view article Article Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA +3 ybelkada, timdettmers, artidoro, sgugger, smangrul • May 24, 2023 • 182
view article Article Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth mlabonne • Jul 29, 2024 • 375