Skip to main content

Different types of tokens used in Generative AI use cases

 

Token TypeDescriptionUse CasesExamples
Word TokensRepresent individual words in the textLanguage modeling, text generation, machine translationExample: "cat," "dog," "house"
Subword TokensRepresent smaller text units like subwordsHandling complex word structures, text generationExample: "un-" (as in "undo"), "happi" (from "happiness")
Character TokensRepresent individual characters in the textText generation, handwriting recognition, OCRExample: "A," "b," "7"
Byte TokensTreat each byte of text as a separate tokenText encoding, binary data analysisExample: "01011010," "1A," "FF"
Special TokensUsed for various purposes (e.g., [CLS], [SEP])Start/end markers, padding, segment separationExample: [CLS] (classification start), [SEP] (sequence separation)
Position TokensIndicate the position of tokens in a sequenceTransformer models for positional awarenessExample: [POS_1], [POS_2], [POS_3]
Mask TokensMask out tokens to be ignored in operationsMasked language modeling, information retrievalExample: [MASK], [PAD]
Entity TokensRepresent recognized entities in the textNamed entity recognition (NER), information extractionExample: [ORG], [PERSON], [LOCATION]
Image TokensRepresent image features or captionsMultimodal models, image-text interactionExample: [IMG_FEATURES], [CAPTION]
Custom TokensDomain-specific tokens for specific tasksCode generation, medical text analysis, specialized NLPExample: [FUNCTION], [DIAGNOSIS], [LAW]
Labels:

Comments

Post a Comment

Popular posts from this blog

How are vector databases used?

  Vector Databases Usage: Typically used for vector search use cases such as visual, semantic, and multimodal search. More recently, they are paired with generative AI text models for conversational search experiences. Development Process: Begins with building an embedding model designed to encode a corpus (e.g., product images) into vectors. The data import process is referred to as data hydration. Application Development: Application developers utilize the database to search for similar products. This involves encoding a product image and using the vector to query for similar images. k-Nearest Neighbor (k-NN) Indexes: Within the model, k-nearest neighbor (k-NN) indexes facilitate efficient retrieval of vectors. A distance function like cosine is applied to rank results by similarity.
Post a Comment
Read more

Error: could not find function "read.xlsx" while reading .xlsx file in R

Got this during the execution of following command in R > dat <- colindex="colIndex," endrow="23," file="NGAP.xlsx" header="TRUE)</p" read.xlsx="" sheetindex="1," startrow="18,"> Error: could not find function "read.xlsx" Tried following command > install.packages("xlsx", dependencies = TRUE) Installing package into ‘C:/Users/amajumde/Documents/R/win-library/3.2’ (as ‘lib’ is unspecified) also installing the dependencies ‘rJava’, ‘xlsxjars’ trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.2/rJava_0.9-8.zip' Content type 'application/zip' length 766972 bytes (748 KB) downloaded 748 KB trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.2/xlsxjars_0.6.1.zip' Content type 'application/zip' length 9485170 bytes (9.0 MB) downloaded 9.0 MB trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.2/xlsx_0.5.7.zip&
Post a Comment
Read more

Feature Engineering - What and Why

Feature engineering is a crucial step in the machine learning pipeline where you create new, meaningful features or transform existing features to improve the performance of your predictive models. It involves selecting, modifying, or creating features from your raw data to make it more suitable for machine learning algorithms. Here's a more detailed overview of feature engineering: Why Feature Engineering? Feature engineering is essential for several reasons: Improving Model Performance: Well-engineered features can significantly boost the predictive power of your machine learning models. Handling Raw Data: Raw data often contains noise, missing values, and irrelevant information. Feature engineering helps in cleaning and preparing the data for analysis. Capturing Domain Knowledge: Domain-specific insights can be incorporated into feature creation to make the model more representative of the problem. Common Techniques and Strategies: 1. Feature Extraction: Transforming raw data
Post a Comment
Read more