Umar Jamil

pytorch-transformer. Attention is all you need implementation

pytorch-stable-diffusion. Stable Diffusion implemented from scratch in PyTorch

pytorch-paligemma. Coding a Multimodal (Vision) Language Model from scratch in PyTorch with full explanation: https://www.youtube.com/watch?v=vAmKB7iPkWw

100-days-of-gpu.

pytorch-llama. LLaMA 2 implemented from scratch in PyTorch

transformer-from-scratch-notes. Notes about "Attention is all you need" video (https://www.youtube.com/watch?v=bCz4OMemCcA)

triton-flash-attention. Python

mamba-notes. Notes on the Mamba and the S4 model (Mamba: Linear-Time Sequence Modeling with Selective State Spaces)

rlhf-ppo. Notes and commented code for RLHF (PPO)

quantization-notes. Notes on quantization in neural networks

pytorch-lora. LORA: Low-Rank Adaptation of Large Language Models implemented using PyTorch

pytorch-transformer-distributed. Distributed training (multi-node) of a Transformer model

pytorch-llama-notes. Notes about LLaMA 2 model

pytorch-ddpm. Implementation of the paper "Denoising Diffusion Probabilistic Models" in PyTorch

multi-latent-attention. Python

lazy-ml. ML algorithms implementations that are good for learning the underlying principles

dpo-notes. Notes on Direct Preference Optimization

mistral-src-commented. Reference implementation of Mistral AI 7B v0.1 model.

retrieval-augmented-generation-notes. Slides for "Retrieval Augmented Generation" video

mistral-llm-notes. Notes on the Mistral AI model

kan-notes.

bert-from-scratch. BERT explained from scratch

vae-from-scratch-notes. Notes about the video on the Variational Autoencoder

ml-interpretability-notes. Jupyter Notebook

segment-anything-slides. Slides for "Segment Anything" video

python-longnet. Tools and experiments with the LongNet model

hanbaobao. Google Chrome extension that helps you learn Chinese, by providing a dictionary and also shows known words.

hkproj.github.io. TypeScript

adversarial_example_generator. A Python library to generate adversarial examples for classification models

karno. Karnaugh map solver that works with any number of variables

torch_notes. PyTorch notes

ai-project. Python

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

mamba. Python

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

xamarin-autoscrolling. Automatic UIView scrolling when keyboard appears on Xamarin iOS

syncnet_pipeline. SyncNet pipeline to align audio to videos

copto. C# library that incrementally parses command line arguments.