Ashvanth.S
@ashvanths.bsky.social
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
Website : https://ash-01xor.github.io/
X : https://twitter.com/ashvanth_s1
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.
It's about being steady and focused.
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 :).
Introducing sollu : AI-powered dictionary. Uses the Gemini model under the hood. It is open-sourced as well :).
May 11, 2025 at 4:23 PM
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 :).
Introducing sollu : AI-powered dictionary. Uses the Gemini model under the hood. It is open-sourced as well :).
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.
Humbled each and every day to understand and accept and that it is how it is.
February 26, 2025 at 2:09 PM
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.
Humbled each and every day to understand and accept and that it is how it is.
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
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.
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.
February 26, 2025 at 2:40 AM
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
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.
Guess the goal is to build systems that can make sure we enter such states like on and off button.
February 19, 2025 at 12:17 PM
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.
Guess the goal is to build systems that can make sure we enter such states like on and off button.
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 ?
Do you guys want me to run benchmark tests and probably write a blog post about it ?
February 13, 2025 at 10:59 AM
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 ?
Do you guys want me to run benchmark tests and probably write a blog post about it ?
Looking forward to the next unit of the Agents course and building more @benburtenshaw.bsky.social @hf.co
February 13, 2025 at 4:30 AM
Looking forward to the next unit of the Agents course and building more @benburtenshaw.bsky.social @hf.co
Reposted by Ashvanth.S
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
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
February 5, 2025 at 1:46 PM
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
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
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.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
February 3, 2025 at 5:52 PM
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.com/ash-01xor/Re...
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
Had to use pyenv and then pip. like now i get why experienced devs are frustrated with python package management
February 3, 2025 at 1:14 PM
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
Had to use pyenv and then pip. like now i get why experienced devs are frustrated with python package management
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 :)
February 2, 2025 at 2:29 PM
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 :)
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
Do join the initiative alongside me , your contribution is highly valuble
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-...
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-...
January 7, 2025 at 12:03 PM
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
Do join the initiative alongside me , your contribution is highly valuble
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'.
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'.
January 7, 2025 at 12:01 PM
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'.
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'.
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 ??
How does the for loop work when i present the number inside range like that ??
January 5, 2025 at 5:09 PM
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 ??
How does the for loop work when i present the number inside range like that ??
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...
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
December 30, 2024 at 2:51 AM
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...
Do join if you would like to contribute!
data-is-better-together-fineweb-c.hf.space/share-your-p...
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 .
December 23, 2024 at 2:50 PM
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 .
got to read that alec radford left open ai , like what is even happening at open ai
December 20, 2024 at 1:38 PM
got to read that alec radford left open ai , like what is even happening at open ai
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 ..
Like while recruiting , where folks are given standard questions to solve or ..
December 17, 2024 at 12:45 PM
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 ..
Like while recruiting , where folks are given standard questions to solve or ..
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...
@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
December 14, 2024 at 7:33 AM
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...
@hf.co
data-is-better-together-fineweb-c.hf.space/share-your-p...
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...
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
December 13, 2024 at 7:38 AM
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...
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...
Its been great few weeks reading about agents after going through the course conducted by Berkeley. While there was lots of insightful talks , one that was particularly insightful was on week 4 , where Burak Gokturk got to talk about enterprise trends about agents.
The most important trend...
The most important trend...
December 12, 2024 at 4:45 PM
Its been great few weeks reading about agents after going through the course conducted by Berkeley. While there was lots of insightful talks , one that was particularly insightful was on week 4 , where Burak Gokturk got to talk about enterprise trends about agents.
The most important trend...
The most important trend...
coding when someone is watching is quite a nervous experience. all of sudden there is quite a bit of fumbling , struggling to come up with names..
December 12, 2024 at 11:05 AM
coding when someone is watching is quite a nervous experience. all of sudden there is quite a bit of fumbling , struggling to come up with names..
Introducing Maya – A New Multimodal Multilingual Vision-Language Model. Maya is a completely open source, open weight, and open dataset, designed to handle 8 languages, cultural diversity, and nuanced real-world contexts in vision-language models.
Paper: arxiv.org/abs/2412.07112
Paper: arxiv.org/abs/2412.07112
Maya: An Instruction Finetuned Multilingual Multimodal Model
The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability...
arxiv.org
December 11, 2024 at 3:32 AM
Introducing Maya – A New Multimodal Multilingual Vision-Language Model. Maya is a completely open source, open weight, and open dataset, designed to handle 8 languages, cultural diversity, and nuanced real-world contexts in vision-language models.
Paper: arxiv.org/abs/2412.07112
Paper: arxiv.org/abs/2412.07112
Vanakkam makkalae , glad that I’ll be leading the FineWeb 2 collaborative annotation sprint for Tamil! 🤗
I’ll be helping to build an open dataset to improve language models for our language. Do join the process of improving models !
huggingface.co/spaces/Huggi...
huggingface.co/spaces/data-...
I’ll be helping to build an open dataset to improve language models for our language. Do join the process of improving models !
huggingface.co/spaces/Huggi...
huggingface.co/spaces/data-...
December 10, 2024 at 11:05 AM
Vanakkam makkalae , glad that I’ll be leading the FineWeb 2 collaborative annotation sprint for Tamil! 🤗
I’ll be helping to build an open dataset to improve language models for our language. Do join the process of improving models !
huggingface.co/spaces/Huggi...
huggingface.co/spaces/data-...
I’ll be helping to build an open dataset to improve language models for our language. Do join the process of improving models !
huggingface.co/spaces/Huggi...
huggingface.co/spaces/data-...
Weekend was quite cool , got to just keep my head down and work on retrieval engines over a custom database. Implemented thing right from TF-IDF to RAG and saw quite some interesting things.
Anyone who says TF-IDF is not the best must need to implement it and check it first...
Anyone who says TF-IDF is not the best must need to implement it and check it first...
December 9, 2024 at 2:44 AM
Weekend was quite cool , got to just keep my head down and work on retrieval engines over a custom database. Implemented thing right from TF-IDF to RAG and saw quite some interesting things.
Anyone who says TF-IDF is not the best must need to implement it and check it first...
Anyone who says TF-IDF is not the best must need to implement it and check it first...