Robyn is a Super Fast Async Python Web Framework with a Rust runtime.

A Conversational Speech Generation Model

Official repository of the paper, PokeChamp: an Expert-level Minimax Language Agent for Competitive Pokemon.

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

MoreFixes: A Large-Scale Dataset of CVE Fix Commits Mined through Enhanced Repository Discovery

A fast Rust based tool to serialize text-based files in a repository or directory for LLM consumption

Machine Learning Engineering Open Book

Solve and animate maze solutions using manim.

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Tool to help Visualize flex attention mod_maps.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Simplifying reinforcement learning for complex game environments

Learn LeetCode and prepare for coding interviews with free resources.

STEP Web agent for WebArena using dspy.

Code for the paper 🌳 Tree Search for Language Model Agents

Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models

TensorRT-FastSAM(https://github.com/CASIA-IVA-Lab/FastSAM)

Fast Segment Anything

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

This software allows to run MobileSAM, without python.

On-device AI across mobile, embedded and edge for PyTorch

A comprehensive survey of datasets for research in host-based and/or network-based intrusion detection, with a focus on enterprise networks

Comparing performance of different InfoNCE type losses used in contrastive learning.

[ICML'24] Code for the loss functions and metrics presented in "Bridging mini-batch and asymptotic analysis in contrastive learning: From InfoNCE to Kernel-based losses"

Deep Reinforcement Learning: Zero to Hero!

LLM training in simple, raw C/CUDA