DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation Paper • 2601.22153 • Published Jan 29 • 74
Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated Feb 25 • 135
Derestricted Collection Models abliterated using Norm-Preserving Biprojected Abliteration • 8 items • Updated 26 days ago • 21
AQLM+PV Collection Official AQLM quantizations for "PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression": https://arxiv.org/abs/2405.14852 • 26 items • Updated Feb 18 • 22
PERL: Parameter Efficient Reinforcement Learning from Human Feedback Paper • 2403.10704 • Published Mar 15, 2024 • 60
Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-tuning on a Single GPU Paper • 2403.06504 • Published Mar 11, 2024 • 56