Qwen models are great. They are notoriously underestimated but have consistently performed well. I recall that most, if not all, of the winning solutions in the LLM Efficiency Challenge at NeurIPS last year were based on a Qwen model. I should make a tutorial some time
@rasbt
-
PyTorch installation with conda and CUDA tools setup
By
–
I can’t recall having issues with it when using PyTorch. I still use conda (I just pop install PyTorch), so I could do ‘conda install cuda-nvcc-tools’ I guess
-
CPU Training Speed Sufficient for Medium-Sized Datasets
By
–
I was recently training a model on a ~100k row & 20 column dataset. Took like ~2 sec on a CPU. Granted it was faster on the GPU (tried it just for fun) but it was already so fast that it’s kind of overkill for my use cases
-
Appreciation for useful content with bonus materials recommendation
By
–
Thanks for the kind words. Super glad it’s useful! Btw I think 7 is the most fun one! Enjoy! (Also, there’s lots of bonus materials if you are bored, from LoRA to DPO from scratch!)
-
Using Miniforge with pip for torch and package management
By
–
Fwiw I am still using miniforge for my env management but use pip for torch and many other packages now (in the conda env), and it works fine in my cases.
-
PyTorch pip installation works seamlessly with CUDA on macOS Linux
By
–
Whoa! But that being said, I've been using `pip install torch` for 1-2 years now and it's fine on macOS and Linux. The wheels come with CUDA and cuDNN, so it should not require any additional setup steps afaik.
-
Textbook Writers and Data Labelers: 2025 Professional Convergence
By
–
So, in 2025, textbook writers are basically synonymous with data labelers?
-
LLM Focus Over Data Cleaning and PDF Text Extraction
By
–
Hi there. This is definitely an interesting topic but not covered as the focus is more on the LLM itself rather than data cleaning etc. But I remember from my grad school days that there are several Python libraries that allow you to extract text from PDFs etc.
-
Appreciation for Detailed Attention Mechanism Explanation Chapter
By
–
Thanks! I'm glad to hear the step-by-step process of building up the attention mechanism is useful! I remember this chapter almost hit the page limit, and I had to do a bit of convincing to avoid shortening it. Happy to know it's helpful!
-
Recommendation of Deep Learning for Coders Book
By
–
Can confirm, I have a copy of Deep Learning for Coders on my shelf and it's great!