We introduced the ParentDocumentRetriever last week to strike a balance between: – using small chunks during indexing
– passing larger chunks to the LLM Great overview and diagram by @clusteredbytes
CODE
-
ParentDocumentRetriever balances chunk size for LLM optimization
By
–
-
Self-Attention Mechanism in Large Language Models: From Scratch
By
–
Understanding and Coding the Self-Attention Mechanism of Large Language Models From Scratch https://
bit.ly/3YL821l #AI #DeepLearning #MachineLearning #DataScience -
Stanford CS229 Machine Learning Course Syllabus Spring 2022
By
–
Stanford CS229: Machine Learning webpage: https://
cs229.stanford.edu/syllabus-sprin
g2022.html
… -
Stanford CS229: Machine Learning Course 2022 Now Available
By
–
Stanford CS229: Machine Learning, Spring 2022 CS229 is one of the best machine learning courses that provides a broad introduction to machine learning. The 2022 version was made available to the public recently. The course covers a wide range of topics from supervised learning,
-
API Key Security Enhancement Prevents Credential Exposure
By
–
6. We’ve done more to ensure your API keys remain secret. Now, if you paste something that looks like an API key into your code, we'll remind you to add it to your Secrets instead, so we can keep it safe for you. pic.twitter.com/PHhxShBaHT
— Replit ⠕ (@Replit) 14 août 20236. We’ve done more to ensure your API keys remain secret. Now, if you paste something that looks like an API key into your code, we'll remind you to add it to your Secrets instead, so we can keep it safe for you.
-
Undo Redo Actions Now Persist Between Repl Reloads
By
–
7. Undo and redo actions now persist between reloads. If you ever need to reload your Repl, you’ll find that picking up and continuing with your work is now instant as your CMD + Z muscle memory will be preserved. pic.twitter.com/K1c5izoQsh
— Replit ⠕ (@Replit) 14 août 20237. Undo and redo actions now persist between reloads. If you ever need to reload your Repl, you’ll find that picking up and continuing with your work is now instant as your CMD + Z muscle memory will be preserved.
-
Faster Deployment for Repls with Large Package Numbers
By
–
4. We've made deployments even better by cutting down the total time to deploy. Repls with a large number of packages deploy 2-3x faster. We’ve also squashed bugs on failed deployments and upgraded the UI and experience. pic.twitter.com/RHqC1ZOBQY
— Replit ⠕ (@Replit) 14 août 20234. We've made deployments even better by cutting down the total time to deploy. Repls with a large number of packages deploy 2-3x faster. We’ve also squashed bugs on failed deployments and upgraded the UI and experience.
-
Package Manager Upgrade Enables Faster Multi-Install Queuing
By
–
5. We upgraded our package manager to allow you to queue up multiple package installs. This will speed up your adding of all those Node modules or Python packages when you’re doing bigger projects, AI or data science work. pic.twitter.com/6YF3Zqab5V
— Replit ⠕ (@Replit) 14 août 20235. We upgraded our package manager to allow you to queue up multiple package installs. This will speed up your adding of all those Node modules or Python packages when you’re doing bigger projects, AI or data science work.
-
Replit Filetree Rebuilt for Performance and Accessibility
By
–
2. We rebuilt the Replit filetree, with a focus on performance and accessibility. Now with quicker interactions when exploring large projects and a more accessible experience with keyboard navigation. pic.twitter.com/ibfDxZfLfQ
— Replit ⠕ (@Replit) 14 août 20232. We rebuilt the Replit filetree, with a focus on performance and accessibility. Now with quicker interactions when exploring large projects and a more accessible experience with keyboard navigation.
-
Repls Launches 256GB Expandable Storage for ML Model Training
By
–
1. First, Expandable Storage: Repls can now store up to 256GB. Pick a plan, or buy storage à la carte. Train your ML models and don’t worry about the size of your data. pic.twitter.com/vpMyKgJ3vH
— Replit ⠕ (@Replit) 14 août 20231. First, Expandable Storage: Repls can now store up to 256GB. Pick a plan, or buy storage à la carte. Train your ML models and don’t worry about the size of your data.