Hands on Large language models (LLMs) are remarkably effective at generating text and regurgitating information, but they're ultimately limited by the corpus of data they were trained on.
Fine-tuning is a useful way of modifying the behavior or style of a pre-trained model. However, if your goal is to teach the model new information, you need to provide a specific dataset.
Training Meta's relatively small Llama 3 8B model required the equivalent of 1.3 million GPU hours when running on 80GB Nvidia H100s.
Thanks to advancements like Low Rank Adaptation (LoRA) and its quantized variant QLoRA, it's possible to fine-tune models using a single GPU.
Collection
[
|
...
]