Hugging Face

State of Open AI - June Edition! https://lnkd.in/db6HTysc June is a great month for the open ML space, but it's hard to keep up! I curated a list of new model releases and grouped them into categories. Let me know if this is useful :)

Alibaba presents Qwen2 Technical Report paper page: https://lnkd.in/eVHdeiZS This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruction-tuned language models, encompassing a parameter range from 0.5 to 72 billion, featuring dense models and a Mixture-of-Experts model. Qwen2 surpasses most prior open-weight models, including its predecessor Qwen1.5, and exhibits competitive performance relative to proprietary models across diverse benchmarks on language understanding, generation, multilingual proficiency, coding, mathematics, and reasoning. The flagship model, Qwen2-72B, showcases remarkable performance: 84.2 on MMLU, 37.9 on GPQA, 64.6 on HumanEval, 89.5 on GSM8K, and 82.4 on BBH as a base language model. The instruction-tuned variant, Qwen2-72B-Instruct, attains 9.1 on MT-Bench, 48.1 on Arena-Hard, and 35.7 on LiveCodeBench. Moreover, Qwen2 demonstrates robust multilingual capabilities, proficient in approximately 30 languages, spanning English, Chinese, Spanish, French, German, Arabic, Russian, Korean, Japanese, Thai, Vietnamese, and more, underscoring its versatility and global reach. To foster community innovation and accessibility, we have made the Qwen2 model weights openly available on Hugging Face1 and ModelScope2, and the supplementary materials including example code on GitHub3. These platforms also include resources for quantization, fine-tuning, and deployment, facilitating a wide range of applications and research endeavors.

Competition admins can now access admin control right from the competition space. Want to host a competition? Use the competition creator or contact us 🚀

Yesterday, Julien Chaumond tweeted about how the 🤗 Huggingface datasets viewer is now embeddable (https://lnkd.in/d-sDKrXR). Inspired, I made a quick PR to integrate the view in the ZenML dashboard. Wrote how I did it in a blog today, thought it be useful for the community: https://lnkd.in/dZzGH3Cj tldr; Return a 🤗 Huggingface dataset from a ZenML step, and see an embedded view of it right in the dashboard.

Hugging Face Tasks is a documentation project for everyone to start building with machine learning! 🤗📖 Link in comments 💬 This month we have shipped a lot of newbies, updated many models and datasets, completely renewed feature extraction task page to have modern retrieval embeddings with RAG scenarios and added a new task page for vision language models 🤩

We just removed the requirement to have a payment method attached to your org when creating competitions on Hugging Face 🚀 Now, universities, organizations & private individuals can create free-tier competitions without the need to worry about CC. https://lnkd.in/dJp82BGv

🔥 🔥 Generate 3D characters with CharacterGen (SIGGRAPH'24) in high-quality shapes and textures! - Highley useful for downstream applications such as animation and game dev - Code, demo, and pretrained weights available now on 🤗 Hugging Face Official Demo on 🤗 Hugging Face Spaces: https://lnkd.in/gVaQ6B4w Model on 🤗 Hugging Face Hub: https://lnkd.in/gew2cyZq CharacterGen (SIGGRAPH'24) 👀 To get more details on the Project, visit their website: https://lnkd.in/gsXcyGmX 👩💻 GitHub Code: https://lnkd.in/gPpbJuXw 😀 To build a Gradio demo locally for CharacterGen: https://lnkd.in/gJgb-xyp

I had an incredible time at EuroPython over the past three days! 🎉 Presenting my poster, receiving my EuroPython cookie, and connecting with the vibrant Python community were absolute AMAZING 🐍 🌟 I also had the pleasure of delivering a ⚡️ lightning talk about AutoQuizzer, where we challenged Llama 3 to a quiz showdown. Shoutout to Stefano Fiorucci for creating such an impressive demo with #Haystack, Groq, and Gradio! 🙌 Catch the lightning talk recording here: https://lnkd.in/dR2ctzdB Explore the AutoQuizzer Demo: https://lnkd.in/dp-M72XR Already looking forward to EuroPython 2025. See you all there! 👋 #europython2024 #Python

Microsoft presents SpreadsheetLLM Encoding Spreadsheets for Large Language Models paper page: https://lnkd.in/eqvykDdT Spreadsheets, with their extensive two-dimensional grids, various layouts, and diverse formatting options, present notable challenges for large language models (LLMs). In response, we introduce SpreadsheetLLM, pioneering an efficient encoding method designed to unleash and optimize LLMs' powerful understanding and reasoning capability on spreadsheets. Initially, we propose a vanilla serialization approach that incorporates cell addresses, values, and formats. However, this approach was limited by LLMs' token constraints, making it impractical for most applications. To tackle this challenge, we develop SheetCompressor, an innovative encoding framework that compresses spreadsheets effectively for LLMs. It comprises three modules: structural-anchor-based compression, inverse index translation, and data-format-aware aggregation. It significantly improves performance in spreadsheet table detection task, outperforming the vanilla approach by 25.6% in GPT4's in-context learning setting. Moreover, fine-tuned LLM with SheetCompressor has an average compression ratio of 25 times, but achieves a state-of-the-art 78.9% F1 score, surpassing the best existing models by 12.3%. Finally, we propose Chain of Spreadsheet for downstream tasks of spreadsheet understanding and validate in a new and demanding spreadsheet QA task. We methodically leverage the inherent layout and structure of spreadsheets, demonstrating that SpreadsheetLLM is highly effective across a variety of spreadsheet tasks.

Open-source AI strikes back with AuraFlow v0.1🤩 - Largest open-sourced flow-based T2I model with Apache 2.0 license - 6.8B parameters - DiT Encoder blocks - Better instruction following - GenEval score 0.703 with prompt enhancement 🥳 Congratulations to Simo, Batuhan & the whole fal ai team on this epic release!👏 Explore AuraFlow with the community Gradio demo: https://lnkd.in/gY27BETy Find the open-source AuraFlow model on Hugging Face Hub: https://lnkd.in/g4ttnJTw Read the fal ai official release blog: https://lnkd.in/gNiK9uYN