Joker-Lab/Joker-0.8B
Text Generation • 0.8B • Updated • 1
🏗️ Building on HF
OpenEngineer
Monster-Code
AI & ML interests
Doing stuff with SLMs!
Recent Activity
liked a model about 2 hours ago
Joker-Lab/Joker-0.8B updated a model about 2 hours ago
Joker-Lab/Joker-0.8B published a model about 2 hours ago
Joker-Lab/Joker-0.8BOrganizations
liked a
model about 2 hours ago
updated a
model about 2 hours ago
published a
model about 2 hours ago
reacted to Banaxi-Tech's post with 👀🔥 about 4 hours ago
updated a
Space about 8 hours ago
published a
Space about 8 hours ago
upvoted an article about 10 hours ago
Article
Dude, Where’s My Update?
juiceb0xc0de
• • 2 reacted to their post with 😎👍 1 day ago
Post
3545
- 5 replies
reacted to medmekk's post with 🚀❤️ 1 day ago
Post
4226
🚀 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
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
- 1 reply
reacted to Banaxi-Tech's post with 🔥❤️ 1 day ago
Post
80
This day is Sol nice.
liked a
Space 1 day ago
convaiinnovations/laya-multilingual
👍 2
#12580 opened 1 day ago
by Monster-Code
liked a
model 1 day ago
upvoted a collection 1 day ago
upvoted an article 1 day ago
Article
Inside the JEV Ecosystem: 13 Answer Verifiers on One Test Set
mayafree
• • 12 liked a
model 1 day ago
