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

What is the difference between Elastic and Enterprise Redis w.r.t "Hybrid Query" capabilities

  We'll explore scenarios involving nested queries, aggregations, custom scoring, and hybrid queries that combine multiple search criteria. 1. Nested Queries ElasticSearch Example: ElasticSearch supports nested documents, which allows for querying on nested fields with complex conditions. Query: Find products where the product has a review with a rating of 5 and the review text contains "excellent". { "query": { "nested": { "path": "reviews", "query": { "bool": { "must": [ { "match": { "reviews.rating": 5 } }, { "match": { "reviews.text": "excellent" } } ] } } } } } Redis Limitation: Redis does not support nested documents natively. While you can store nested structures in JSON documents using the RedisJSON module, querying these nested structures with complex condi...
Post a Comment
Read more

Training LLM model requires more GPU RAM than storing same LLM

Storing an LLM model and training the same model both require memory, but the memory requirements for training are typically higher than just storing the model. Let's dive into the details: Memory Requirement for Storing the Model: When you store an LLM model, you need to save the weights of the model parameters. Each parameter is typically represented by a 32-bit float (4 bytes). The memory requirement for storing the model weights is calculated by multiplying the number of parameters by 4 bytes. For example, if you have a model with 1 billion parameters, the memory requirement for storing the model weights alone would be 4 GB (4 bytes * 1 billion parameters). Memory Requirement for Training: During the training process, additional components use GPU memory in addition to the model weights. These components include optimizer states, gradients, activations, and temporary variables needed by the training process. These components can require additional memory beyond just storing th...
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 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' Content type 'application/zip' length 400968 bytes (391 KB) downloaded 391 KB package ‘rJava’ successfully unpacked and MD5 sums checked package ‘xlsxjars’ successfully unpacked ...
Post a Comment
Read more