🏠 Home
Benchmark Hub
📊 All Benchmarks 🦖 Dinosaur v1 🦖 Dinosaur v2 ✅ To-Do List Applications 🎨 Creative Free Pages 🎯 FSACB - Ultimate Showcase 🌍 Translation Benchmark
Models
🏆 Top 10 Models 🆓 Free Models 📋 All Models ⚙️ Kilo Code
Resources
💬 Prompts Library 📖 AI Glossary 🔗 Useful Links

AI Glossary

The complete dictionary of Artificial Intelligence

162
categories
2,032
subcategories
23,060
terms
📖
terms

Low-rank matrices

Mathematical representation where a matrix is expressed as the product of two smaller matrices with reduced rank. This decomposition reduces the number of required parameters while capturing the essential information of transformations.

📖
terms

Memory efficiency

Optimization of RAM and VRAM usage during AI model training and inference. Techniques like LoRA drastically reduce memory consumption by limiting the modified parameters.

📖
terms

Trainable parameters

Subset of neural network weights that are actually modified during the learning process. In LoRA, only a small percentage (typically 0.1-1%) of total parameters are trainable.

📖
terms

Rank decomposition

Algebraic technique factoring a weight matrix W into W + BA where B and A are low-rank matrices. This decomposition forms the mathematical foundation of LoRA adaptation.

📖
terms

Efficient fine-tuning

Paradigm of adapting pre-trained models aiming to minimize computational and memory resources required. Methods like LoRA, Adapters or Prefix-tuning allow model specialization without modifying all their parameters.

📖
terms

PEFT (Parameter-Efficient Fine-Tuning)

Category of model adaptation techniques aiming to modify a minimum of parameters during fine-tuning. LoRA is one of the most popular PEFT approaches along with Adapters, Prefix-tuning and soft prompts.

📖
terms

Alpha scaling factor

Crucial hyperparameter in LoRA controlling the amplitude of adaptation applied to original weights. This scaling factor adjusts the relative influence of low-rank matrices compared to pre-trained weights.

📖
terms

Multi-LoRA

Architecture allowing simultaneous application of multiple specialized LoRA adaptations to the same base model. This approach facilitates rapid switching between different tasks or domains of expertise without full model reloading.

📖
terms

Zero-shot adaptation

Ability of a model adapted with LoRA to generalize to tasks or domains not seen during adaptation training. This property emerges from preserving the base model's general knowledge while adding targeted specializations.

📖
terms

LoRA rank hyperparameter

Parameter determining the dimension of the low-rank matrices in LoRA decomposition, controlling the trade-off between expressiveness and efficiency. Typical ranks range from 4 to 64 depending on the complexity of the adaptation task.

📖
terms

Weight merging

Process of integrating LoRA adaptations into the base model weights to eliminate computational overhead during inference. This merging allows recovering a standard model with the same performance as the adapted version.

🔍

No results found