Track 10: Training LLMs, Fine-Tuning Methods
Your First Fine-Tune on Colab (Instruction Tuning)
Instruction-tune a model and resume after disconnect.
Part of Train and Fine-Tune Models (29 of 45)
Get notified on YouTube Udemy certificate: coming soon
Course
Fine-Tune Your Own LLM (Free GPU, Step by Step)
Udemy: coming soon
Tools
- Unsloth (open-source, free)
- Google Colab (freemium)
- Hugging Face TRL (open-source, free)
Watch first
Then try
- Make It Better: Data, Hyperparameters, Continued Pre-training, Multi-GPU
- DPO Hands-On (and ORPO, KTO, Reward Models)
- Evaluate Your Fine-Tune Properly
- Quantization: GGUF, GPTQ, AWQ, bitsandbytes
- Distillation: Teach a Small Model From a Big One
- Fine-Tune Whisper for Indian Accents
In this module
- Full Fine-Tuning vs Parameter-Efficient (PEFT)
- LoRA Explained and Applied
- QLoRA: Bigger Models on Small GPUs
- Your First Fine-Tune on Colab (Instruction Tuning)
- Make It Better: Data, Hyperparameters, Continued Pre-training, Multi-GPU
The course this lesson belongs to