A commenting system powered by GitHub Discussions. 💬 💎

💪 User-generated content for Git-powered websites

Fil-C: completely compatible memory safety for C and C++

Unofficial API for YouTube Music

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

The best ChatGPT that $100 can buy.

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

⭐ Pretty-print `git` repository collaborators sorted by contributions

My learning notes for ML SYS.

Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. …

PyTorch native quantization and sparsity for training and inference

A tool kit for generating high quality prompts using DSPy GEPA optimizer

Catch MCP server issues before your agents do.

Fish shell like syntax highlighting for Zsh.

Distribute and run LLMs with a single file.

This benchmark tests how well LLMs incorporate a set of 10 mandatory story elements (characters, objects, core concepts, attributes, motivations, etc.) in a short creative story

Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.

Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna

A fork to add multimodal model training to open-r1

Simple GRPO scripts and configurations.

First-principle implementations of groundbreaking AI algorithms using a wide range of deep learning frameworks, accompanied by supporting research papers and demos.

This is the official repository for The Hundred-Page Language Models Book by Andriy Burkov

Async RL Training at Scale

Fully open reproduction of DeepSeek-R1