FR
Back to portfolio
Section 7

Fine-Tuning

Specializing Large Language Models (LLMs) using Low-Rank Adaptation (LoRA) and PEFT techniques.

Projects in this section: 0

Bloomz LoRA Fine-Tuning
Fine-TuningLocal path

Bloomz LoRA Fine-Tuning

Applied PEFT on a Large Language Model.

Open project
LoRA from Scratch
Fine-TuningLocal path

LoRA from Scratch

Understanding Low-Rank Adaptation at the tensor level.

Open project
LoRA Implementation (PyTorch)
Fine-TuningLocal path

LoRA Implementation (PyTorch)

Custom adapter implementation.

Open project
QA Model Fine-Tuning (Haystack)
Fine-TuningLocal path

QA Model Fine-Tuning (Haystack)

Domain adaptation for Question Answering.

Open project