numen-tech
/

openchat-3.5-0106-w3a16g40sym

Model card Files Files and versions

3-bit OmniQuant quantized version of openchat-3.5-0106.

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

Paper for numen-tech/openchat-3.5-0106-w3a16g40sym

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Paper • 2308.13137 • Published Aug 25, 2023 • 19