Build a RAG app with Llama-3 running locally on your computer
(100% free and without internet):
LLMS
-
Build Local RAG App with Llama-3 Offline
By
–
-
Vibe-Eval Wins Best Evaluation Benchmark Name Prize
By
–
Vibe-Eval wins the prize for the best name for an eval benchmark, surprised no-one had taken that name already
-
1 Trillion Edges: Breakthrough in AI Model Architecture
By
–
An edgy post… 1 trillion edges, in fact! https://t.co/ymbl16TL2X
— Jeff Dean (@JeffDean) 1 mai 2024An edgy post… 1 trillion edges, in fact!
-
Why Open Source AI Models Lag Behind Commercial Solutions
By
–
Several people told me to add "open source performance is still lagging compared to commercial models". Is there any fundamental reason that stops open source models from catching up? The biggest reason I can think of is what @soumithchintala told me: open source models don't
-
Running Standard LLM Benchmarks: The Easiest Approach
By
–
What’s the easiest way to run the standard set of LLM benchmarks?
-
Open Source vs Commercial AI Models: Privacy and Security Considerations
By
–
I’m making a list of things to consider when using open source models and commercial models. What else should I add? Commercial models
1. Data privacy: employees might accidentally include confidential information in the prompt, e.g. when Samsung employees leaked the company’s -
LangSmith Regression Testing Improvements for LLM Applications
By
–
🧮Regression testing your LLM applications
— LangChain (@LangChain) 1 mai 2024
We've made big improvements to the "regression testing" flow in LangSmith to allow you to quickly spot changes in your application's performance:
🟥Automatically highlighting changes
⛪️Filter to changed datapoints
📄Different ways of… pic.twitter.com/ZxnE6pHAyiRegression testing your LLM applications We've made big improvements to the "regression testing" flow in LangSmith to allow you to quickly spot changes in your application's performance: Automatically highlighting changes
Filter to changed datapoints
Different ways of -
ChatRTX Update Brings New LLM Models Image Search Voice
By
–
New ChatRTX update to level up your #AIonRTX capabilities. More LLM Models Image Search Voice Support Learn more in this week's #AIDecoded blog https://
nvda.ws/3WiN247 -
Claude Launches New Team Plan with 200K Context Window
By
–
Introducing a new Team plan for Claude. Get increased usage for team members, easily manage users and billing, and tackle complex tasks with our large 200K context window.
-
ROBOSHOT: Optimizing Foundation Models Without Fine-tuning
By
–
Snorkel AI research series! Dyah Adilla walked us through the finer points of ROBOSHOT, an approach to squeeze better performance out of foundation models without fine tuning. Adila's talk: https://
buff.ly/3UqgVgv Next webinar: https://
buff.ly/3JFtOhR