What fresh insights can we gain from studying similarities and differences in learning between children and AI? Listen to this episode of The Future of Everything podcast with @Rbaltman and @stanfordeng
: https://
stanford.io/48o0zd6
MACHINE LEARNING
-
Learning Similarities Between Children and Artificial Intelligence Systems
By
–
-
Gemini-1.5 Pro Represents Most Significant LLM Advancement
By
–
— Oriol Vinyals (@OriolVinyalsML) 20 février 2024
Ok, I've been waiting a while before saying it confidently, but I now understand that the Gemini-1.5 Pro had its deserved spotlight stolen last week by Sora. After experimenting with it for a while, I believe it represents the most significant advancement in LLM capabilities
-
Problem-solving uncertainty in complex technical challenges
By
–
thinking really hard about a problem when you're not sure if you will find its solution, or if the solution is out there but you're googling the wrong words, or the problem is completely intractable for reasons you are currently unaware of
-
27 Mistral-7B Adapters Fine-Tuned for Under $8 Each
By
–
We fine-tuned 27 adapters using #Mistral-7B on Predibase for < $8.00 each and 25 of them rival or outperform #GPT4 Check out our blog to see benchmarks, learn how we did it & get the link to download the #LLMs on @HuggingFace #TheFutureIsFineTuned https://
pbase.ai/49Hrwtn -
Data Poisoning Paper: Practical Applications and Implications
By
–
also quite enjoyed his recent paper on data poisoning is practical.
-
MinBPE: Minimal Byte Pair Encoding Implementation for LLM Tokenization
By
–
Also, releasing new repository on GitHub: minbpe
Minimal, clean, code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization. https://
github.com/karpathy/minbpe In the video we essentially build minbpe from scratch.
Don't miss the http://
exercise.md to build your -
New Lecture: Building GPT Tokenizer with Byte Pair Encoding
By
–
New (2h13m ) lecture: "Let's build the GPT Tokenizer" Tokenizers are a completely separate stage of the LLM pipeline: they have their own training set, training algorithm (Byte Pair Encoding), and after training implement two functions: encode() from strings to tokens, and
-
Tokenization: The Root of LLM Problems and Quirks
By
–
We will see that a lot of weird behaviors and problems of LLMs actually trace back to tokenization. We'll go through a number of these issues, discuss why tokenization is at fault, and why someone out there ideally finds a way to delete this stage entirely.
-
RAG Query Translation: Decomposition Approaches From Scratch
By
–
RAG From Scratch: Query Translation (Decomposition) Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. This is the third in our videos on Query Translation, focused on approaches for decomposition w/ ideas from Least-to-Most
-
Chat LLMs and AI Agents Webinar Next Week
By
–
If you missed out on our previous Chat LLMs & AI Agents Webinar you can tune in next week! Learn how you can build an AI brain for your organization using our ML and LLM Ops Platform! We will cover the following topics:
•Chat LLMs – customize a ChatGPT like interface and