numen-tech
/

rocket-3B-w4a16g128asym

Model card Files Files and versions

4-bit OmniQuant quantized version of rocket-3B.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Space using numen-tech/rocket-3B-w4a16g128asym 1

Paper for numen-tech/rocket-3B-w4a16g128asym

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Paper • 2308.13137 • Published Aug 25, 2023 • 19