llm-classifier
LLMs-from-scratch
| llm-classifier | LLMs-from-scratch | |
|---|---|---|
| 4 | 21 | |
| 249 | 33,995 | |
| - | - | |
| 7.2 | 9.8 | |
| 6 months ago | 17 days ago | |
| Python | Jupyter Notebook | |
| GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
llm-classifier
-
Lessons after a Half-billion GPT Tokens
We do this for the null hypothesis - is uses an LLM to bootstrap a binary classifier - which handles null easily
https://github.com/lamini-ai/llm-classifier
- FLaNK Stack 29 Jan 2024
-
Good old-fashioned AI remains viable in spite of the rise of LLMs
LLMs introduced zero-shot learning, or “prompt engineering” which is drastically easier to use and more effective than labeling data.
You can also retrofit “prompt engineering” onto good old fashion ML like text classifiers. I wrote a library to do just that here: https://github.com/lamini-ai/llm-classifier
IMO, it’s a short matter of time before this takes over all of what used to be called “deep learning”.
- How to use a LLM to classify text
LLMs-from-scratch
- Implementing the Llama 3.2 1B and 3B Architectures from Scratch
- Converting GPT to Llama step-by-step code guide
-
Ask HN: How can I experiment with LLMs with a old machine?
Dear all,
Recently I purchased "[Build a Large Language Model (From Scratch)](https://www.manning.com/books/build-a-large-language-model-from-scratch)" by Sebastian Raschka, so that I could learn more about how to build and/or fine-tune a LLM, and even developing some applications with them. I have also been skimming and reading on this sub for several months, and have witnessed many interesting developments that I would like to follow and experiment with.
However, there is a problem: The machine I have is a very old Macbook Pro from 2011 and I probably would not be able to afford a new one until I'm in graduate school next year. So I was wondering that, other than getting a new machine, what are the other (online/cloud) alternatives and/or options that I could use, to experiments with LLMs?
Many thanks!
-
Tutorial on Diffusion Models for Imaging and Vision
Andrej Karpathy has a youtube playlist:
https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThs...
He is building new learning materials under his new company "Eureka Labs":
https://eurekalabs.ai
Sebastian Raschka's book "Build a Large Language Model (From Scratch) just released:
https://www.manning.com/books/build-a-large-language-model-f...
All of these resources are excellent.
-
Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs
> Define what reasoning is to you.
Reasoning was the process I went through to formulate this response, doing so with intent to convey meaning as best as I can, and understand as best as possible the message to which I am replying.
> Then tell us why LLMs don't reason and why it matters.
LLM's do not possess the ability to perform the process detailed above.
This is why it matters.
0 - https://github.com/rasbt/LLMs-from-scratch
1 - https://en.wikipedia.org/wiki/Large_language_model
-
Building LLMs from the Ground Up: A 3-Hour Coding Workshop
Most likely this one.
https://www.manning.com/books/build-a-large-language-model-f...
(I've taken it from the footnotes on the article)
-
Programmers Don't Read Books – But You Should (2008)
- https://www.manning.com/books/build-a-large-language-model-f...
-
Ask HN: What are the best resources today for learning AI/LLMs
You can try this.https://github.com/rasbt/LLMs-from-scratch
-
Building My Own LLM: A Journey into Language Models Building a Tokenizer 🛠️
I would highly recommend buying this book; you can get it from here: https://www.manning.com/books/build-a-large-language-model-from-scratch. Also, please do check out my blog for more posts similar to this one, as I don't post here all the time. Link To Blog
- LLM instruction finetuning from-scratch tutorial
What are some alternatives?
ml-ferret
s4 - Structured state space sequence models
heynote - A dedicated scratchpad for developers
NeMo-Curator - Scalable data pre processing and curation toolkit for LLMs
java-snapshot-testing - Facebook style snapshot testing for JAVA Tests
machine-learning-book - Code Repository for Machine Learning with PyTorch and Scikit-Learn
reor - Private & local AI personal knowledge management app for high entropy people.
kafkaflow - Apache Kafka .NET Framework to create applications simple to use and extend.
sendenv
build-your-own-x - Master programming by recreating your favorite technologies from scratch.
Deep_Object_Pose - Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)
ml-engineering - Machine Learning Engineering Open Book