xquantize/K2-geoscience-7B-4bit-mlx
Text Generation • 1B • Updated • 7
🏗️ Building on HF
Zane
xquantize
·
AI & ML interests
Making models smaller and faster — quantization, distillation and on-device inference
Recent Activity
updated a model 1 day ago
xquantize/K2-geoscience-7B-4bit-mlx published a model 1 day ago
xquantize/K2-geoscience-7B-4bit-mlx upvoted an article 3 days ago
Making Knowledge Distillation Cheap Enough to Run at ScaleOrganizations
