PyData Prague #27 - LLMs Anonymous

👋 Hello data privateers and advanced language models!

🗓️ The 27th Prague PyData meetup is sponsored by Rossum and it will take place at Miton offices. The talks will start at 18:30 and we encourage you to come as soon as 18:00 to enjoy the opportunity to socialise and refresh yourselves (which you can continue doing during the break and after the talks).

🤗 Our main goal is to build the community around Python and data and make it welcoming to people of various skills and experience levels.

⚡ If you are interested in giving a lightning talk (up to 5 minutes to present an idea, tool or results related at least to some degree to Python and/or data), please contact us before or during the event.

📢 Anonymization: Why is it so hard?
Katharine Jarmul
In this talk, we'll look at the problem of anonymizing data and pick apart several common mistakes people make when attempting to remove or modify sensitive data in order to anonymize it. We'll review basic approaches like pseudonymization and redaction, and then look at more advanced approaches like k-anonymization/aggregation and differential privacy. Expect to think a bit like a hacker and a data scientist to see if you can imagine ways to defeat these approaches, and explore how intertwined information theory is to privacy work.

📢 LLMs, the do-it-yourself edition
Štěpán Procházka
How Rossum researched, trained and deployed their very own T-LLM to process millions of documents a month. #huggingface #pytorch-lightning #nvidia-triton #pgvector #vllm https://rossum.ai/blog/rossum-aurora/

The venue will open at 6.00pm but the intro won't take place sooner than at 6:30pm. There will be refreshments available, 🤗 sponsors!

Please, RSVP here.
See you soon,
PyData Prague team