We’re on a journey to advance and democratize artificial intelligence through open source and open science.

HuggingFace's platform is a resource for developers and researchers working in natural language processing (NLP) and machine learning, offering insights into NLP models, tools, and datasets. Through articles, tutorials, and open-source projects, HuggingFace offers insights into state-of-the-art NLP techniques, transformer architectures, and transfer learning methods. Developers can learn about using pre-trained models, fine-tuning strategies, and deploying NLP applications with HuggingFace's libraries and APIs.

Hugging Face

Smolagents is a new library designed to simplify the creation and use of AI agents. These agents can control workflows in applications by utilizing large language models (LLMs). The library supports code-based actions, enhancing composability, object management, and generality compared to JSON-based approaches. It also includes integrations with popular AI models and a hub for sharing tools. Smolagents is aimed at users who need more flexibility in their application's workflows.

Introducing smolagents: simple agents that write actions in code.

✅ When to use agents / ⛔ when to avoid them

Introducing smolagents : making agents simple 🥳