Lists (1)
Stars
Minimal reproduction of DeepSeek R1-Zero
verl: Volcano Engine Reinforcement Learning for LLMs
Open source LLM UI, compatible with all local LLM providers.
Tutorials of econometrics featuring Python programming. This is a crash course for reviewing the most important concepts and techniques of basic econometrics, the theories are presented lightly wit…
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
📖 Repo pour le manuel "Machine Learning pour l'économétrie"
React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic last-mile 🪁
🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
FlashInfer: Kernel Library for LLM Serving
A high-throughput and memory-efficient inference and serving engine for LLMs
Large-scale LLM inference engine
Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)
Full-stack framework for building Multi-Agent Systems with memory, knowledge and reasoning.
Implementation of Nougat Neural Optical Understanding for Academic Documents
ONNXMLTools enables conversion of models to ONNX
Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models
Generative AI extensions for onnxruntime
Gradio based tool to run opensource LLM models directly from Huggingface
We Replicate Research Papers in the field of AI & ML.
Portfolio optimization and back-testing.
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive lea…
Notebooks and code for the book "Introduction to Machine Learning with Python"
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
A fast & densely stored hashmap and hashset based on robin-hood backward shift deletion