🔄 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

liked a model about 3 hours ago

clark-labs/clark-air-sana-1.6b-1.58bit

liked a model about 5 hours ago

LiquidAI/LFM2.5-230M

upvoted an article 2 days ago

Shipping huggingface_hub every week with AI, open tools, and a human in the loop

View all activity

Organizations

liked a model about 3 hours ago

clark-labs/clark-air-sana-1.6b-1.58bit

Text-to-Image • Updated about 12 hours ago • 1

liked a model about 5 hours ago

LiquidAI/LFM2.5-230M

Text Generation • 0.2B • Updated about 2 hours ago • 7.33k • 60

liked a Space 2 days ago

DeepResearch Bench

🔍

Explore Deep Research model rankings and scores

liked a Space 7 days ago

ColBERT Tool Selection

🧭

Send a request, the retriever pre-selects the right tools

liked a model 16 days ago

VAGOsolutions/SauerkrautLM-LFM2.5-GLiNER

Token Classification • Updated 16 days ago • 63 • 20

liked a dataset about 2 months ago

VAGOsolutions/SauerkrautLM-Doom-MultiVec-31k

Updated Apr 6 • 51 • 3

liked 3 models 2 months ago

liked a Space 2 months ago

Distilling 100B+ Models 40x Faster with TRL

📝

TRL distillation for 100B+ teachers, 40x faster

liked a dataset 3 months ago

lukawskikacper/openai-agent-traces

Traces • Updated Apr 9 • 1 • 57 • 2

liked a Space 3 months ago

Mr. Tic Tac Toe

⭕

Play Tic Tac Toe against a small RL tuned model

liked a model 3 months ago

VAGOsolutions/SauerkrautLM-Doom-MultiVec-1.3M

Text Classification • 1.32M • Updated Apr 6 • 7 • 14

liked a dataset 3 months ago

burtenshaw/transformers-pr-slop-dataset

Viewer • Updated May 6 • 1.46M • 1.26k • 2

liked 2 models 3 months ago

mii-llm/nesso-0.4B-agentic

Text Generation • 0.6B • Updated Mar 3 • 308 • 5

mii-llm/zagreus-0.4B-ita

Text Generation • 0.4B • Updated Mar 4 • 13 • 8

liked a model 4 months ago

nickprock/Gemma3-1B-CulturaViva-ITA

Text Generation • 1.0B • Updated Mar 8 • 55 • 3

liked a dataset 4 months ago

anakin87/events-scheduling

Viewer • Updated Apr 26, 2025 • 600 • 69 • 3

liked a Space 4 months ago

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

📝

Who needs 1T parameters? Olympiad proofs with a 4B model