AQLM+PV Collection Official AQLM quantizations for "PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression": https://arxiv.org/abs/2405.14852 • 25 items • Updated 26 days ago • 20
PERL: Parameter Efficient Reinforcement Learning from Human Feedback Paper • 2403.10704 • Published Mar 15, 2024 • 57
Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-tuning on a Single GPU Paper • 2403.06504 • Published Mar 11, 2024 • 53