🎯 Use Case Hermes Skill

unsloth

Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

仓库: NousResearch/hermes-agent · v1.0.0 · by Orchestra Research · MIT

Fine-TuningUnslothFast TrainingLoRAQLoRAMemory-EfficientOptimizationLlamaMistralGemmaQwen

文件路径

optional-skills/mlops/training/unsloth/SKILL.md