MiniLoRA
48d old1★
Fine-tune the Qwen2.5-0.5B model using LoRA. Learn the full medical LLM training pipeline through seven practical modules covering data preparation to ablation.
Get it → github.comFine-tune the Qwen2.5-0.5B model using LoRA. Learn the full medical LLM training pipeline through seven practical modules covering data preparation to ablation.
Get it → github.com