Ramesh Sampath
@sampathweb
ML Engineer. Previously @landingAI @lilyai_ @fivestars @insightfellows
You might like
This is the quote I come back to for motivation when I am not happy with what I am making. - vimeo.com/24715531 - goodreads.com/author/quotes/… Thank you @iraglass
As I bid farewell to India after serving as the 26th U.S. Ambassador to this amazing country, my heart is full. You’ve given me a second home, a family of friends, and memories that will last a lifetime. Today, I leave as more than an ambassador—I leave as a lifelong friend and…
Here's the table of contents for my end-of-year review of things we learned out about LLMs in 2024 - we learned a LOT
Life lessons from @rogerfederer (must watch) 1 Effortless is a myth 2 Belief in yourself has to be earned 3 Grit > Gift 4 Discipline is talent 5 Trust and loving the process is talent 6 You can do your best and still lose 7 Life is bigger than the court
New Keras starter notebook from @awsaf49 for the "LMSYS Chatbot Arena Human Preference" competition on Kaggle. This one is interesting for how it achieves preference classification over pairs of (prompt+response) using the DeBERTaV3 model from KerasNLP. kaggle.com/code/awsaf49/l…
If you missed it, this I/O session on LLMs with Keras 3 is a great tutorial on LLM training and fine-tuning best practices youtu.be/TV7qCk1dBWA
youtube.com
YouTube
Large language models with Keras
Presented our team project "CityHub" in the @Meta #Llama3Hackathon at @SHACK15sf. It is an AI-powered conversational assistant that provides personalized information on San Francisco city services, aiding residents and visitors in navigating government websites.
8/ City Hub Llama3 powered chat agent that lets residents ask questions about city laws and regulations. RAG’s over city documents to inform the answers Chat with your city
New Kaggle starter notebook from @awsaf49 for the Automated Essay Scoring competition: kaggle.com/code/awsaf49/a…. It showcases the right way to do ordinal regression in Keras, i.e. how to predict ordered integer grades reliably (no it's neither a classification, nor regression!)
🎥 Check out the details of our recent Keras integration with @fchollet and @MeganRisdal!
Keras 3 makes switching DL frameworks a env. variable setting and the rest of the code works the same. Nice example using LM and StableDiffusion. Excited to try it out.
Good looking Jax coders! Seriously, this is a Keras 3.0 demo, runnig KerasCV and KerasNLP generative models on Jax, TensorFlow or PyTorch. colab.research.google.com/drive/1tlQ8xOA… It also shows how to install everything.
Excited to have framework optionality with the familiar Keras API, where simple usecases are easy and complex usecases are made possible!
Big news: we just released Keras 3.0! ▶ Run Keras on top of JAX, TensorFlow, and PyTorch ▶ Train faster with XLA compilation ▶ Unlock training runs with any number of devices & hosts via the new Keras distribution API It's live on PyPI now! 🚀
Donald Knuth advice to young engineers - - Follow your own instincts. - Prestige comes from doing good science, not just popular science. - Deep knowledge builds confidence. - A liberal education involves learning everything about something and something about everything.
How to become an expert at any thing 🙏 I rediscovered this gem by @karpathy in my bookmarks today
Large Language Models Explained - At a High Level LLMs such as GPT-4, Bard and LLama appear magical and have displayed emergent human-like intelligence Fundamentally, the work on a pretty simple principle - next-word prediction. An LLM, uses something called conditional…
The Question You Must Ask Yourself 🤔🎯 youtube.com/shorts/aF_a--8… via @YouTube
We're launching Keras Core, a new library that brings the Keras API to JAX and PyTorch in addition to TensorFlow. It enables you to write cross-framework deep learning components and to benefit from the best that each framework has to offer. Read more: keras.io/keras_core/ann…
The University of Toronto made a video for a non technical audience in which I explain how deep learning works, the enormous promise of this technology and some of the potential risks. youtu.be/-9cW4Gcn5WY
youtube.com
YouTube
The Godfather in Conversation: Why Geoffrey Hinton is worried about...
Emerging LLM Application Stack! 👌 This write up by @a16z is one of the best and most pragmatic on the topic. I would even call this a perfect complimentary to @karpathy’s State of GPT talk. The post goes beyond just covering architectural overview to the why, alternative…
GPT in 60 Lines of NumPy -- a simple yet complete technical introduction to the GPT as an educational tool. jaykmody.com/blog/gpt-from-… I love this! It reminds me why coding in Python can be so much fun!
Announcement: the new Keras model saving format is available in tf-nightly. This format is aimed at reloading the exact same Python object, in a safe way (it does not rely on bytecode or pickling at all). In the future, the TF SavedModel format will be for inference-only export.
New tutorial on keras.io: use Textual Inversion to teach StableDiffusion about a new visual concept (such as a specific character) to generate more images featuring the same concept. keras.io/examples/gener…
United States Trends
- 1. Slot 94.1K posts
- 2. Delap 17.5K posts
- 3. Powell 69K posts
- 4. Gittens 20.8K posts
- 5. Sonya Massey 14.4K posts
- 6. Metchie 3,936 posts
- 7. $META 33.3K posts
- 8. Jennifer Welch 16.4K posts
- 9. Pierre Robert 2,187 posts
- 10. Michael Carter 5,176 posts
- 11. Magic 327K posts
- 12. #CarabaoCup 24.2K posts
- 13. Crystal Palace 43.4K posts
- 14. Merino 11.6K posts
- 15. #NationalCatDay 5,725 posts
- 16. Welcome to Philly N/A
- 17. Woodward 7,607 posts
- 18. Jeff Landry 2,256 posts
- 19. Anfield 13.1K posts
- 20. Richarlison 3,139 posts
You might like
-
Lisha
@lishali88 -
Machine Learning Mastery
@TeachTheMachine -
Yisong Yue
@yisongyue -
Max Sklar
@maxsklar -
Justin Herman
@JustinHerman -
Chelsea Finn
@chelseabfinn -
Oriol Vinyals
@OriolVinyalsML -
Hilary Mason
@hmason -
Aurélien Geron
@aureliengeron -
Tuana
@tuanacelik -
caroline sinders
@carolinesinders -
Xavier Bresson
@xbresson -
Ryan R. Rosario
@DataJunkie -
Aman Arora
@amaarora -
Michael Bronstein
@mmbronstein
Something went wrong.
Something went wrong.