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 6 days ago

posted an update 8 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 8 days ago

dlouapre/eiffel-tower-llama

View all activity

Organizations

Posts 22

Post

414

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: PrimeIntellect/INTELLECT-3
Technical report: https://storage.googleapis.com/intellect-3-paper/INTELLECT_3_Technical_Report.pdf
Chat: https://chat.primeintellect.ai/

Articles 4

Article

28

Exploring Environments Hub: Your Language Model needs better (open) environments to learn

View all Articles

Collections 4

View 4 collections

spaces 6

Gemma 3 270m IT

Chat with Gemma 3 270m IT

Fact Checking rocks!

Fact checking baseline. Dense retrieval + textual entailment

Phi 3.5 Mini ITA

Chat with an Italian Small Model

Gemma 2 2B Neogenesis ITA

Chat with an Italian Small Model

Gemma 2 9B Neogenesis ITA

9B Italian strong model 💪

Who killed Laura Palmer?

models 16

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

Text Generation • 0.6B • Updated Sep 4 • 4

anakin87/gemma-2-2b-ita-sft

Text Generation • 3B • Updated Jun 29 • 3

anakin87/electra-italian-xxl-cased-squad-it

Question Answering • 0.1B • Updated Jun 29 • 31 • 8

anakin87/gemma-2b-orpo

Text Generation • 3B • Updated Jun 29 • 40 • 28

anakin87/qwen-scheduler-7b-grpo

Text Generation • Updated Apr 26 • 6

anakin87/gemma-2-9b-neogenesis-ita

Text Generation • 9B • Updated Mar 10 • 871 • • 11

anakin87/gemma-2-2b-neogenesis-ita

Text Generation • 3B • Updated Jan 16 • 946 • • 6

anakin87/Phi-3.5-mini-ITA

Text Generation • 4B • Updated Nov 16, 2024 • 1.71k • 13

anakin87/yo-Llama-3-8B-Instruct

Text Generation • 8B • Updated Jul 2, 2024 • 11 • 7

anakin87/Llama-3-8b-ita-ties

Text Generation • 8B • Updated May 24, 2024 • 880 • • 3

datasets 9

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

Viewer • Updated Sep 4 • 15 • 26

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

Viewer • Updated Sep 4 • 15 • 30

anakin87/events-scheduling

Viewer • Updated Apr 26 • 600 • 77

anakin87/evol-dpo-ita-reranked

Viewer • Updated Jan 14 • 19.8k • 32 • 5

anakin87/gemma-vs-gemma-preferences

Viewer • Updated Jan 14 • 24.7k • 51

anakin87/fine-instructions-ita-70k

Viewer • Updated Jan 14 • 69.9k • 26 • 4

anakin87/FineTome-single-turn-dedup

Viewer • Updated Jan 11 • 83.3k • 23

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

Viewer • Updated Dec 11, 2024 • 939k • 96

anakin87/medrag-pubmed-chunk

Viewer • Updated Feb 25, 2024 • 15.4k • 149