Stars
Compiling strategy guides into reward functions for reinforcement learning. Uses Claude Vision to extract unit tests from game guides, then trains agents with dense, interpretable rewards.
Complete end-to-end setup for maximizing DGX Spark compute for AI Workloads
An Open Source C# 3D Game Engine under MIT license, inspired by Unity and featuring a complete editor
VortexNet: Neural Computing through Fluid Dynamics
Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.
MMORPG prototype inspired by World of Warcraft.
A little(lil) Language Model (LM). A tiny reproduction of LLaMA 3's model architecture.
Inference engine for Intel devices. Serve LLMs, VLMs, Whisper, Kokoro-TTS, Embedding and Rerank models over OpenAI endpoints.
A fast Rust based tool to serialize text-based files in a repository or directory for LLM consumption
Implementation of the BitLinear layer from: The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
This is the implentation of our paper "SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms" in ICML 2024.
Run Large-Language Models (LLMs) 🚀 directly in your browser!
Efficient Python library for Extended LSTM with exponential gating, memory mixing, and matrix memory for superior sequence modeling.
Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.
Intel® NPU Acceleration Library
TrinityCore Open Source MMO Framework (master = 12.0.1.66709, 3.3.5 = 3.3.5a.12340, cata classic = 4.4.2.60895)
Implementation of the Llama architecture with RLHF + Q-learning
Unsloth Studio is a web UI for training and running open models like Qwen, DeepSeek, gpt-oss and Gemma locally.
A pythonic library providing light-weighted interface with LLMs
A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (https://arxiv.org/pdf/2307.08621.pdf)
An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"
Explore large language models in 512MB of RAM
Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
Pure Rust implementation of a minimal Generative Pretrained Transformer
PanML is a high level generative AI/ML development and analysis library designed for ease of use and fast experimentation.
BladewindUI is a collection of elegant Laravel blade-based UI components spiced with TailwindCSS and Javascript.