Lists (12)
Stars
The all-in-one LLM developer platform: prompt management, evaluation, human feedback, and deployment all in one place.
☁️ Build multimodal AI applications with cloud-native stack
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"
Unified framework for robot learning built on NVIDIA Isaac Sim
Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.
Alpaca dataset from Stanford, cleaned and curated
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
2nd solution of ICDAR 2021 Competition on Scientific Literature Parsing, Task B.
fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
Data-Driven Evaluation for LLM-Powered Applications
The Open-Source Data Annotation Platform
DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Models
UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform…
A Comprehensive Toolkit for High-Quality PDF Content Extraction
The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.
GRUtopia: Dream General Robots in a City at Scale
A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。
[ECCV2022, TPAMI2023] FAST-VQA, and its extended version FasterVQA.
A Pythonic framework to simplify AI service building
DataComp: In search of the next generation of multimodal datasets
The unified platform for data-related resources.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
A self-organizing file system with llama 3