This will be my own journey of learning to be better at ML. This is meant to encourage me to learn and build more often. my 2d resume is here
-
The
C
folder in this directory is for the cc4e.com class. More coming soon. -
The
Karapathy
folder is for the Karapathy learning videos. -
And I am doing my experiments in the
Random Code
folder I will try to add more explanations once I have them. venv will probably be missing for most of them 😊.
- FinMAs
- Byte Latent mini implemntation, mine has a static patches 4 bites each.
- NeoFetch yes i use windows :/
- I have older stuff but I'm still too lazy to add them
- FinMAs working (slowly) on adding vision and updating the crew to work with flow
- Learning C cc4e
- I will need to pour my life into this
- neetcode a day keeps the unemployment away
- Also reading it's a new theoretical reintro to the math and theory
- write better code
- Document your grind
- Reclaiming your attention and focus - Unc advice for the world
- Reward Hacking what could go wrong in RLHF
- LLM tuning and alignment series by HF Explains different techniques
- What We’ve Learned From A Year of Building with LLMs Guide to building llms from exp
- Byte Latent Transformer: Patches Scale Better Than Tokens instead of a single byte, they use patches, which could scale better with images in the future
- High-Quality Human Data How human data is made, based on what I do on a daily basis, this is a useful read. It's not always about the model...
- HF smol course. Small but super nice intro to using HF finetuning and more.
- learnpytorch.io mostly following and not much else.
- transformer math
- GNN intro
- Understanding Multimodal LLMs
- Physics of Language Models
- Policy Gradient
- Flash Attention
- LLM visualized
- LLM training
- LLM Research Insights:
- FineWeb: decanting the web for the finest text data at scale
- torch.compile, the missing manual
- Build a GENAI platform
- New LLM Pre-training and Post-training Paradigms
- Mathematics for Machine Learning
- Applied Linear Algebra Notes
- MAT3341 Applied Linear Algebra
- Introduction to Linear Algebra
- Financial analysis book
- Graphic data science
- THE HUNDRED-PAGE LANGUAGE MODELSBOOK
- Building Blocks for theoretical computer science
- Stanford CS Library
- Beej's Guide to C Programming
- How to Optimize a CUDA Matmul Kernel
- From Scratch series
- LLM.c
- PMPP-notes
- my weak parralel guide
- GPU MODE
- BIRDS cohort
- GPU Glossary
- VLM's are blind
- Mamba the hard way
- LORA
- 1-bit LLM
- XLSTM
- Scalable MatMul-free Language Modeling
- Trading GPT
- Karapathy mibpe
- Cohere agents
- Building A GPT-Style LLM Classifier From Scratch By Sebastian
- lora from scratch by Sebastian
- try comet in case for job
- llama from scratch
- lightning snippets
- DPSY
- Use and play the mini LLM boiii
- Financial Analysis With Langchain and Crewai some testing from langchain and crewai docs
- Automate Job Applications auto-rejection deserves auto-apply
- FineTune Clip
- Zero-shot Classification
- Data Scrapping project with R