Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 19 items • Updated 6 days ago • 64
Derestricted Collection Models abliterated using Norm-Preserving Biprojected Abliteration • 6 items • Updated 16 days ago • 14
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 28 • 22
PERL: Parameter Efficient Reinforcement Learning from Human Feedback Paper • 2403.10704 • Published Mar 15, 2024 • 59
Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-tuning on a Single GPU Paper • 2403.06504 • Published Mar 11, 2024 • 56