talk-data.com talk-data.com

Event

MLOps.community Berlin - Summer Edition ☀️☀️

2024-07-25 – 2024-07-25 Meetup Visit website ↗

Activities tracked

3

Hello Community!

Experience an engaging evening of insightful discussions and networking on July 25th at 18:00 at TechSpace Kreuzberg 💫

This event is supported by Nebius AI 🙌 Nebius AI is an AI-centric cloud platform ready for intensive workloads.

Join us for two main talks, a lightning talk and then some summer activities 🥳.

Main talks:

  1. The first one from Sergei Polezhaev about: "Taming AI, or how we build the alignment pipeline"
  2. The second one from Joanna Stoffregen about: "Challenges & lessons learned from implementing RAG systems".

We will also have a lightning talk by Katja Wittfoth: "Function Calling: Teaching LLMs to use tools and extract structured data".

We booked a place that has a terrace where we will be able to network and meet peers before and after the talks! 🌞

On top of this, we will have a trivia quiz in which you can win cool prizes! Make sure to be on time (see agenda below) to take part in the trivia.

The meetup agenda is the following:

  • 6:00 pm - Open the doors & Food
  • 6:40 pm - Trivia Quiz
  • 7:00 pm - Taming AI, or how we build the alignment pipeline by Sergei Polezhaev (Nebius.ai)
  • 7:30 pm - break
  • 7:45 pm - Challenges & lessons learned from implementing RAG systems by Joanna Stoffregen (Labsbit.ai)
  • 8:15 pm - Function Calling: Teaching LLMs to use tools and extract structured data by Katja Wittfoth
  • 8:20 pm - Socializing

🚀 RSVP Now 🚀

🎙️Main speakers:

  • Sergei Polezhaev, In this presentation, we will explore into the key aspects of aligning Large Language Models (LLMs) and explore how to set up the necessary infrastructure to maintain a versatile alignment pipeline. Specifically, we will cover: · Incorporating LLMs into the data collection for supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to maximize efficiency. · Techniques for instilling desired behaviors in LLMs with the use of prompt tuning. · A cutting-edge workflow management approach, and how it facilitates rapid prototyping of highly-intensive distributed training procedures. This session is tailored for machine learning engineers who are deploying their LLMs and seeking to improve their models.
  • Joanna Stoffregen, Large Language Models (LLMs) are powerful tools for generating text, yet they often fall short when accurate or industry-specific information is needed. Retrieval-Augmented Generation (RAG) has become a popular method to address this issue, augmenting LLMs with an external knowledge base. However, implementing RAG introduces distinct challenges.

In this presentation, Joanna will share practical insights into the challenges encountered while implementing RAG systems, alongside strategies for overcoming them. You'll be equipped with the tools and methodologies needed to navigate these challenges successfully.

--- 🔒 Code of Conduct: Please familiarize yourself with our Code of Conduct before attending the event. We strive to create an inclusive and respectful environment for all participants. By joining us, you agree to abide by the guidelines outlined in our Code of Conduct. You can find it here. ​​📷 Important note: Please be advised that this event will be recorded and photographed, and we will have a photographer on-site. If you prefer not to be included in any recordings or photographs, please do not hesitate to let us know before or during the event. Your comfort and privacy are important to us.

MachineLearning #MeetupEvent #BerlinTech #MLOPS

Sessions & talks

Showing 1–3 of 3 · Newest first

Search within this event →

Function Calling: Teaching LLMs to use tools and extract structured data

2024-07-25
talk
Katja Wittfoth (San Francisco (visiting))
LLM

Function Calling: Teaching LLMs to use tools and extract structured data

Challenges & lessons learned from implementing RAG systems

2024-07-25
talk
Joanna Stoffregen (Labsbit.ai)
LLM RAG

Retrieval-Augmented Generation (RAG) has become a popular method to address this issue, augmenting LLMs with an external knowledge base. However, implementing RAG introduces distinct challenges. In this presentation, Joanna will share practical insights into the challenges encountered while implementing RAG systems, alongside strategies for overcoming them. You'll be equipped with the tools and methodologies needed to navigate these challenges successfully.

Taming AI, or how we build the alignment pipeline

2024-07-25
talk
AI/ML Data Collection LLM

In this presentation, we will explore into the key aspects of aligning Large Language Models (LLMs) and explore how to set up the necessary infrastructure to maintain a versatile alignment pipeline. Specifically, we will cover: Incorporating LLMs into the data collection for supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to maximize efficiency. Techniques for instilling desired behaviors in LLMs with the use of prompt tuning. A cutting-edge workflow management approach, and how it facilitates rapid prototyping of highly-intensive distributed training procedures. This session is tailored for machine learning engineers who are deploying their LLMs and seeking to improve their models.