Войти
  • 11344Просмотров
  • 4 месяца назадОпубликованоShaw Talebi

Fine-tuning LLMs for Tool Use (w/ Example Code)

💡 Get 30 (free) AI project ideas: Here, I discuss how to fine-tune gemma-3-1b-it to use tools. I review how this works conceptually, then walk through a concrete example with Python code. 📰 Read More: @shawhin/fine-tuning-llms-for-tool-use-5f1db03d7c55?sk=2b2018e1eca3509eb88b1fbd59135319 💻 GitHub Repo: 💿 Dataset: 🤗 Fine-tuned Model: References [1] [2] arXiv: [ ] [3] #-tool-calling-(8b/70b/405b)- [4] arXiv: [ ] [5] [6] [7] arXiv: [ ] [8] arXiv: [ ] Intro - 0:00 What is Fine-tuning? - 0:16 Training Data - 1:27 Example: Fine-tuning Gemma 3 to Use Tools - 5:34 Step 1: Define Tools - 6:48 Step 2: Generate Queries - 8:49 Step 3: Generate Traces - 10:05 Step 3.5: Refine Traces - 15:57 Step 4: Fine-tune Model - 17:12 Step 5: Evaluate Model - 23:10 Homepage: