A container for all my views with excerpts from technology, travel, films, books, kannada, friends and other interests. I am Thejesh GN, friends call me Thej.
Table of Contents1 Open Weight Models1.1 nomic-embed-text-v2-moe1.2 paraphrase-multilingual1.3 bge-m31.4 snowflake-arctic-embed22 OpenAI Model2.1 text-embedding-3-large Embedding models transform words, sentences, documents, or digital items into vectors of numbers (usually floats) so that machines can understand and compare them semantically1. A good embedding model has enough information to capture the meaning and relationships in dense vector...
I have been searching for models that perform translations between Kannada and English and vice versa. I learned about the Sarvam Translate model, which seemed very promising. I tried it on their site before downloading the model directly to run locally. Model weights are available under GPL. Sarvam-Translate is an advanced translation model...
Nammooral techu (ನಮ್ಮೂರಲ್ ಟೆಕ್ಕು) is the new project I am involved with. Idea is to translate technology jargons to Kannada, build vocabulary etc. In a way start discussions around it in Kannada. From the about page ಇದು ಟೆಕ್ (ಐಸಿಟಿ, ಡೇಟ ಇತ್ಯಾದಿ)ಗೆ ಸಂಬಂಧಿಸಿದ ಕನ್ನಡ ಪದಗಳನ್ನು ಶಬ್ದಕೋಶಕ್ಕೆ ಸೇರಿಸುವ ನಮ್ಮ ಪ್ರಯತ್ನ. ಸದ್ಯಕ್ಕೆ, ಟೆಕ್ ಪದದ ಕನ್ನಡ ಅನುವಾದದೊಂದಿಗೆ...
This morning I was trying to print some maps in Kannada using Marble. Then to my surprise1 I found Philippines in English, which means there is no Kannada translation available. Then ran a simple query on Overpass to see the missing Kannada country names. The query prints the details in CSV format (separated...
For a while I have been using KDE Marble as my desktop map client. The project describes itself as “a virtual globe and world atlas — your swiss army knife for maps”. It can do a lot but I use it for my day today work like bookmarking areas, creating KML files etc....
Table of Contents1 Standards2 Unicode CLDR and ICU projects3 Transliteration4 How to type Accents and Symbols5 Footnotes Wikipedia says Transliteration is a type of conversion of a text from one script to another that involves swapping letters (thus trans- + liter-) in predictable ways. For Kannada we usually use Latin letters to represent1...
There are many ways to subscribe to this blog. Email is probably the best.
Thejesh GN (ತೇಜೇಶ್ ಜಿ.ಎನ್) "Thej" is an Independent Technologist, Hacker, Maker, Traveler, Blogger, InfoActivist, Open data and Open internet enthusiast from Bangalore, India. He loves experimenting with all things life and hence some times he is called hacker and other times duct tape. You can read more about him here. Email [ i @ thejeshgn dot com]. PGP/GPG Keys are here.
(C) Thejesh GN.The views expressed on this site are mine (Thejesh GN) alone and do not necessarily reflect the views of my employer. Please read the terms and conditions before reading or commenting on this blog.
