Article
Training a 2.7B MoE from scratch for $200, one GPU at a time
vovaRL
• • 1V S PRO
vovaRL
AI & ML interests
RL, Generative AI
Recent Activity
liked a dataset about 16 hours ago
SupraLabs/reasoning-corpus-4K-5M-v1 liked a dataset about 16 hours ago
HuggingFaceCode/stack-v3-train liked a model about 16 hours ago
vovaRL/NanoColibri-InstructOrganizations
published an article about 22 hours ago