1/ LeanDojo – an open-source Lean playground consisting of toolkits, data, models, and benchmarks for theorem proving; also develops ReProver, a retrieval augmented LLM-based prover for theorem solving using premises from a vast math library.
RESEARCH
-
Extending LLM Context Windows to 32K with Minimal Fine-tuning
By
–
2/ Extending Context Window of LLMs – extends the context window of LLMs like LLaMA to up to 32K with minimal fine-tuning (within 1000 steps); attains good performance on several tasks while being more efficient and cost-effective.
-
Top Machine Learning Papers: LeanDojo, DragDiffusion, LLM Context
By
–
Top ML Papers of the Week (June 26 – July 2): – LeanDojo
– DragDiffusion
– Scaling MLPs
– Visual Navigation Transformer
– GPT-4 for Programming Education
– Extending Context Window of LLMs
… -
Tip #1: Learn Mathematics Alongside AI Development
By
–
It’s tip #1
I did not say start with maths.
But you should learn it along the way, it’s important. -
Following 70000 AI Accounts: Choosing Favorites Challenge
By
–
I follow 70,000 in AI and you are asking me to pick favorites?
-
Daily AI and Machine Learning Content: Python, NLP, Computer Vision
By
–
That's a wrap! If you interested in: – Python – Data Science – Machine Learning – Maths for ML – MLOps – NLP – Computer Vision – LLMs I'm sharing daily content over here, follow me → @akshay_pachaarif you haven't already!! Cheers!!
-
Understanding problems before solutions in AI development
By
–
Understand the problem before jumping onto solution. Staying close to the product & domain knowledge can help you find simpler solution to most complex problems. And this is the key!
-
Networking in Data Science: Events, Meetups and Best Practices
By
–
Networking Attend industry events, meetups & conferences to connect with folks in data science. You will learn about new tools, techniques & best-practices. Twitter is a great place to start! Here's my Elite-ml-list
-
Master Python Programming with CS50 Harvard Course
By
–
Become a strong programmer Programming helps you to bridge the gap between theory and building stuff that's useful. Python is the language data science community speaks! And CS50p is arguably the best place to learn Python. Check this out http://
cs50.harvard.edu/python/2022/ -
Master Mathematics Fundamentals for Machine Learning Success
By
–
Learn the fundamentals! It's important to have a strong foundation in mathematics, it helps you to stand out. Here's a great place to start https://
coursera.org/specialization
s/mathematics-machine-learning
…