Josenildo
@silvajc
Artificial intelligence and machine learning enthusiast. Lecturer at IFMA. https://medium.com/@josenildo_silva
You might like
This paper shows that you can predict actual purchase intent (90% accuracy) by asking an LLM to impersonate a customer with a demographic profile, giving it a product & having it give its impressions, which another AI rates. No fine-tuning or training & beats classic ML methods.
The fastest way to get smarter is to read smarter people. I went through @tbpn’s Metis List and pulled together blogs from some of the most influential people in AI. I’ve also added a few gems outside the list 🧵 I find the most value in blogs where people share applied…
Tem github?
O BUG NÃO TAVA NO INTERPRETADOR E SIM NO CODIGO TTO KKKKKKKKKKKKKKKK
Cientistas brasileiros participam de importantes projetos de IA no mundo todo. Mas não no Brasil. Sabe por quê? Por que não há verbas para esse tipo de projeto no Brasil. Então, quem tem que tomar vergonha é o governo federal que despreza a ciência. O governo federal está…
A suggestion for an effective 11-step LLM summer study plan: 1) Read* Chapters 1 and 2 on implementing the data loading pipeline (manning.com/books/build-a-… & github.com/rasbt/LLMs-fro…). 2) Watch Karpathy's video on training a BPE tokenizer from scratch (youtube.com/watch?v=zduSFx…). 3)…
I've been advised to avoid the phrase: "No previous studies have investigated..." It's a cheap hook to claim the value of your study. Here are 5 approaches I use in my writing instead:
Struggling to find a unique angle for your research? The key to groundbreaking research is in its gaps 7 types of research gaps every scholar should know
The top 8 open-source LLMs for 2024. Tap into the most powerful open-source LLMs and why they will be crucial for the future of generative AI. Prepare for the future.👇 ow.ly/oQ7n50RoQvB
I recorded another 1-hour video: Building a RAG application using open-source models. This time, we'll answer questions from a PDF using Llama2 and Mixtral 8x7B running on my computer. Here is the video: youtu.be/BrsocJb-fAo There's something important about these videos:
youtube.com
YouTube
Building a RAG application from scratch using Python, LangChain, and...
Um guia prático para LLMs github.com/Mooler0410/LLM…
I recorded a step-by-step tutorial on building a RAG application from scratch. It's a 1-hour YouTube video where I show you how to use Langchain, Pinecone, and OpenAI. You'll learn how to build a simple application to answer questions from YouTube videos using an LLM. But the…
SQL in Jupyter Notebooks 🔥 Introducing Jupysql a python library that lets you run SQL commands right inside Jupyter Notebooks: Thread🧵👇
RAG vs. Fine Tuning - A Case Study on Agriculture The most common question we get from customers is - can you fine-tune the LLM for our domain. The answer, of course, has to do with data! If you have several supervised examples, you can fine-tune a model, and often, RAG +…
United States Trends
- 1. #BUNCHITA 1,382 posts
- 2. #SmackDown 44.9K posts
- 3. Tulane 4,245 posts
- 4. Aaron Gordon 3,606 posts
- 5. Giulia 14.6K posts
- 6. Supreme Court 184K posts
- 7. Russ 13.6K posts
- 8. Frankenstein 77.2K posts
- 9. Connor Bedard 2,836 posts
- 10. #TheLastDriveIn 3,633 posts
- 11. #TheFutureIsTeal N/A
- 12. Podz 2,955 posts
- 13. #OPLive 2,246 posts
- 14. Northwestern 5,014 posts
- 15. Caleb Wilson 5,680 posts
- 16. Justice Jackson 5,456 posts
- 17. Memphis 16.2K posts
- 18. Keon 1,168 posts
- 19. Scott Frost N/A
- 20. Tatis 1,994 posts
Something went wrong.
Something went wrong.