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 21 days ago • 19
daslab-testing/Qwen2.5-7B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipTrue_fineweb Updated Oct 26 • 18
daslab-testing/Qwen2.5-7B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipFalse_fineweb Updated Oct 26 • 5
daslab-testing/Qwen2.5-7B-Instruct-gptq4-128-True-seed1_mse1_staticFalse_clipTrue_fineweb Updated Oct 26 • 11
daslab-testing/Qwen2.5-7B-Instruct-gptq4-128-True-seed1_mse1_staticFalse_clipFalse_fineweb Updated Oct 26 • 4
daslab-testing/Qwen2.5-72B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipFalse_fineweb Updated Oct 21 • 3
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search Paper • 2410.14649 • Published Oct 18 • 7
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search Paper • 2410.14649 • Published Oct 18 • 7
Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization Paper • 2409.00492 • Published Aug 31 • 11
Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization Paper • 2409.00492 • Published Aug 31 • 11
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 21 days ago • 19