Editors Pick

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 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 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 discover how to apply post-training quantization to an instruction-tuned language mannequin using llmcompressor. We begin with an FP16 baseline and then examine a number of compression methods, together with FP8 dynamic quantization, GPTQ W4A16, and SmoothQuant with GPTQ W8A8. Along the way in which, we benchmark every mannequin variant for disk…