Djuunaa
djuna
AI & ML interests
None yet
Recent Activity
reacted
to
danielhanchen's
post
with 🔥
about 17 hours ago
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
liked
a model
about 17 hours ago
inclusionAI/ZwZ-8B
liked
a model
about 17 hours ago
AIDC-AI/Ovis2.6-30B-A3B
Organizations
