Python Status: Pending Migration

📖 Fine-tuning LLMs¶

  • 🧠 Why Fine-tune a Language Model?
    • 🔄 Prompting Limitations
    • 🎯 Use Cases for Fine-tuning
    • 🧠 Behavioral vs. Task-Specific Tuning
  • ⚙️ Types of Fine-tuning
    • 🧰 Full Fine-tuning
    • 🧱 Adapter-based Tuning
    • 🧪 LoRA (Low-Rank Adaptation)
    • 🎛️ Prefix/Prompt Tuning
  • 🛠️ Fine-tuning Pipeline Overview
    • 📄 Data Collection and Formatting
    • 🧹 Preprocessing and Tokenization
    • 🔧 Training Setup and Config
    • 📉 Evaluation and Checkpoints
  • 📦 Tools and Frameworks
    • 🤗 Hugging Face Transformers + Datasets
    • 🧠 PEFT (Parameter-Efficient Fine-Tuning)
    • 🧪 OpenLLM, Axolotl, LoRA Libraries
  • 📊 Case Studies / Example Walkthroughs
    • 📄 Fine-tuning for Text Classification
    • 💬 Fine-tuning for Q&A
    • 🤖 Fine-tuning for Chatbots
  • ⚖️ Tradeoffs and Considerations
    • 💰 Compute and Cost Constraints
    • 🧠 Catastrophic Forgetting
    • 🔄 Overfitting to Instruction Style
  • 🧪 Evaluation Best Practices
    • 🧠 Task-specific Metrics
    • 🔍 Manual Review of Generations
    • 📊 Comparing Baseline vs. Fine-tuned
  • 🔚 Closing Notes
    • 🧭 Summary and When to Fine-tune
    • 🚀 Next Up: Hugging Face Workflows (07)
    • 🧠 What to Try on Your Own

🧠 Why Fine-tune a Language Model?¶

🔄 Prompting Limitations¶

🎯 Use Cases for Fine-tuning¶

🧠 Behavioral vs. Task-Specific Tuning¶

Back to the top

⚙️ Types of Fine-tuning¶

🧰 Full Fine-tuning¶

🧱 Adapter-based Tuning¶

🧪 LoRA (Low-Rank Adaptation)¶

🎛️ Prefix/Prompt Tuning¶

Back to the top

🛠️ Fine-tuning Pipeline Overview¶

📄 Data Collection and Formatting¶

🧹 Preprocessing and Tokenization¶

🔧 Training Setup and Config¶

📉 Evaluation and Checkpoints¶

Back to the top

📦 Tools and Frameworks¶

🤗 Hugging Face Transformers + Datasets¶

🧠 PEFT (Parameter-Efficient Fine-Tuning)¶

🧪 OpenLLM, Axolotl, LoRA Libraries¶

Back to the top

📊 Case Studies / Example Walkthroughs¶

📄 Fine-tuning for Text Classification¶

💬 Fine-tuning for Q&A¶

🤖 Fine-tuning for Chatbots¶

Back to the top

⚖️ Tradeoffs and Considerations¶

💰 Compute and Cost Constraints¶

🧠 Catastrophic Forgetting¶

🔄 Overfitting to Instruction Style¶

Back to the top

🧪 Evaluation Best Practices¶

🧠 Task-specific Metrics¶

🔍 Manual Review of Generations¶

📊 Comparing Baseline vs. Fine-tuned¶

Back to the top

🔚 Closing Notes¶

🧭 Summary and When to Fine-tune¶

🚀 Next Up: Hugging Face Workflows¶

🧠 What to Try on Your Own¶

Back to the top