DeepSeek-R1: A Deep Dive into Next-Gen LLM Reasoning
Details
We will walk through the paper:
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
[2501.12948] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Join us for an insightful 2-hour session exploring DeepSeek-R1, a groundbreaking reasoning model that challenges conventional LLM training methods. This session is designed for Engineers, and enthusiasts eager to understand and experiment with cutting-edge LLM reasoning techniques.
What to Expect?
We start by exploring how LLMs reason, the challenges of LLMs face, and how models like OpenAI’s GPT and Gemini compare to DeepSeek. We will break down the limitations of current LLM training and why reinforcement learning (RL) without explicit reward models is a game-changer. We will walk through Python code demonstrating RL and CoT/GRPO
You will gain a technical and conceptual understanding of DeepSeek’s unique approach, including its Mixture of Experts (MoE) framework, GPU optimizations, and memory-efficient neural network execution. We will explore DeepSeek’s training and inference pipelines, including cold-start fine-tuning, rejection sampling, and reasoning-oriented RL.
For hands-on learners, we will run DeepSeek-R1 on a laptop, test its reasoning capabilities, and fine-tune it for real-world applications. You’ll also learn how to optimize reasoning, create CoT datasets, and develop reasoning-aware applications based on DeepSeek.
Why Attend?
Understand how LLMs process reasoning and what sets DeepSeek apart
Gain insights into advanced AI training techniques
Experiment with DeepSeek on your own hardware
Learn best practices for reasoning-aware AI applications
----
We are a group of applied AI practitioners and enthusiasts who have formed a collective learning community. Every Wednesday evening, we hold our research paper reading seminar covering an AI topic. One member carefully explains the paper, making it more accessible to a broader audience. Then, we follow this reading with a more informal discussion and socializing.
You are welcome to join this in person or over Zoom. SupportVectors is an AI training lab located in Fremont, CA, close to Tesla and easily accessible by road and BART. We follow the weekly sessions with snacks, soft drinks, and informal discussions.
If you want to attend by Zoom, the Zoom registration link will be visible once you RSVP. Note that we have had to change and add security to the Zoom link to prevent Zoom bombing.
Speaker :
Krishnan Ramaswamy
LinkedIn: https://www.linkedin.com/in/krishnan-ramaswamy/
Gen AI Product Development & Principal Architect @ Cisco for, AI, ML, and Gen AI-enabled computer networking products & solutions.
In my current role as Gen AI Product Owner and Principal Architect at Cisco, I spearhead the innovation of AI/ML-enabled solutions within the Customer Experience portfolio, concentrating on Data Center and Security domains. Our team's initiatives have led to the identification of transformative Gen AI solutions, significantly enhancing productivity across support teams, customers, and partners.
I take pride in leading the development of advanced AI technologies, such as Conversational AI Search and Custom LLMs-based applications, which have been instrumental in advancing Cisco's product configuration and deployment design. The strategic integration of next-generation products and services under my guidance has driven meaningful advancements, positioning us at the forefront of the industry's evolution.
You are welcome to join this in person or over Zoom (https://us02web.zoom.us/meeting/register/tZUvf-uvrTwvHdP9B-vE03j3BapgRypn64CS). SupportVectors is an AI training lab located in Fremont, CA, close to Tesla and easily accessible by road and BART. We follow the weekly sessions with snacks, soft drinks, and informal discussions.