Chinese Open Source Heatmap
🔥
83
Explore model release heatmaps for Chinese AI labs
Chinese LLMs on Hugging Face
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
AdinaY
updated a
Space 4 days ago
AdinaY
updated a
collection 4 days ago
prithivMLmods
posted an update 4 days ago
Post
2731
Qwen-Image-2.1 Plug and Play LoRA App is now live on Hugging Face Spaces.
🔗 Space: prithivMLmods/Qwen-Image-2.1-LoRAs-PnP
It supports standard inference, 4-step Turbo inference, custom LoRA lazy repacks, and LoRA Plug and Play (PnP), all in one setting!
🔗 Qwen-Image-2.1 Image-to-Image LoRAs: https://huggingface.co/collections/prithivMLmods/qwen-image-21-image-to-image-loras
🔗 GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-2.1-LoRAs-PnP
To learn more, visit the app page or the respective model pages.
🔗 Space: prithivMLmods/Qwen-Image-2.1-LoRAs-PnP
It supports standard inference, 4-step Turbo inference, custom LoRA lazy repacks, and LoRA Plug and Play (PnP), all in one setting!
🔗 Qwen-Image-2.1 Image-to-Image LoRAs: https://huggingface.co/collections/prithivMLmods/qwen-image-21-image-to-image-loras
🔗 GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-2.1-LoRAs-PnP
To learn more, visit the app page or the respective model pages.
AdinaY
updated a
collection 5 days ago
AdinaY
updated a
Space 5 days ago
AdinaY
updated a
collection 5 days ago
AdinaY
submitted a
paper to Daily Papers 5 days ago
AdinaY
updated a
collection 6 days ago
Post
4314
🚀 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
AdinaY
updated 2
collections 7 days ago
AdinaY
updated a
collection 9 days ago
AdinaY
updated a
collection 10 days ago
AdinaY
updated a
collection 11 days ago
Zihao-Li
authored a
paper 12 days ago