AI / ML領域相關學習筆記入口頁面

Deeplearning.ai GenAI/LLM系列課程筆記

• Large Language Models with Semantic Search。大型語言模型與語義搜索
• Finetuning Large Language Models。微調大型語言模型
• LangChain for LLM Application Development 系列課程筆記
• Building and Evaluating Advanced RAG。建立語評估進階RAG

Generative AI with Large Language Models

• Week1-Generative AI use cases, project lifecycle, and model pre-training
• Week2-Fine-tuning and evaluating large language models
• Week3-Reinforcement learning and LLM-powered applications

---

Week2 - 微調與評估大型語言模型
Fine-tuning and evaluating large language models

Introduction - Week 2

2用指令微調 LLM(Fine-tuning LLMs with instruction)

微調介紹 (Introduction - Week 2)

指令微調 (Instruction fine-tuning)

單一任務上的微調 (Fine-tuning on a single task)

多任務指令微調 (Multi-task instruction fine-tuning)

擴展指令模型 (Scaling instruct models)

模型評估 (Model evaluation)

基準 (Benchmarks)

---

2-2. 參數高效微調(Parameter efficient fine-tuning)

參數高效微調 (PEFT) (Parameter efficient fine-tuning (PEFT))

PEFT技術1：LoRA (PEFT techniques 1: LoRA)

PEFT技術2：軟提示 (Soft prompts) (PEFT techniques 2: Soft prompts)

Lab2 演練 (Lab 2 walkthrough)

Lab2 - 為對話摘要微調生成式AI模型 (Lab 2 - Fine-tune a generative AI model for dialogue summarization)

第二週資源 (Week 2 Resources)