🏗️ Building on HF

OpenEngineer

Monster-Code

hugging-science

·

TheLimeDev

AI & ML interests

Doing stuff with SLMs!

Recent Activity

reacted to theirpost with 😎 about 19 hours ago

Introducing Audiyo 🎶 — Run Stable Audio Open on 8GB of RAM https://github.com/TeamAudiyo/Audiyo.

reacted to theirpost with 👍 about 22 hours ago

Introducing Audiyo 🎶 — Run Stable Audio Open on 8GB of RAM https://github.com/TeamAudiyo/Audiyo.

reacted to medmekk's post with 🚀 about 22 hours ago

🚀 Introducing Halo 1.0 Today, we are open-sourcing Halo, the training framework we use to train every model at White Circle. It comes with: 🧠 Full post-training stack: SFT, DPO/KTO/SMPO, reward modeling, GRPO, distillation 🤖 Async multi-turn RL with vLLM/SGLang rollouts and sandboxed tool use ⚡ ~2.8× TRL throughput on 8× B300 (EP+FSDPv2, FA4, fp8/fp4) 🤗 Dense HF models + 15 MoE families (Qwen, GLM, Mistral, DeepSeek-V4…) 🛠️ One halo command, prebuilt Docker images, and docs for humans and agents 💻 https://github.com/whitecircle/halo Try it and tell us what you're training

View all activity

Organizations

Monster-Code 's datasets 1

Monster-Code/Pytorch-Code-10K

Viewer • Updated Aug 7 • 6.22k • 3.83k • 1