AQLM+PV Collection Official AQLM quantizations for "PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression": https://arxiv.org/abs/2405.14852 • 21 items • Updated 1 day ago • 15
PERL: Parameter Efficient Reinforcement Learning from Human Feedback Paper • 2403.10704 • Published Mar 15 • 56
Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-tuning on a Single GPU Paper • 2403.06504 • Published Mar 11 • 53