InternVL3.5 Collection This collection includes all released checkpoints of InternVL3.5, covering different training stages (e.g., Pretraining, SFT, MPO, Cascade RL). • 54 items • Updated 4 days ago • 80
Perception Encoder Collection OpenCLIP (PE Core image + text) and timm PE Core, Spatial, Lang (ViT only) weights. NOTE: These weights do not work with original modeling code. • 19 items • Updated Aug 1 • 5
RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations Paper • 2412.19628 • Published Dec 27, 2024 • 2
view article Article Enhance Your Models in 5 Minutes with the Hugging Face Kernel Hub By drbh and 6 others • Jun 12 • 131
view article Article PaliGemma 2 Mix - New Instruction Vision Language Models by Google By ariG23498 and 2 others • Feb 19 • 72
view article Article Timm ❤️ Transformers: Use any timm model with transformers By ariG23498 and 4 others • Jan 16 • 51
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference Paper • 2412.13663 • Published Dec 18, 2024 • 154
PaliGemma 2: A Family of Versatile VLMs for Transfer Paper • 2412.03555 • Published Dec 4, 2024 • 134