huggingface
huggingface on Beyond Market Intelligence: a running collection of 2 stories we have gathered and hand-picked because they are worth your time. Every post here touches on huggingface in some way — the news, the analysis, the deep dives, and the occasional surprise find. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work with data. New stories are added to this page as we find them, so check back if you want to keep up with what is happening around huggingface, or subscribe to the RSS feed to get them as soon as they are published. Browse the collection below, or head back to the homepage to see everything Beyond Market Intelligence is covering right now.
![Bart- A vintage llm [R]](https://preview.redd.it/27z2aamswclh1.png?width=640&crop=smart&auto=webp&s=ba36a31376435bcec7f675b732595ad9dd2641a7)
Bart- A vintage llm [R]
Unbounded Labs proudly introduces Bart, a 2.82B parameter LLM meticulously trained from scratch on a unique corpus of 20.1B tokens of English text predating 1931. After three months and a modest $800 investment, we’ve achieved a significant milestone: the best-performing vintage base model at its scale on Vintage CORE. Our research, detailed in a comprehensive article, explores the potential for LLMs to replicate historical scientific reasoning—a crucial step toward understanding AI originality. Explore Bart and our methodology at the links provided.
EU AI Act OpenRAG: 933 legally structured chunks and BGE-M3 embeddings in one SQLite file [P]
Introducing EU AI Act OpenRAG, a meticulously structured resource for legal-NLP experimentation. This downloadable corpus, based on Regulation (EU) 2024/1689, comprises 933 legally-aligned chunks—organized by article paragraph, recital, and definition—within a single SQLite file. Utilizing BGE-M3 embeddings, it delivers a normalized 1024-dimensional vector for each chunk, alongside EUR-Lex links and application-date metadata. Initial evaluations demonstrate improved recall and QA performance compared to baselines, showcasing the value of structural chunking. Explore the dataset at huggingface.co/datasets/faitholopade