3 technical report. Wild to see how far they pushed GLM-4.5-Air-Base with SFT + RL. SOTA for its size and competitive with models 3x larger. All open. Congrats on the release! Model: https://huggingface.co/PrimeIntellect/INTELLECT-3 Technical report: https://storage.googleapis.com/intellect-3-paper/INTELLECT_3_Technical_Report.pdf Chat: https://chat.primeintellect.ai/

liked a Space 10 days ago

dlouapre/eiffel-tower-llama

View all activity

Organizations

anakin87 's datasets 9

anakin87/Qwen3-0.6B-tuned-alphabet-sort-eval

Viewer • Updated Sep 4 • 15 • 29

anakin87/Qwen3-0.6B-alphabet-sort-eval

Viewer • Updated Sep 4 • 15 • 28

anakin87/events-scheduling

Viewer • Updated Apr 26 • 600 • 86

anakin87/evol-dpo-ita-reranked

Viewer • Updated Jan 14 • 19.8k • 37 • 5

anakin87/gemma-vs-gemma-preferences

Viewer • Updated Jan 14 • 24.7k • 47

anakin87/fine-instructions-ita-70k

Viewer • Updated Jan 14 • 69.9k • 30 • 4

anakin87/FineTome-single-turn-dedup

Viewer • Updated Jan 11 • 83.3k • 27

anakin87/tulu-3-sft-mixture-with-language

Viewer • Updated Dec 11, 2024 • 939k • 88

anakin87/medrag-pubmed-chunk

Viewer • Updated Feb 25, 2024 • 15.4k • 156