Pinned Repositories
attention-is-all-you-need
Implementation of the 'Attention is all you need' paper in PyTorch
attention-lab
Chess-Challenge
Chess Engine developed for the Chess Coding Challenge by Sebastian Lague
llama-discord-bot
Chat with Llama models on Discord! Supports inference both on the cloud, using replicate.com and locally, with llama.cpp.
nextjs-deploy-plesk
Simple guide/template to deploy a Next.js app on a Plesk server.
openai_instant_assistant
Generate an OpenAI assistant with Retrieval Augmented Generation on your directories!
pequegrad
Tensors with automatic differentiation and JIT compilation for Python. Pequegrad is a toy deep learning and scientific computing library that runs on the CPU and GPU
sat-ts
A DPLL-based SAT solver written in TypeScript, powered by Bun.
uvlhub-egc
csrf-csrf
A utility package to help implement stateless CSRF protection using the Double Submit Cookie Pattern in express.
davidgonmar's Repositories
davidgonmar/pequegrad
Tensors with automatic differentiation and JIT compilation for Python. Pequegrad is a toy deep learning and scientific computing library that runs on the CPU and GPU
davidgonmar/uvlhub-egc
davidgonmar/attention-is-all-you-need
Implementation of the 'Attention is all you need' paper in PyTorch
davidgonmar/Chess-Challenge
Chess Engine developed for the Chess Coding Challenge by Sebastian Lague
davidgonmar/binary-connect
davidgonmar/diffusion-explore
davidgonmar/dual
davidgonmar/experiment
davidgonmar/fast_infer
jax llm inference
davidgonmar/forward-forward
Playing around with Hinton's forward forward algorithm
davidgonmar/forward-gradients
Using forward autodiff and randomness to estimate gradients with no bakpropagation
davidgonmar/gan
davidgonmar/gemma
Open weights LLM from Google DeepMind.
davidgonmar/jax-contrastive-learning
davidgonmar/leetcode
davidgonmar/Liger-Kernel
Efficient Triton Kernels for LLM Training
davidgonmar/llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
davidgonmar/llm-notebooks
davidgonmar/low_rank_compression
davidgonmar/moe
davidgonmar/optimal-brain-damage
Implementation of the Optimal Brain Damage paper in PyTorch (using second order Taylor series to prune neural networks)
davidgonmar/phi.jl
davidgonmar/ptq
davidgonmar/regex_from_scratch
davidgonmar/rl-barto-sutton
davidgonmar/transformers.jl-playground
davidgonmar/triton-kernels
davidgonmar/uvlhub_practicas
Repository of feature models in UVL format integrated with Zenodo and flamapy following Open Science principles - Developed by DiversoLab
davidgonmar/vae
davidgonmar/verlet_sym