samsja

muon_fsdp_2. Muon fsdp 2

pydantic_config. Manage ML configuration with pydantic

rusty-grad. Pytorch like framework in rust: Autograd with dynamic graphs for deep learning

belote_libre. Belote libre: Implementation of a open source version of the french game Belote. The repo contains the code for the backend server, the frontend website and the reinforcement learning models for the IA in game

k8s-rasb-config. Config files for k8s cluster of raspberry pi

stable-diffusion-executor. Jupyter Notebook

rusty-llm. Fast inference of LLM on cpu written in rust

samsja.github.io. repo for github page files

eim. GPU implementation of the dimension reduction algorithm Empirical Interpolation Method (EIM) in pytorch

llama-jaxtyping. LLaMa implementation fork from lit-llama fully typed with jaxtyping

finding-a-needle-code. Code for the paper : Improving traffic sign recognition by active search

corona_simu_and_vizu. Jupyter Notebook

prime. prime is a framework for efficient, globally distributed training of AI models over the internet.

git-agent. Langchain-based Agent utilizing OpenAI Functions to help you with a couple of Git commands

reason_net. bigger context window, less weight = good local model

torchft. Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)

pytorch-vision-transformers. My implementation of transformers related papers for computer vision in pytorch

hopfield_network. Jupyter Notebook

zeroband. Python

verifiers. Verifiers for LLM Reinforcement Learning

open-flamingo-serve. Serve Open Flamingo via gRPC

homer_conf. Dockerfile

home_website. Dockerfile

dotfiles. My dotfiles for my manjaro i3 linux configuration,

web2dataset. Jupyter Notebook

docarray. (Core maintainer) 🧬 Represent, send, and store multimodal data · Neural Search · Vector Search · Document Store