Hugging Face demonstrates building a fast multilingual OCR model using synthetic data generation. The approach combines data synthesis techniques with model optimization to achieve efficient performance across multiple languages. This method reduces reliance on expensive labeled datasets while maintaining accuracy.See more
Hugging Face tutorial on training and finetuning multimodal embedding and ranking models using Sentence Transformers. Covers practical techniques for building custom embeddings and rerankers for search and retrieval applications. Targeted at engineers with ML and transformer model experience.See more
Tutorial on implementing tool calling with Gemma 4, an open-weights model, using Python. Covers practical setup and integration patterns for developers building with open-source LLMs. Relevant for teams evaluating alternatives to closed-model APIs.See more
WildDet3D is an open-source monocular 3D detection model released by AI2. Enables 3D object detection from single-image inputs. Technical resource for computer vision product teams.See more
Cannot assess without post body.See more
AI2 demonstrates integrating MolmoWeb, an open-source vision model, as a Claude Code skill to extend Claude's multimodal capabilities. The tutorial shows how to use MolmoWeb for image understanding tasks within Claude's code execution environment.See more