Lightnews — Scholar-powered news

Ashvanth.S

@ashvanths.bsky.social

58 followers 73 following 60 posts

Deep Learning Practitioner | Language Lead for Tamil @ HuggingFace | Interested in Continual Learning and Generative Models | Website : https://ash-01xor.github.io/ X : https://twitter.com/ashvanth_s1

ash-01xor.github.io

Posts Media Videos Starter Packs

Pinned

Ashvanth.S @ashvanths.bsky.social · Nov 28

Feel like i wish i can do too many things that I'm interested in , but got to remind myself to focus on few things at a time.

It's about being steady and focused.

Ashvanth.S @ashvanths.bsky.social · May 11

Have you ever felt like you lost your focus while reading a book and wandered into deep internet rabbit holes?

Introducing sollu : AI-powered dictionary. Uses the Gemini model under the hood. It is open-sourced as well :).

Ashvanth.S @ashvanths.bsky.social · Feb 26

Quite a humbling experience every day while coding. You start with an issue and a vision about how to solve the problem and then pretty much the road traveled often to reach the solution isn't straightforward.

Humbled each and every day to understand and accept and that it is how it is.

Ashvanth.S @ashvanths.bsky.social · Feb 26

Pretty similar to how Jio first gained share of the internet users in India. Interesting to note big companies have the ability to shell out too much to develop and operate to gain market share. Only time shall tell what this will lead to

Gergely Orosz @gergely.pragmaticengineer.com · Feb 25

Wild how the price of AI functionality that costs $$$ to develop and $$ to operate is being subsidized to zero - to gain market share.

By Google making this move: expect Microsoft to follow, and AI coding startups having little to no choice but to also offer generous free tiers.

Ashvanth.S @ashvanths.bsky.social · Feb 19

Ahh finally a blog post from you , it is quite difficult to maintain a site right like publishing frequent posts

Ashvanth.S @ashvanths.bsky.social · Feb 19

Over a period of time , getting to realize that im having my flow states during certain periods of time and getting to schedule tasks around it.
Guess the goal is to build systems that can make sure we enter such states like on and off button.

Ashvanth.S @ashvanths.bsky.social · Feb 13

Not able to point of the difference particularly , but gpt-4o-mini seems to work way too fast over the last day. From taking around 4 to 5 mins to process a 65-page PDF for extraction, it takes around 3 mins.

Do you guys want me to run benchmark tests and probably write a blog post about it ?

Ashvanth.S @ashvanths.bsky.social · Feb 13

Looking forward to the next unit of the Agents course and building more @benburtenshaw.bsky.social @hf.co

Reposted by Ashvanth.S

Sebastian Raschka (rasbt) @sebastianraschka.com · Feb 5

I just finished writing up my take on reasoning models: magazine.sebastianraschka.com/p/understand...
Here, I
1. Discuss the advantages & disadvantages of reasoning models
2. Of course, describe and discuss DeepSeek R1
3. Describe the 4 main ways to building & improving reasoning models

Understanding Reasoning LLMs

Methods and Strategies for Building and Refining Reasoning Models

magazine.sebastianraschka.com

3 21 93

Ashvanth.S @ashvanths.bsky.social · Feb 3

Slowly building it one at a time. Thanks to @sebastianraschka.com for his book. Implementing things from scratch takes a lot of time , but valuable experience.
github.com/ash-01xor/Re...

GitHub - ash-01xor/Rebuild-LLM: Building Large language model from scratch

Building Large language model from scratch. Contribute to ash-01xor/Rebuild-LLM development by creating an account on GitHub.

github.com

Ashvanth.S @ashvanths.bsky.social · Feb 3

Building SmolGPT myself , have plans to extend it. but before that struggling with managing python versions !!!

Had to use pyenv and then pip. like now i get why experienced devs are frustrated with python package management

Ashvanth.S @ashvanths.bsky.social · Feb 2

Updated my site after quite a long time also added a note for how to update your arch linux system. Do check it out if you use arch or if you like to as well :)

Ashvanth.S @ashvanths.bsky.social · Jan 7

Only a few more annotations are needed to complete the initial goal. for Tamil.
Do join the initiative alongside me , your contribution is highly valuble

Daniel van Strien @danielvanstrien.bsky.social · Jan 6

The finish line is near! We're building FineWeb-Edu for many languages and need your help 🤗

Many FineWeb-C languages are close to 1,000 annotations!

Assamese is 99.4% done, French needs 64 more annotations, Tamil: 216.

Please help us reach the goal: huggingface.co/spaces/data-...

Progress bars showing remaining annotations needed for 15 languages in FineWeb-C dataset, ranging from 6 to 593 annotations needed

Ashvanth.S @ashvanths.bsky.social · Jan 7

Interesting to see the hype of agents and using them , but almost everyone who uses the term throws it away just like that.
All I get to see is a clearly well-defined workflow in a constrained environments most of the time and yet they are being called 'agents'.

Ashvanth.S @ashvanths.bsky.social · Jan 5

Got to find this today only in Python when i made a typo by mistake.
How does the for loop work when i present the number inside range like that ??

Ashvanth.S @ashvanths.bsky.social · Jan 1

Happy new year sebastian !! was waiting for the post

Ashvanth.S @ashvanths.bsky.social · Dec 30

Well, we are halfway through our initial goal of the Fineweb-C sprint for Tamil. Hopefully I would love to complete the initial goal of annotating 1000 texts within the next two days

Do join if you would like to contribute!

data-is-better-together-fineweb-c.hf.space/share-your-p...

tam - தமிழ் - Tamil

Join and contribute to the dataset tam - தமிழ் - Tamil

data-is-better-together-fineweb-c.hf.space

Ashvanth.S @ashvanths.bsky.social · Dec 23

Since being used to python development from the start i dont think i never had an issue using pyenv , venv , conda etc. Like it never felt like a chore. But then hearing about devs from other communities really does make me question why .

Ashvanth.S @ashvanths.bsky.social · Dec 20

got to read that alec radford left open ai , like what is even happening at open ai

Ashvanth.S @ashvanths.bsky.social · Dec 17

which in itself is based on the success of their previous films.
As risks taken decreases due to a formulaic process , so does the excitement and the curiosity.

Ashvanth.S @ashvanths.bsky.social · Dec 17

the big names present in the resume is overlooked as a factor of judgement for their talent or in making films where rather than the concept or story , the focus shifts to the kind of artists brought in to play the characters , their star power and influence to bring audience to theaters ...

Ashvanth.S @ashvanths.bsky.social · Dec 17

Somehow deep down i always get to think about how optimization of any process leads to boredom over a period of time. The excitement and the risks once taken might decreases due to the numbers the clouds our judgement.

Like while recruiting , where folks are given standard questions to solve or ..

Ashvanth.S @ashvanths.bsky.social · Dec 14

Big thanks to @dvilasuero.hf.co , @nataliaelv.hf.co and team 🙌. Would love to see more people join this effort

Ashvanth.S @ashvanths.bsky.social · Dec 14

Well, around 10 percent of the initial goal is complete, and so far, it's been quite a one-man army effort. We're still in the hunt for more people to join and contribute to this open-source initiative.

@hf.co

data-is-better-together-fineweb-c.hf.space/share-your-p...

tam - தமிழ் - Tamil

Join and contribute to the dataset tam - தமிழ் - Tamil

data-is-better-together-fineweb-c.hf.space

1 1 4

Ashvanth.S @ashvanths.bsky.social · Dec 13

The process has just begun, and we are actively seeking collaborators for Tamil. Join us in this open-source initiative!

Building better models demands a better annotation process, and we are deeply committed to achieving this together

data-is-better-together-fineweb-c.hf.space/share-your-p...

tam - தமிழ் - Tamil

Join and contribute to the dataset tam - தமிழ் - Tamil

data-is-better-together-fineweb-c.hf.space

Ashvanth.S @ashvanths.bsky.social · Dec 12

While these are like the summary of what he considers to be the trends going on right now , interesting to note how it might span out in the future.

Looking forward to building now !