➡️ Get Life-time Access to the complete scripts (and future improvements): [ Ссылка ]
➡️ Runpod one-click fine-tuning template (affiliate link, supports Trelis' channel): [ Ссылка ] (see [ Ссылка ] for full setup)
➡️ Trelis Livestreams: Thursdays 5 pm Irish time on YouTube and X.
➡️ Newsletter: [ Ссылка ]
➡️ Resources/Support/Discord: [ Ссылка ]

VIDEO RESOURCES:
- Slides: [ Ссылка ]
- Unsloth GitHub: [ Ссылка ]
- Dataset: [ Ссылка ]

TIMESTAMPS:
0:00 Comparing full fine-tuning and LoRA fine tuning
1:57 Video Overview
3:53 Comparing VRAM, Training Time + Quality
8:42 How full fine-tuning works
9:03 How LoRA works
10:35 How QLoRA works
12:45 How to choose learning rate, rank and alpha
20:13 Choosing hyper parameters for Mistral 7B fine-tuning
21:39 Specific tips for QLoRA, regularization and adapter merging.
26:16 Tips for using Unsloth
27:46 LoftQ - LoRA aware quantisation
30:39 Step by step TinyLlama QLoRA
47:05 Mistral 7B Fine-tuning Results Comparison
52:29 Wrap up

свернуть