Browser Use is a library that enables AI agents to interact with web browsers, making websites accessible for automated tasks. It includes features for browser automation, agent memory, and various demos showcasing its capabilities.
A terminal-based platform to experiment with the AI Software Engineer. It allows users to specify software in natural language, watch as an AI writes and executes the code, and implement improvements. Supports various models and customization options.
ClickUi is a powerful, open-source, cross-platform AI-assistant application built in Python. It integrates various AI models, speech recognition, and web scraping capabilities, providing both voice and text interaction interfaces. The tool is designed to be a comprehensive AI-computer assistant, supporting features such as voice mode, chat mode, file attachments, property lookups, and web searches. It aims to be user-friendly and adaptable, encouraging community collaboration for future development and improvements.
This repository provides a Python script to fetch and summarize research papers from arXiv using the free Gemini API. It includes features for summarizing a single paper or multiple papers, easy setup, and automatic daily extraction and summarization based on specific keywords. The tool is designed to help researchers, students, and enthusiasts quickly extract key insights from arXiv papers without manually reading through lengthy documents.
SmolVLM2 represents a shift in video understanding technology by introducing efficient models that can run on various devices, from phones to servers. The release includes models of three sizes (2.2B, 500M, and 256M) with Python and Swift API support. These models offer video understanding capabilities with reduced memory consumption, supported by a suite of demo applications for practical use.
This tutorial demonstrates how to fine-tune the Llama-2 7B Chat model for Python code generation using QLoRA, gradient checkpointing, and SFTTrainer with the Alpaca-14k dataset.
OpenInference is a set of conventions and plugins that complements OpenTelemetry to enable tracing of AI applications, with native support from arize-phoenix and compatibility with other OpenTelemetry-compatible backends.
Simon Willison introduces llm-smollm2, a plugin for LLM that includes a quantized version of the SmolLM2-135M-Instruct model. The article details how to install and use the model, discusses the process of finding, building, packaging, and publishing the plugin, and evaluates the model's capabilities.
The article by Krishan Walia provides a beginner-friendly guide on fine-tuning the DeepSeek R1 model using Python. It highlights how developers can transform a general-purpose AI model into a specialized, domain-specific language model for various applications.
This folder contains some example client scripts using our Python SDK for connecting with Llama Stack Distros. Instructions are provided for setting up dependencies and running demo scripts and apps.
