Vidyasagar Bhargava
@vidyasagarbhargava.bsky.social
Lead Data Scientist
#data #machinelearning #datascience #llm
#data #machinelearning #datascience #llm
Great News !
🎉 Big news! Google Colab now comes with Gradio pre-installed (v5.38)!
No more pip install gradio needed - just import and start building AI apps instantly.
Thanks to @GoogleColab team for making Gradio more accessible to millions of developers worldwide!
No more pip install gradio needed - just import and start building AI apps instantly.
Thanks to @GoogleColab team for making Gradio more accessible to millions of developers worldwide!
July 23, 2025 at 6:46 AM
Great News !
Current Weight : 84.8 Kgs
July 16, 2025 at 3:25 PM
Current Weight : 84.8 Kgs
Reposted by Vidyasagar Bhargava
Built a thing to solve my annoyance setting up Python + Quarto projects in Positron (& teaching others to do the same)
For anyone moving from .Rmd to .qmd who wants a cleaner on-ramp: meet Quoncierge.
🔗 github.com/lkwhite/Quoncierge
#positron #quarto #rstats #datascience #reproducibility #jupyter
For anyone moving from .Rmd to .qmd who wants a cleaner on-ramp: meet Quoncierge.
🔗 github.com/lkwhite/Quoncierge
#positron #quarto #rstats #datascience #reproducibility #jupyter
GitHub - lkwhite/Quoncierge: Automate initializing reproducible Quarto + Jupyter + GitHub projects
Automate initializing reproducible Quarto + Jupyter + GitHub projects - lkwhite/Quoncierge
github.com
July 8, 2025 at 6:01 PM
Built a thing to solve my annoyance setting up Python + Quarto projects in Positron (& teaching others to do the same)
For anyone moving from .Rmd to .qmd who wants a cleaner on-ramp: meet Quoncierge.
🔗 github.com/lkwhite/Quoncierge
#positron #quarto #rstats #datascience #reproducibility #jupyter
For anyone moving from .Rmd to .qmd who wants a cleaner on-ramp: meet Quoncierge.
🔗 github.com/lkwhite/Quoncierge
#positron #quarto #rstats #datascience #reproducibility #jupyter
Check out Vidyasagar Bhargava on Strava
strava.app.link/A27owlCaQUb
strava.app.link/A27owlCaQUb
strava.app.link
July 8, 2025 at 5:03 PM
Check out Vidyasagar Bhargava on Strava
strava.app.link/A27owlCaQUb
strava.app.link/A27owlCaQUb
Learning attention and transformers. Focus on below topics.
1. Attention and its types
2. Working of attention mechanism
3. Positional encoding and types
4. Layer norm and residual
1. Attention and its types
2. Working of attention mechanism
3. Positional encoding and types
4. Layer norm and residual
June 30, 2025 at 10:55 AM
Learning attention and transformers. Focus on below topics.
1. Attention and its types
2. Working of attention mechanism
3. Positional encoding and types
4. Layer norm and residual
1. Attention and its types
2. Working of attention mechanism
3. Positional encoding and types
4. Layer norm and residual
Why Attention Mechanism?
The attention mechanism was introduced to improve the performance of encoder-decoder architecture for machine translation task.
Traditional RNN struggle with long-range dependencies and Attention helps focus on relevant parts of the input sequence.
The attention mechanism was introduced to improve the performance of encoder-decoder architecture for machine translation task.
Traditional RNN struggle with long-range dependencies and Attention helps focus on relevant parts of the input sequence.
June 24, 2025 at 10:54 AM
Why Attention Mechanism?
The attention mechanism was introduced to improve the performance of encoder-decoder architecture for machine translation task.
Traditional RNN struggle with long-range dependencies and Attention helps focus on relevant parts of the input sequence.
The attention mechanism was introduced to improve the performance of encoder-decoder architecture for machine translation task.
Traditional RNN struggle with long-range dependencies and Attention helps focus on relevant parts of the input sequence.
For next few weeks I will be posting about my daily learning about Generative AI. It includes topics like attention mechanism, transformer architecture, distributed model training, training large language model from scratch, llm finetuning, RAG, reinforcement learning , Alignment.
June 23, 2025 at 8:07 PM
For next few weeks I will be posting about my daily learning about Generative AI. It includes topics like attention mechanism, transformer architecture, distributed model training, training large language model from scratch, llm finetuning, RAG, reinforcement learning , Alignment.
Thinking is difficult, thats why most people judge. - Carl Jung
June 13, 2025 at 6:02 PM
Thinking is difficult, thats why most people judge. - Carl Jung
Prayers
BREAKING: An Air India Boeing 787 plane traveling from Ahmedabad to London’s Gatwick airport has crashed, according to local media reports
Air India Boeing 787 From Ahmedabad to London Gatwick Crashes
An Air India Ltd. Boeing Co. 787 aircraft, traveling from Ahmedabad to London’s Gatwick airport, has crashed, according to local media reports.
bloom.bg
June 12, 2025 at 9:11 AM
Prayers
Reposted by Vidyasagar Bhargava
BREAKING: An Air India Boeing 787 plane traveling from Ahmedabad to London’s Gatwick airport has crashed, according to local media reports
Air India Boeing 787 From Ahmedabad to London Gatwick Crashes
An Air India Ltd. Boeing Co. 787 aircraft, traveling from Ahmedabad to London’s Gatwick airport, has crashed, according to local media reports.
bloom.bg
June 12, 2025 at 9:03 AM
BREAKING: An Air India Boeing 787 plane traveling from Ahmedabad to London’s Gatwick airport has crashed, according to local media reports
Nice
Understanding multi-agent handoffs
Handoffs are a central concept in multi-agent systems.
LangGraph swarm is built on them.
But, they can be hard to understand.
Here, we break-down the swarm handoff mechanism.
📽️:
youtu.be/WTr6mHTw5cM
Handoffs are a central concept in multi-agent systems.
LangGraph swarm is built on them.
But, they can be hard to understand.
Here, we break-down the swarm handoff mechanism.
📽️:
youtu.be/WTr6mHTw5cM
June 5, 2025 at 3:16 AM
Nice
Best course on langgraph !
When you're building conversational AI, things can get messy & hard to scale. But the LangGraph Python framework can help manage dialogue flow & keep your bots organized. In this course, you'll build five agents from scratch, learn how to integrate RAG, and more.
www.freecodecamp.org/news/learn-l...
www.freecodecamp.org/news/learn-l...
June 5, 2025 at 3:15 AM
Best course on langgraph !
Reposted by Vidyasagar Bhargava
You can finetune Llama-3.2-Vision-11B for free on Colab now!
Unsloth finetunes VLMs 2x faster, with 50% less VRAM, 6x longer context - with no accuracy loss.
Other VLMs like Qwen2-VL, Llava & Pixtral are supported.
Blog: unsloth.ai/blog/vision
Fine-tuning Colabs: docs.unsloth.ai/get-started/...
Unsloth finetunes VLMs 2x faster, with 50% less VRAM, 6x longer context - with no accuracy loss.
Other VLMs like Qwen2-VL, Llava & Pixtral are supported.
Blog: unsloth.ai/blog/vision
Fine-tuning Colabs: docs.unsloth.ai/get-started/...
Llama 3.2 Vision Fine-tuning with Unsloth
Fine-tune Meta's Llama 3.2 Vision, Llava, Qwen 2.5 Vision models open-source 2x faster via Unsloth! Beginner friendly.
unsloth.ai
November 21, 2024 at 7:14 PM
You can finetune Llama-3.2-Vision-11B for free on Colab now!
Unsloth finetunes VLMs 2x faster, with 50% less VRAM, 6x longer context - with no accuracy loss.
Other VLMs like Qwen2-VL, Llava & Pixtral are supported.
Blog: unsloth.ai/blog/vision
Fine-tuning Colabs: docs.unsloth.ai/get-started/...
Unsloth finetunes VLMs 2x faster, with 50% less VRAM, 6x longer context - with no accuracy loss.
Other VLMs like Qwen2-VL, Llava & Pixtral are supported.
Blog: unsloth.ai/blog/vision
Fine-tuning Colabs: docs.unsloth.ai/get-started/...
Reposted by Vidyasagar Bhargava
Thrilled to announce Boltz-1, the first open-source and commercially available model to achieve AlphaFold3-level accuracy on biomolecular structure prediction! An exciting collaboration with Jeremy, Saro, and an amazing team at MIT and Genesis Therapeutics. A thread!
November 17, 2024 at 4:20 PM
Thrilled to announce Boltz-1, the first open-source and commercially available model to achieve AlphaFold3-level accuracy on biomolecular structure prediction! An exciting collaboration with Jeremy, Saro, and an amazing team at MIT and Genesis Therapeutics. A thread!
Reposted by Vidyasagar Bhargava
🧠🤖 Do you have an ML background and want to learn a bit about #neuroscience? Check out our free online course!
We think neuro and ML both aim to understand intelligence, and so it's good to know a bit of both to inspire new ideas that neither field might find on their own.
neuro4ml.github.io
We think neuro and ML both aim to understand intelligence, and so it's good to know a bit of both to inspire new ideas that neither field might find on their own.
neuro4ml.github.io
Neuroscience for machine learners
A freely available short course on neuroscience for people with a machine learning background. Designed by Dan Goodman and Marcus Ghosh.
neuro4ml.github.io
November 14, 2024 at 3:17 PM
🧠🤖 Do you have an ML background and want to learn a bit about #neuroscience? Check out our free online course!
We think neuro and ML both aim to understand intelligence, and so it's good to know a bit of both to inspire new ideas that neither field might find on their own.
neuro4ml.github.io
We think neuro and ML both aim to understand intelligence, and so it's good to know a bit of both to inspire new ideas that neither field might find on their own.
neuro4ml.github.io
Reposted by Vidyasagar Bhargava
👇💗 Now testing out Gemini 1.5 Flash, Pro, and Flash-8B is as easy as modifying a few lines in your scripts!
Just released, hot off the press: Gemini model compatibility with the OpenAI library.
developers.googleblog.com/en/gemini-is...
Just released, hot off the press: Gemini model compatibility with the OpenAI library.
developers.googleblog.com/en/gemini-is...
November 8, 2024 at 8:55 PM
👇💗 Now testing out Gemini 1.5 Flash, Pro, and Flash-8B is as easy as modifying a few lines in your scripts!
Just released, hot off the press: Gemini model compatibility with the OpenAI library.
developers.googleblog.com/en/gemini-is...
Just released, hot off the press: Gemini model compatibility with the OpenAI library.
developers.googleblog.com/en/gemini-is...
Reposted by Vidyasagar Bhargava
🚨 5-Day GenAI course from Google !!!
5-Day Gen AI Intensive Course with Google
Join our 5-day course on Nov 11 - 15 designed to help you deeply understand some of the fundamental technologies and techniques behind Generative AI.
rsvp.withgoogle.com
November 6, 2024 at 7:03 PM
🚨 5-Day GenAI course from Google !!!