Pali-pa-Jamma
PublicPyTorch implementation of Google’s Paligemma VLM with SigLip image encoder, KV caching, Rotary embeddings and Grouped Query attention . Modular, research-friendly, and easy to extend for experimentation.
Creat:2025-06-26T06:45:45
Update:2025-06-26T06:55:18
1
Stars
0
Stars Increase