Lightning AI Studios: Never set up a local environment again →

LLM Glossary

This comprehensive glossary is meant to demystify complex terms and empower you with a deeper understanding of the AI field.

A

Adapter

Adapter is a lightweight adaptation method that adds a small...

Alpaca

Alpaca is a model fine-tuned from the LLaMA 7B model...

Attention

An attention mechanism is a component used in large language...

C

Cosine Similarity

Cosine similarity is a measure used to determine the similarity...

E

Embeddings

Embeddings are dense, lower-dimensional representations of words, sentences, or other...

F

Falcon

Falcon is the latest open-source large language model released by Technology Innovation...

G

GPT-NeoX

GPT-NeoX-20B is a 20 billion parameter autoregressive language model trained...

GPTQ

GPTQ is a one-shot weight quantization method based on approximate...

I

Inference

Inference refers to the process of using a trained model...

Instruction Tuning

Instruction tuning, in the context of large language models, is...

L

LLaMA

LLaMA is a foundational large language model that has been...

LoRA

LoRA achieves parameter reduction in large language models by learning...

M

Multimodal learning

Multimodal learning models the combination of different types of data...

P

Prefix tuning

Prefix-tuning is a lightweight alternative to fine-tuning for natural language...

Pretraining

Pretraining an LLM involves training the model on a large,...

Prompt Engineering

Prompt engineering refers to the process of carefully designing and...

Prompt Tuning

Prompt-tuning is a cost-effective and efficient method for adapting an...

Q

QLoRA

QLoRA is a highly effective method for fine-tuning, which significantly...

Question answering model

Question answering is a natural language processing task where a...

R

RLHF

Reinforcement learning from human feedback (RLHF), also known as reinforcement...

S

Self-instruct

Self-instruct is a method that combines self-supervised learning and reinforcement...

semantic search

Semantic search is a search technique that aims to understand...

StableLM

StableLM is a series of language models from Stability AI...

T

Text Summarization

Text summarization is the process of condensing a longer piece...

Tokenization

Tokenization is the process of splitting text into smaller units...

Topic Modeling

Topic modeling is a statistical technique used to uncover latent...

Transformer

The Transformer is a neural network architecture introduced in the...