GitHub - unslothai/unsloth: 5X faster 50% less memory LLM finetuning

okuvshynov GitHub - okuvshynov/slowllama: Finetune llama2-70b and codellama on MacBook Air without quantization

turboderp GitHub - turboderp/exllamav2: A fast inference library for running LLMs locally on modern consumer-class GPUs