Low-rank adaptation

As explained in Build a Large Language Model (From Scratch)

A parameter-efficient fine-tuning method that adapts a model by training low-rank updates instead of all weights.

Low-rank adaptation (LoRA) is a parameter-efficient fine-tuning method that adapts a language model by training low-rank updates instead of all model weights. section 7.8

Use LoRA to make instruction fine-tuning more efficient, then compare the modified run with the original:

• Modify an existing instruction-fine-tuning implementation to use LoRA. section 7.8
• Compare training runtime before and after applying the method. section 7.8
• Compare model performance using the evaluation procedure and scored responses. section 7.8

Parameter-efficient fine-tuning exercise

Apply LoRA to the instruction-fine-tuning code, run the resulting training workflow, and compare its runtime and model performance with the original full fine-tuning run. section 7.8

Figure 7.19 The three-stage process for instruction fine-tuning the LLM. In this last step of the instruction-fine-tuning pipeline, we implement a method to quantify the performance of the fine-tuned model by scoring the responses it generated for the test.

Use the instruction-fine-tuning evaluation pipeline to score generated responses and quantify performance differences between runs. section 7.8

How Build a Large Language Model (From Scratch) covers it

How deep it goes

Defines low-rank updates and assigns a runtime-versus-performance experiment, but does not detail the underlying implementation.

Examples

Uses a code-modification exercise comparing training runtime and model performance before and after LoRA.

What it assumes

Assumes an existing instruction-fine-tuning implementation and the ability to compare training runs and evaluation results.

What you can do after

Apply it via an existing fine-tuning implementation and evaluate its runtime and model-performance effects.

How it connects

Connects parameter-efficient fine-tuning with instruction fine-tuning and model evaluation.

liveBookmanning.com

Read Build a Large Language Model (From Scratch) on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  LLMs in ProductionLow-rank adaptation is a parameter-efficient fine-tuning method that adapts a pretrained model through trainable low-rank updates while leaving most original parameters fixed.
• 

  liveBookmanning.com
  Building Reliable AI SystemsLow-Rank Adaptation is a parameter-efficient fine-tuning method that trains added low-rank matrices while keeping a pretrained model's weights frozen.
• 

  liveBookmanning.com
  Introduction to Generative AI, Second EditionLow-rank adaptation is a parameter-efficient fine-tuning technique that trains low-rank update matrices while keeping most pretrained parameters fixed.
• 

  liveBookmanning.com
  Generative AI in ActionLow-rank adaptation is a parameter-efficient technique that adapts a pretrained model by training small low-rank matrices while leaving the original model weights frozen.
• 

  liveBookmanning.com
  Transformers in ActionA low-rank adapter is a parameter-efficient fine-tuning component that represents a weight update through low-rank factors.
• 

  liveBookmanning.com
  The Complete Obsolete Guide to Generative AILoRA is a parameter-efficient fine-tuning technique that adapts a pretrained model by learning low-rank updates rather than modifying all model parameters.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionLow-rank adaptation is a parameter-efficient fine-tuning technique that freezes a model's original weights and trains a low-rank update to selected projections.
• 

  liveBookmanning.com
  The AI Pocket BookA fine-tuning method that adds small trainable layers or low-rank updates while leaving the original model largely intact.

Compare how 9 books explain low-rank adaptation →

Related concepts

• parameter-efficient fine-tuningkind of · Parameter-efficient fine-tuning adapts a pretrained model by training a limited subset of its parameters or added components rather than all its parameters.
• QLoRAused by · QLoRA is a parameter-efficient fine-tuning method that quantizes a pretrained model’s weights while training low-rank adapters to reduce memory requirements.
• low-rank approximationuses · A low-rank approximation represents a matrix by a lower-rank matrix or factorization, often retaining important structure while reducing storage or computation.

This explainer was generated by Manning's knowledge graph from the text of Build a Large Language Model (From Scratch). The section links point to the parts of the book it draws on.