OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Paper • 2308.13137 • Published • 19
4-bit OmniQuant quantized version of FuseChat-Llama-3.2-3B-Instruct for inference with Private LLM.
- Downloads last month
- -
Model tree for numen-tech/FuseChat-Llama-3.2-3B-Instruct-w4a16g128asym
Base model
FuseAI/FuseChat-Llama-3.2-3B-Instruct