YZ Sözlüğü

Yapay zeka modellerinin metni işlemek ve faturalandırmak için kullandığı temel birim.

Bir modelin tek bir istekte işleyebileceği maksimum token sayısı.

Büyük miktarda metin verisiyle eğitilmiş, insan benzeri metin üretebilen yapay sinir ağı.

A large pre-trained model that serves as the base for many downstream applications.

Eğitilmiş bir yapay zeka modelinin yeni girdiler için çıktı üretme süreci.

The text output generated by a language model in response to a prompt.

Yapay zeka modelinden en iyi çıktıyı almak için girdileri tasarlama sanatı ve bilimi.

An instruction block sent before the conversation that configures model behavior.

Kelimelerin veya metinlerin anlamlarını temsil eden çok boyutlu sayısal vektörler.

A sampling parameter that controls the randomness of model outputs.

A sampling strategy that limits token selection to the smallest set covering a cumulative probability threshold.

Delivering model output token-by-token as it is generated rather than waiting for the full response.

The time between sending a request and receiving the first token of a response.

The number of tokens or requests a model can process per second.

Modeli harici bir bilgi bankasından gelen gerçek zamanlı verilerle besleme tekniği.

A database optimized for storing and searching high-dimensional embedding vectors.

Search that retrieves results based on meaning rather than exact keyword matching.

Prompting a model to perform a task without providing any examples.

Providing a small number of input-output examples in the prompt to guide the model.

A prompting technique that instructs the model to reason step-by-step before answering.

An LLM-powered system that autonomously takes actions in pursuit of a goal.

The ability for a model to call external functions or APIs to retrieve data or take actions.

The date beyond which a model has no training data and is unaware of events.

The algorithm that converts raw text into a sequence of tokens for a language model.

The per-million-token cost charged for tokens in your prompt.

The per-million-token cost charged for tokens the model generates.

A provider feature that stores a reusable prefix in memory to avoid re-processing repeated tokens.

Submitting requests asynchronously in bulk for a 50% price discount.

An architecture where only a subset of model parameters is activated per token.

The neural network architecture underlying virtually all modern LLMs.

The core operation in transformers that lets each token attend to all other tokens.

Compressing model weights to lower numerical precision to reduce memory and speed up inference.

A model that can process and generate multiple types of data, such as text and images.

A learnable weight in a neural network; model size is measured in billions of parameters.

The standard unit for expressing model scale, where larger usually means more capable.

A model variant that produces explicit step-by-step thinking before answering.

Önceden eğitilmiş bir modeli belirli bir görev veya veri kümesi için özelleştirme işlemi.

The initial large-scale training phase where a model learns language from massive text corpora.

Fine-tuning a model on examples of instructions paired with ideal responses.

Reinforcement Learning from Human Feedback — training models to align with human preferences.

Yapay zekanın doğru olmayan veya uydurma bilgileri gerçekmiş gibi üretmesi.

Connecting model responses to verified, real-world information sources.

The field of ensuring AI systems behave according to human values and intentions.

Anthropic's method of training models to self-critique and revise outputs using a set of principles.

An attack where malicious text in the environment overrides a model's instructions.

The discipline of building AI systems that are reliably beneficial and avoid harmful outputs.

Massive Multitask Language Understanding — a benchmark testing knowledge across 57 academic subjects.

A coding benchmark measuring a model's ability to write correct Python functions from docstrings.

A metric of how well a language model predicts a sample of text — lower is better.