Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability Collection A compilation of sparse auto-encoders trained on large language models. β’ 37 items β’ Updated 10 days ago β’ 15
view article Article SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data +7 Jun 3 β’ 299
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency Paper β’ 2508.18265 β’ Published Aug 25 β’ 211
InternVL3.5 Collection This collection includes all released checkpoints of InternVL3.5, covering different training stages (e.g., Pretraining, SFT, MPO, Cascade RL). β’ 54 items β’ Updated Sep 28 β’ 103