最有价值项目

📊 ETL pipeline for YouTube competitor analytics. Orchestrated with Airflow, Docker, and AWS. Features sentiment analysis and a Power BI dashboard.

Collection of OSS models that are containerized into a serving container

HFCommunity offers an offline up-to-date relational database built from the data available at the Hugging Face Hub, providing queriable data about the repositories hosted in the Hub

ESGenius: EMNLP 2025 Main Oral benchmark for LLM ESG and sustainability knowledge, with 1,136 questions, evaluation code, interactive heatmap, and Hugging Face dataset release.

This open-source project delivers a complete pipeline for converting multi-page documents (PDFs/images) into structured JSON using Vision LLMs on Amazon SageMaker. The solution leverages the SWIFT Framework to fine-tune models specifically for document understanding tasks.

Scala bindings for Hugging Face Tokenizers

This repository implements pi0, pi0fast and smolvla models on sim and real robots using Lerobot interface

Retrieval-Augmented Generation on PDF for Free, Integrated with Memory to recall previous interactions, it operates as a sophisticated lang-chain application.

LLM-powered financial analyst using LoRA-tuned Llama-3 and RAG pipeline to answer complex queries over SEC 10-K filings with contextual accuracy.

chap - A Python interface to chatgpt, including a terminal user interface (tui)

Whisper in TensorRT-LLM

Our Process for Llama2 Finetuning

Python framework for artificial text detection: NLP approaches to compare natural text against generated by neural networks.

Empower Truly Autonomous AI Agents through our Experimental Adversarial and Evolutionary Reinforcement Learning Framework. Join our Community: https://t.me/evolveRL_portal

Official PyTorch Implementation for the "Learning on Model Weights using Tree Experts" paper (CVPR 2025).

Dockerized FastAPI wrapper for OmniVoice — zero-shot TTS for 600+ languages with voice cloning, voice design, and OpenAI-compatible API. GPU & CPU support.

A vector database for querying meaningfully similar data.

End-to-end deployment of Azure OpenAI applications using Redis Enterprise as a vector database.

KoutenDB: locality-aware NoSQL document/vector database built around rings and orbit-inspired retrieval

Nautobot Model Context Protocol (MCP) Server - Contains STDIO and HTTP Deployments with Embedding Search and RAG.