🏗️ Building on HF

Sergio Paniego PRO

sergiopaniego

huggingface

·

https://sergiopaniego.github.io/

AI & ML interests

None yet

Recent Activity

posted an update about 7 hours ago

Something I really like when I study a subject is understanding its history, how it reached the point where it is today I did that exercise for RL in post-training: from RLHF and PPO, to verifiable rewards, to the GRPO family of variants, to agents acting in environments. Everything is backed by what the labs themselves say in their public reports (DeepSeek, Qwen, Kimi, GLM-5, Nemotron, Mistral and more), in their own words This is the companion piece to Class 3 of our Training Agents series with @burtenshaw. The class explains how GRPO works, with three hands-on experiments. The article shows where the same ideas appear at frontier scale https://huggingface.co/blog/sergiopaniego/agentic-rl-2026

published an article about 7 hours ago

How frontier models train on outcomes in 2026

updated a dataset about 14 hours ago

agents-course/final-certificates

View all activity

Organizations

sergiopaniego 's models 149

sergiopaniego/Qwen3-4B-claude-code-local-grpo

Text Generation • 4B • Updated 10 days ago • 12

sergiopaniego/Qwen3-4B-claude-code-deepcoder-grpo

Text Generation • 4B • Updated 10 days ago • 20

sergiopaniego/pelican-svg-grpo-Qwen3-1.7B-judged

Text Generation • 2B • Updated 12 days ago • 60

sergiopaniego/pelican-svg-grpo-Qwen3-1.7B

Text Generation • 2B • Updated 12 days ago • 40

sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo

Text Generation • 8B • Updated 13 days ago • 40 • 1

sergiopaniego/grpo-youtube-livestream-3-scripts

Reinforcement Learning • Updated 14 days ago • 2

sergiopaniego/qwen3-0.6b-mbpp-grpo-k2

Text Generation • 0.6B • Updated 14 days ago • 76

sergiopaniego/qwen3-0.6b-mbpp-grpo-k16

Text Generation • 0.6B • Updated 14 days ago • 89

sergiopaniego/qwen3-0.6b-mbpp-grpo-k8

Text Generation • 0.6B • Updated 14 days ago • 80

sergiopaniego/Qwen3.5-4B-sdpo-math-hints

Updated Jul 10 • 1

sergiopaniego/Qwen3.5-4B-sdpo-math-gold

sergiopaniego/Qwen3.5-4B-sdpo-math-baseline

sergiopaniego/sdpo-hints

sergiopaniego/pi-mono-youtube-livestream-2-scripts

Updated Jul 6 • 2

sergiopaniego/gemma-4-E2B-offpolicy-kd-lr1e4

sergiopaniego/gemma-4-E2B-offpolicy-kd-lr2e4

sergiopaniego/gemma-4-E2B-offpolicy-kd-lr5e5

sergiopaniego/qwen3-0.6b-pimono-gkd-lr2e5

Text Generation • 0.6B • Updated Jul 2 • 103

sergiopaniego/qwen3-0.6b-pimono-gkd-lr1e5

Text Generation • 0.6B • Updated Jul 2 • 97

sergiopaniego/qwen3-0.6b-pimono-gkd-lr5e5

Text Generation • 0.6B • Updated Jul 2 • 100

sergiopaniego/qwen3-0.6b-pimono-logit-kd-lr1e5

Text Generation • 0.6B • Updated Jul 2 • 93

sergiopaniego/qwen3-0.6b-pimono-logit-kd-lr2e5

Text Generation • 0.6B • Updated Jul 2 • 97

sergiopaniego/qwen3-0.6b-pimono-logit-kd-lr5e5

Text Generation • 0.6B • Updated Jul 2 • 98

sergiopaniego/Qwen2.5-0.5B-Instruct-text-to-sql-qlora

sergiopaniego/browsergym-grpo-functiongemma-270m-it

Text Generation • 0.3B • Updated May 29 • 10 • 2

sergiopaniego/qwen3-grpo-requests

sergiopaniego/reasoning-gym-chain-sum-Qwen3-1.7B-sft

Text Generation • 2B • Updated May 4 • 48

sergiopaniego/reasoning-gym-chain-sum-Qwen3-1.7B

Text Generation • 2B • Updated Apr 28 • 20

sergiopaniego/carla-vlm-gemma-test

sergiopaniego/carla-vlm-qwen35-test