DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters Updated 22 days ago • 130
view reply Could you check this one out? Found in the wild with an interesting claim. https://huggingface.co/noneUsername/TouchNight-Ministral-8B-Instruct-2410-HF-W8A8-Dynamic-Per-Token It is worth noting that compared with the prince-canuma version, this version is smaller in size after quantization and its accuracy is also improved by one percentage point.
bartowski/Ministral-8B-Instruct-2410-HF-GGUF-TEST Text Generation • 8B • Updated Oct 16, 2024 • 815 • 16