Welcome to the torchtune Documentation¶

torchtune is a Native-PyTorch library for LLM fine-tuning.

Getting Started¶

Topics in this section will help you get started with torchtune.

What is torchtune?

A gentle introduction to torchtune and how you can use the library in your projects.

Installation instructions

A step-by-step tutorial on how to install torchtune.

Finetune your first model

Follow a simple tutorial to finetune Llama2 with torchtune.

Ready to experiment? Check out some of the interactive torchtune tutorials.

Topics: finetuning,llama3

Topics: finetuning,llama2,lora

Parameter-efficient finetuning of Llama2 using LoRA

Topics: finetuning,llama2,qlora

Using QLoRA to quantize base model weights and maximize memory savings

Topics: finetuning,quantization,inference,evals,llama2

Train, Evaluate, Quantize and then Generate with your LLM.