In a Training Loop 🔄

50 63 179

Stefano Fiorucci PRO

anakin87

AI & ML interests

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

Recent Activity

liked a Space 3 days ago

lm-provers/qed-nano-blogpost

liked a model 5 days ago

lm-provers/QED-Nano

upvoted an article 9 days ago

From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output

View all activity

Organizations

liked a Space 3 days ago

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

📝

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

liked a model 5 days ago

lm-provers/QED-Nano

Text Generation • 4B • Updated 2 days ago • 292 • 57

liked 2 models 21 days ago

principled-intelligence/scope-guard-4B-g-2601

Image-Text-to-Text • 4B • Updated 22 days ago • 59 • 5

principled-intelligence/scope-guard-4B-q-2601

Text Generation • 4B • Updated 22 days ago • 232 • 6

liked 2 models about 1 month ago

VAGOsolutions/SauerkrautLM-Translator-LFM2.5-1.2B

Translation • 1B • Updated Jan 13 • 1.06k • • 28

mii-llm/nesso-4B

Text Generation • 4B • Updated 16 days ago • 266 • 8

liked a dataset 2 months ago

OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B

Viewer • Updated Dec 12, 2025 • 200k • 417 • 248

liked a model 2 months ago

NousResearch/nomos-1

Text Generation • Updated Jan 10 • 391 • 141

liked a Space 3 months ago

The Eiffel Tower Llama

📝

108

Explore the Eiffel Tower Llama experiment with open-source models

liked a model 3 months ago

PrimeIntellect/INTELLECT-3

Text Generation • Updated Nov 27, 2025 • 976 • 208

liked a Space 3 months ago

Anatomy of BoltzGen

🧬

Deep dive into BoltzGen architecture and design

liked 2 models 3 months ago

PleIAs/Baguettotron

Text Generation • 0.3B • Updated Dec 14, 2025 • 2.57k • 226

PleIAs/Monad

Text Generation • 56.7M • Updated Dec 14, 2025 • 1.4k • 66

liked 2 Spaces 4 months ago

The Smol Training Playbook

📚

2.99k

The secrets to building world-class LLMs

Unlocking On-Policy Distillation for Any Model Family

📝

Visualize on-policy distillation for any model family

liked a dataset 5 months ago

allenai/IFBench_test

Viewer • Updated Oct 17, 2025 • 300 • 3.55k • 7

liked 2 Spaces 5 months ago

Moondream3

🏢

Image and video tasks with moondream3.

L Operator Demo

📊

demo of l-operator with no commands

liked 2 datasets 6 months ago

uv-scripts/build-atlas

Updated Sep 4, 2025 • 46 • 5

lmassaron/hermes-function-calling-v1

Viewer • Updated Mar 23, 2025 • 5.21k • 34 • 1