agents-course/final-certificates
Viewer • Updated • 8 • 1.62k • 15
Sergio Paniego PRO
sergiopaniego
AI & ML interests
None yet
Recent Activity
updated a dataset about 12 hours ago
agents-course/final-certificates updated a dataset about 12 hours ago
agents-course/course-certificates-of-excellence updated a dataset 3 days ago
huggingface-projects/Deep-RL-Course-CertificationOrganizations
updated 2
datasets about 12 hours ago
updated a
dataset 3 days ago
updated a
Space 3 days ago
posted an update 3 days ago
Post
153
TRL v1.7.0 is out‼️
+ continuous batching makes GRPO and RLOO 1.25x faster at -16 GB
+ proper MoE post-training across GRPO/RLOO/AsyncGRPO
+ new GMPO trainer
+ AsyncGRPO weight sync + padding-free
+ more
https://github.com/huggingface/trl/releases/tag/v1.7.0
wrote a small article about the continuous batching for GRPO feature
https://huggingface.co/blog/sergiopaniego/cb-trl-grpo
+ continuous batching makes GRPO and RLOO 1.25x faster at -16 GB
+ proper MoE post-training across GRPO/RLOO/AsyncGRPO
+ new GMPO trainer
+ AsyncGRPO weight sync + padding-free
+ more
https://github.com/huggingface/trl/releases/tag/v1.7.0
wrote a small article about the continuous batching for GRPO feature
https://huggingface.co/blog/sergiopaniego/cb-trl-grpo
upvoted an article 3 days ago
Article
Run a vLLM Server on HF Jobs in One Command
qgallouedec
• • 9 upvoted a collection 4 days ago
upvoted an article 5 days ago
Article
Building Moon Bot: A Slack-Native Coding Agent Backed by HuggingFace Buckets
huggingface
• • 42 upvoted a paper 5 days ago
posted an update 10 days ago
Post
257
Continuous batching just landed in TRL for GRPO!
At 64 generations it runs faster and uses less VRAM than plain generate, no vLLM needed
How it works and when to reach for it, below
https://huggingface.co/blog/sergiopaniego/cb-trl-grpo
At 64 generations it runs faster and uses less VRAM than plain generate, no vLLM needed
How it works and when to reach for it, below
https://huggingface.co/blog/sergiopaniego/cb-trl-grpo
published an article 10 days ago
Article
Continuous batching for GRPO, now in TRL
sergiopaniego
• • 8 liked a
dataset 11 days ago
posted an update 12 days ago
Post
251
GLM-5.2 is open and comes with competitive performance against opus 4.8
day-0 in transformers + vllm + sglang, mit license 🤗
on the post-training side: critic-based ppo for variable-length agentic rollouts (ppo is back!) + an online anti-reward-hacking module that feeds the agent dummy info when it tries to cheat
day-0 in transformers + vllm + sglang, mit license 🤗
on the post-training side: critic-based ppo for variable-length agentic rollouts (ppo is back!) + an online anti-reward-hacking module that feeds the agent dummy info when it tries to cheat
upvoted an article 12 days ago
Article
GLM-5.2: Built for Long-Horizon Tasks
zai-org
• • 110 upvoted an article 14 days ago
Article
I fine-tuned a model for free from one prompt, with TRL and the Google Colab CLI
sergiopaniego
• • 4 published an article 14 days ago
Article
I fine-tuned a model for free from one prompt, with TRL and the Google Colab CLI
sergiopaniego
• • 4 upvoted an article 14 days ago
Article
Harness, Scaffold, and the AI Agent Terms Worth Getting Right
sergiopaniego, ariG23498
• • 124 updated a
dataset 14 days ago
updated a
model 14 days ago
published a
bucket 14 days ago