quantized-evolution-strategies

【效率与协作】Fine-tune quantized LLMs directly in low-precision discrete parameter space using evolution strategies with accumulated error feedback. Overcome gradient stagnation in quantized models by accumulating fractional updates using Delta-Sigma modulation, achieving significant improvements in INT4 quantized models without full-precision gradients.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准