FINE-TUNING
Fine-Tuning 5 Chapters • Self-paced

LLM Fine-Tuning & Quantization

Execute QLora local training routines, compile weights to GGUF format, and evaluate parameter loss curves.

Start Learning Back to Courses

Course Syllabus

1

1. Converting Models to GGUF Local Run Format

Focus: How to convert huggingface model weights to GGUF format

Study Lesson
2

2. QLora 8B Single-GPU Training Pipelines

Focus: Fine-tune llama-3-8b using qlora on one 24gb gpu

Study Lesson
3

3. Synthetic Data Reasoner Loops via Unsloth

Focus: Fine-tuning local reasoning models using synthetic data generation

Study Lesson
4

4. Custom Loss Functions for Alignment Tuning

Focus: Implementing custom loss functions for alignment tuning algorithms

Study Lesson
5

5. Tracking VRAM Weight Degradation during Quantization

Focus: How to track parameter degradation during deep model quantization cycles

Study Lesson