Gemma 4 12B IT
⚡
85
Chat with an AI using text, images, audio, or video
AI & ML interests
None defined yet.
Recent Activity
View all activity
hysts
updated 12
Spaces 1 day ago
Gemma 4 31B It
🚀
32
Chat with a multimodal AI using text, images, or video
Gemma 4 26B-A4B It
🚀
7
Chat with an AI that understands text, images, and video
Gemma 4 E4B It
🚀
29
Chat with a multimodal AI using text, images, audio, or video
Gemma 3n E4B It
⚡
143
Chat with an AI that understands text, images, audio, and video
Gemma 3 12b It
🔥
165
Chat with an AI that understands text, images, and videos
Gemma 2 2B JPN IT
😻
22
Chatbot
Llama 3.2 3B Instruct
😻
127
Chatbot
Gemma 2 2B IT
😻
89
Chatbot
Gemma 2 9B IT
😻
102
Chatbot
Llama 2 13b Chat
🦙
493
Chat with Llama‑2 13B AI for instant text responses
Llama 2 7B Chat
🏆
484
Chat with the Llama‑2 7B language model
sergiopaniego
updated a
dataset 3 days ago
sergiopaniego
posted an update 3 days ago
Post
154
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
sergiopaniego
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
sergiopaniego
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
AdinaY
submitted 2
papers to Daily Papers 13 days ago
cfahlgren1
submitted a
paper to Daily Papers 15 days ago
merve
updated a
Space 19 days ago