Tagged: Free and Open Source
English wasn’t my first/primary language. I attended a Kannada-medium school during my primary school years and switched to an English-medium school in high school. I caught up with it as I grew up speaking it with friends and then colleagues, as English is the primary language at work 1. Now that we are...
Welcome to the second half of 2025. How was the year so far for you? For me, it’s been mostly good, except for the radiculopathy and the rapid pace of the year. If the first half has gone by so quickly, I can’t imagine how fast the second will go. It usually feels...
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...
It’s that time of the year again. I am IITM/Chennai for Paradox 2025. I reached today. I will be there till Monday. If you’re around, we can grab a coffee. You already know how to reach me.
I listen to Music from my homelab server using Navindrome and several client apps. It works both when I am online and offline. But one of the things that you miss when you listen to local Music is discoverability. It’s not easy to find new, interesting Music unless you’re on one of those...