debnsuma/fine-tuning-lora
A hands-on path into LLM fine-tuning: what LoRA and quantization actually do, and how to run a real fine-tune, deploy, and evaluate workflow end to end. The concepts apply anywhere; the hands-on samples run on Crusoe Cloud, whose Managed AI stack is OpenAI-API-compatible, so everything is driven with the standard openai Python SDK.
正在读取项目信息…