Matt Squire - Diving into Transformer Model Internals | PyData London 25
PyData
@pydatatvAbout
PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. We aim to be an accessible, community-driven conference, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases.
Latest Posts
Video Description
www.pydata.org Diving into Transformer Model Internals While everybody and their dog is building applications on generative AI, the inner workings of transformers - the model architecture behind genAI age - is a mystery for most people. In this talk, I'll walk through how transformers are implemented, using real-life Python code from the HuggingFace transformers library. PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases.
Essential Transformer Model Tools
AI-recommended products based on this video

Seasonic Focus V4 GX-1000 (ATX3) - 1000W - 80+ Gold - ATX 3.0 & PCIe 5.1 Ready -Full-Modular -ATX Form Factor -Premium Japanese Capacitor -10 Year Warranty -Nvidia RTX 30/40 Super & AMD GPU Compatible

(2 Pack) Outlet Wall Mount Holder for Google Home Mini and Google Nest Mini, A Space-Saving Accessories with Cord Management for Google Mini Smart Speaker, No Messy Wires or Screws

MSI Stealth A18 AI+ A3XWIG-013CA 18" UHD+ mini LED 120Hz Gaming Laptop, AMD Ryzen AI 9 HX 370, RTX 5080, 64GB DDR5, 2TB NVMe SSD, Windows 11 Home

Asus Zenbook S 14, Next-Level AI PC, 14” Ultrathin Laptop, 3K 120Hz OLED Touchscreen, Intel Core™ Ultra 7 (Series 2) Processor, 16GB Memory, 1TB SSD, Wi-Fi 7, Zumaia Gray, UX5406SA-DH71T-CB

MSI Stealth 18 HX AI 18” 240Hz QHD+ Gaming Laptop: Intel Ultra 9-275HX, NVIDIA Geforce RTX 5080, 32GB DDR5, 2TB NVMe SSD, Wi-Fi 7, Win 11 Home :Midnight Black A2XWIG-045US










![Pandas + Dask DataFrame 2.0 - Comparison to Spark, DuckDB and Polars [PyCon DE & PyData Berlin 2024]](https://imgz.pc97.com/?width=500&fit=cover&image=https://i.ytimg.com/vi/qyvLJ2LvKLc/hqdefault.jpg)





















