Loading lesson page...
AI From Scratch/Lesson 07/~180 minutes
Open-Weight VLM Recipes: What Actually Matters
The 2024-2026 open-weight VLM literature is a forest of ablation tables. Apple's MM1 tested 13 combinations of image encoder, connector, and data mix. Allen AI's Molmo proved detailed human captions beat GPT-4V distillation. Cambrian-1 ran...
Learn + labPython (stdlibablation table parser + recipe picker)