view article Article Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMs Jan 27 • 24
view post Post 5158 We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe See translation 1 reply · 🔥 29 29 🤗 5 5 + Reply