In this tutorial, we arrange Microsoft Fara in Google Colab and run a browser-use workflow from begin to end. We start by cloning the repository, putting in the package deal, getting ready Playwright, and verifying that the put in Fara recordsdata work even when the package deal format modifications. Instead of instantly counting on a…
In this tutorial, we work with the amphora/ResearchMath-14k dataset, a assortment of research-level arithmetic issues mined from arXiv. We load the dataset, examine its construction, and discover how the issues are distributed throughout mathematical fields and open-status classes. We then transfer past fundamental evaluation by extracting field-specific key phrases, producing semantic embeddings, visualizing the downside…
In this tutorial, we fine-tune Liquid AI’s LFM2 mannequin via an entire open-source workflow. We begin by loading the bottom LFM2 checkpoint with QLoRA, getting ready a chat-style supervised fine-tuning dataset, coaching a light-weight LoRA adapter utilizing TRL and PEFT, and then merging the adapter again into the mannequin. We additionally lengthen the workflow with…
In this tutorial, we construct a ruled AI-agent workflow utilizing Microsoft’s Agent Governance Toolkit as the reference level. We create a Colab-ready implementation the place brokers don’t straight execute instruments; as an alternative, each motion first passes by way of a governance layer that checks the agent’s identification, belief rating, danger tier, requested device, motion…
In this tutorial, we implement a SkillNet use case as a sensible framework for discovering, putting in, inspecting, evaluating, and organizing reusable AI expertise. We begin by establishing a sturdy SkillInternet consumer with SDK and REST fallback help, then evaluate key phrase search with semantic search to grasp how expertise may be discovered for totally…
In this tutorial, we discover AgentTrove, one of many largest open-source collections of agentic interplay traces, and find out how to work with it effectively. Instead of downloading the complete dataset, we use streaming to examine rows, detect the dialog schema, normalize agent turns, and perceive how person, assistant, system, and device messages are structured….
In this tutorial, we use zeroentropy/zerank-2-reranker, a 4B Qwen3-based cross-encoder reranker, to enhance retrieval high quality. We begin by organising the runtime, loading the reranker, and understanding the way it scores query-document pairs. Then, we transfer from easy pairwise scoring to a sensible two-stage retrieve-and-rerank pipeline, the place a quick bi-encoder first retrieves candidates and…
In this tutorial, we discover the TuringEnterprises/Open-MM-RL dataset as a sensible basis for multimodal reasoning and reinforcement studying with verifiable rewards. We load the dataset, examine its schema, analyze domains, codecs, query lengths, reply sorts, and picture distributions, and visualize consultant examples from every area. We additionally construct a light-weight reward operate that checks precise,…
In this tutorial, we construct a sophisticated federated studying experiment with NVIDIA FLARE. We evaluate FedAvg and FedProx on a non-IID CIFAR-10 setup, the place consumer knowledge is cut up utilizing a Dirichlet distribution to simulate practical label imbalance throughout federated websites. We use the NVFlare Job API to outline and launch federated jobs, whereas…
In this tutorial, we construct an superior agentic AI system utilizing the OpenAI API and a hidden terminal immediate for the API key. We design the agent as a small pipeline of specialised roles: planner, tool-using executor, and critic, in order that we are able to separate technique, motion, and high quality management. We additionally…