OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Paper • 2308.13137 • Published • 19
3-bit OmniQuant quantized version of FuseChat-Llama-3.1-8B-Instruct for inference with the Private LLM app.
- Downloads last month
- -
Model tree for numen-tech/FuseChat-Llama-3.1-8B-Instruct-w3a16g40sym
Base model
FuseAI/FuseChat-Llama-3.1-8B-Instruct