Lists (1)
Stars
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.
Accompanying code for "Discovering State-of-the-art Reinforcement Algorithms" Nature publication
🚀 Efficient implementations for emerging model architectures
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
Static suckless single batch CUDA-only qwen3-0.6B mini inference engine
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A remote for Insta360 cameras based on the M5StickC, M5StickC Plus, and M5StickC Plus2
[AAAI 2026 🔥 Poster] ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning
llama.cpp fork with additional SOTA quants and improved performance
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
[JMLR 2026] "UQLM: A Python Package for Uncertainty Quantification in Large Language Models"
Minimal and annotated implementations of key ideas from modern deep learning research.
A directional speaker with a driver based on STM32
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.
Powerpoint to Markdown converter - Python 3 script
CMMLU: Measuring massive multitask language understanding in Chinese