This is your work, valued
GPT-2. Following Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish
172leetcode. Intro to leetcodes. Basic techniques, quicksort and hash structures implementation, space and time complexities.
98matryoshka. Implementation of "Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensions"
25RL. Python
15mup. Minimal (truly) muP implementation, consistent with TP4 and TP5 papers notation
14ziglings. Extensive introductory writeup on Zig language functionalities
9blog-i-guess.
9spikingNeuralNetworks. Spiking Neural Networks dependance on initial conditions using snnTorch. The results are presented in my Bachelors Thesis: "The impact of initial parameters on the learning of spiking neural networks".
6matrix. Efficient matrix and matmul implementations in Python and C
52headgrad. Want to scale it to most of modern LLM stack, with other languages (Zig/C/Go?) and some CUDA examples, writing stuff that helped me click
3PMPP. C++
2MulticlassBrainSegmentation. UNET based multiclass segmentation network written with PyTorch for the FeTA 2021 Challenge.
2Triton-Puzzles. Puzzles for learning Triton
2CS-552-EPFL. Modern Natural Language Processing at EPFL
1llm_compressor. Jupyter Notebook
1information-theory. Python
1craftinginterpreters. My dumbass writing while I go through Crafting Interpreters as a side-side-side project
1entropix. Entropy Based Sampling and Parallel CoT Decoding
1sentiment-analysis. Jupyter Notebook
1alphazero. Jupyter Notebook
1MedSignalAnalysis. Signals from electro- medical examination methods analysed with Python.
1CS-433-EPFL-Project1-ML. Python
1