Yeah but interestingly I also sometimes find that 1/2x the rank works better. Like you said it may be the data distribution. But yeah overall it’s a hyperparameter that sometimes has its own mind
@rasbt
-
Small Models Performance for Spam Classification Task
By
–
Sebastian Raschka
How about these wrt to small models on a specific task (here: spam classification) -
LLM Coding Resources and Bonus Materials for Weekend Learning
By
–
If you are looking for something to read/study this weekend, I added lots of LLM-related bonus from-scratch coding resources over the last few months (from implementing Llama 3.2 to preference tuning with DPO): https://
github.com/rasbt/LLMs-fro
m-scratch?tab=readme-ov-file#bonus-material
… I hope you find them useful! -
Layer Selection Method: Random or Similarity-Based Approach
By
–
Interesting! How did you select these layers? Was this a random selection or did you sort them by input/output similarity?
-
Interleaving Tokens and Training Data for Vision Models
By
–
These are good questions! Regarding 1, yes, interleaving text and image tokens makes a lot of sense then. For part 2, not sure but I suspect you'd need to train the model on data that contains bounding box coordinates at the very least.
-
LLM Default Settings Run on CPU and GPU
By
–
Thanks for getting a copy! The default settings for the LLM in the book are such that it runs on CPU and GPU (it automatically uses a GPU if a compatible one is present). However, I made sure that everything works fine on a laptop (I tested everything on my MacBook Air
-
SigLIP Replaces CLIP as New Standard Choice
By
–
Yes, you are right. I think CLIP used to be the standard but now SigLIP seems to be a more popular choice
-
MacBook RAM recommendations for local AI development work
By
–
Glad you found my book helpful, and congrats on landing a job in AI!
Regarding the Mac… I am actually on a MacBook Air for (and have a 32 Gb Pro for work) as I run AI experiments on cloud machines anyways. But yeah, if you plan to run most stuff locally, I would max out the RAM -
Catching Up on LLM Developments and Book Progress
By
–
Ha, yes. And there's always more to catch up on in LLM land. PS: I hope you are liking the book so far!
-
Understanding Multimodal LLMs: Decoder-Only and Cross-Attention Approaches
By
–
If you are curious how Multimodal LLMs work, I wrote a new article to explain the two main approaches, decoder-only- and cross-attention-style: https://
magazine.sebastianraschka.com/p/understandin
g-multimodal-llms
…
Plus, I reviewed and summarized the 10 latest research papers to see how it's done in practice.
Happy reading!