Editors Pick

In this tutorial, we construct an ensemble climate forecasting workflow with NVIDIA Earth2Studio. We set up the required Earth2Studio parts whereas preserving Colab’s present CUDA-enabled PyTorch atmosphere, load the FCN prognostic mannequin, and retrieve atmospheric preliminary situations from GFS. We then implement a customized wind-power diagnostic that converts 10-meter wind parts into turbine capability elements,…

In this tutorial, we design an end-to-end preference-learning workflow utilizing the Anthropic HH-RLHF dataset and Direct Preference Optimization (DPO). We start by making ready a sturdy Colab surroundings, loading and parsing chosen–rejected response pairs, and auditing the dataset for structural and length-based choice biases. We then run lexical shortcut diagnostics to find out whether or…

In this tutorial, we construct an entire pixel-native retrieval-augmented era pipeline from scratch and study how doc retrieval works with out counting on standard HTML parsing, textual content extraction, or mounted chunking methods. We render net pages and PDF paperwork as photographs, divide them into overlapping tiles, generate multimodal embeddings with SigLIP, CLIP, or an…

In this tutorial, we construct a sophisticated end-to-end time-series forecasting workflow with TimesFM 2.5. We start by configuring the runtime, putting in the required dependencies, detecting out there {hardware}, and producing a sensible multi-store retail dataset with pattern, seasonality, pricing, promotions, holidays, temperature results, and random variation. We then load and compile the TimesFM 2.5…

In this tutorial, we discover FAIRChem v2 and the UMA common machine-learning interatomic potential as a unified framework for atomistic simulation across molecular chemistry, catalysis, and inorganic supplies. We configure an atmosphere, authenticate with Hugging Face to entry the gated UMA mannequin weights, and initialize task-specific calculators for the omol, oc20, and omat domains. We…