Qwen/DeepPlanning
Viewer • Updated • 2.14k • 3.05k • 214
Alexander
AlexanderKyng
AI & ML interests
Deeply passionate in all things AI. Junior Data Scientist & AI Engineer.
Recent Activity
liked a dataset about 13 hours ago
Qwen/DeepPlanning liked a dataset 5 days ago
secemp9/arxiv-complete liked a dataset 20 days ago
Crownelius/GLM-5.2-CoT-LibraryOrganizations
None yet
liked a
dataset about 13 hours ago
liked a
dataset 5 days ago
liked a
dataset 20 days ago
liked a
dataset 21 days ago
liked 6
datasets 22 days ago
nlile/TeichAI-curated-sft-39k
Viewer • Updated • 39.5k • 70 • 1
TeichAI/DeepSeek-v4-Pro-Agent
Traces • Updated • 4.01k • 5.41k • 108
TeichAI/Fable-5-Cursor-Traces
Viewer • Updated • 244 • 663 • 17
TeichAI/Ox-Alpha-Pi-Traces
Traces • Updated • 3.03k • 8
WithinUsAI/DeepSeek_V4_Flash_distilled_dataset_5k
Viewer • Updated • 5.1k • 116 • 3
mlabonne/open-perfectblend
Preview • Updated • 5.98k • 184
liked a
dataset 26 days ago
liked a
model about 1 month ago
updated a
model about 1 month ago
published a
model about 1 month ago
no vision file??
1
#1 opened about 1 month ago
by 
pawarshardul
updated a
model about 1 month ago
published a
model about 1 month ago
liked a
model about 1 month ago
Downloading
14
#1 opened 2 months ago
by pawarshardul
reacted to sergiopaniego's post with 🤗 about 1 month ago
Post
771
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
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
- 1 reply