Deep Dive into ChatGPT - Architecture & Comparison with Bard, LLaMa
Details
At this in-person meetup at RV University, we will take a close look at ChatGPT - its basics, origins, architecture, implementation and evolution. There will also be a code walkthrough of how you can build your own tinyGPT! Finally, we will compare ChatGPT with Bard (Google's conversational bot and competitor to ChatGPT) and LLaMa (the Large Language Model from Meta).
AGENDA:
11:00 AM - Welcome note
11:05 AM - Transformers
- Why do we need Attention? Is it really worth the compute?
- How to scale up a simple attention concept to millions of parameters?
- What is the impact of having Attention mechanism?
11:30 AM - GPT - What, How & When of GPT family of models
- The three versions and their details
- How big it has become and future of GPT
- Models derived from GPT - DALL-E, CLIP, ChatGPT, Co-pilot, etc.
11:45 AM - ChatGPT - Why is it a buzzword?
- Implementation overview and future scope
12:15 PM - Walkthrough (with code) of how to build a tinyGPT on your custom conversational data
12:30 PM - Comparison between ChatGPT, Bard, LlaMa
12:50 PM - Q&A and conclusion
SPEAKER: Pranav Raikote is an R&D Engineer (AI & ML) at Applied Singularity and Data Scientist (Energy & AI) at PlexFlo. His research interests include Transformers, Recommendation Systems, Time Series Data Analysis and Computer Vision. Read his 27-part blog series on Natural Language Processing, which includes detailed explanations of seminal research papers in the field as well as practical guidance on how to build expertise in NLP.
FEE: This meetup is FREE to attend but prior registration is required, with seats being available on a first-come-first-served basis. Please register by filling in the form below.
REGISTRATION: Please fill in this Event Registration Form: https://bit.ly/ASRVU-ChatGPT
Note that RSVPing on meetup.com or in the Meetup app DOES NOT reserve your seat. You must register by filling in the form above.
Please reach Nihal at 9663374431 or at [info@appliedsingularity.com](mailto:info@appliedsingularity.com) if you need any clarifications or have any challenges in registration. We look forward to seeing many of you at the session!
We thank our partners RV University, for co-hosting this session with us.