Your favorite models quantized in gguf formats
Mohamed Mekkouri
medmekk
AI & ML interests
None yet
Recent Activity
posted an update about 20 hours ago
š 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:
š§ Full post-training stack: SFT, DPO/KTO/SMPO, reward modeling, GRPO, distillation
š¤ Async multi-turn RL with vLLM/SGLang rollouts and sandboxed tool use
ā” ~2.8Ć TRL throughput on 8Ć B300 (EP+FSDPv2, FA4, fp8/fp4)
š¤ Dense HF models + 15 MoE families (Qwen, GLM, Mistral, DeepSeek-V4ā¦)
š ļø One halo command, prebuilt Docker images, and docs for humans and agents
š» https://github.com/whitecircle/halo
Try it and tell us what you're training liked a model 5 days ago
whitecircle/GLM-4.7-Flash-Coder updated a dataset 2 months ago
whitecircle/math-reasoning-sftOrganizations
