In the last 5 months, Generative AI Community has organised:
- Demo Day Meetup in February, a Deep Coffee Hack,
- A Hackathon with 5L INR in cash prizes, 43 submissions from almost 100 participants!
- April meetup which saw a stellar demo on a chatbot for farmers, evaluating question answering from a Llama Index contributor and an Intro to Model Quantisation from Amod Malviya
- May meetup that saw talks on unet architecture by Vignesh, CTO hexo.ai and composability with stable diffusion by Amogh Vaishampayam, Founding Team @ dashtoon.ai
- June Meetup which saw a discussion with Amod Malviya, Kailash Nadh and Charu Tak.
Pratyush is a researcher at Microsoft Research and AI4Bharat (IIT M) with a focus on systems and deep learning for language technologies. He is deeply interested in realising AI as a force of social good.
Talk Theme: Brief story of AI4Bharat - the mission and what we have achieved. Will then move on to LLMs, provide some technical insight into intrinsic dimensionality in deep learning, and his take on how innovation will develop in building custom LLMs
Sachin Dharashivkar will speak about LLM Finetuning and RLHF
Sachin is a founder who is exploring use cases of AI agents. He enjoys training Reinforcement Learning agents and exploring novel applications of Large Language Models.
Talk Theme: Introduction to Supervised and Reinforcement Finetuning.
Three steps of training chatGPT style models. How to perform supervised finetuning. Why is Reinforcement Learning from Human Feedback important and How to train Reward and Policy models.
Location: Bengaluru. Exact location is shared in the invite on approval.
Recommendation systems with Large Language models - Is cold start problem solved ?
Recommendation systems with large language models (LLMs) have the potential to solve the cold start problem, which is the challenge of recommending items to users who have not yet interacted with the system. LLMs can learn to represent users and items in a way that captures their latent preferences, even if they have not interacted with the system very much. This allows LLMs to make recommendations to new users that are more likely to be relevant to their interests.
However, the cold start problem is not completely solved with LLMs. LLMs still need to be trained on a large dataset of user-item interactions in order to learn to represent users and items effectively. This can be a challenge, especially for new services that do not have a lot of user data. Additionally, LLMs can be computationally expensive to train, which can make them impractical for some applications.
Despite these challenges, LLMs have the potential to significantly improve the performance of recommendation systems, especially for new users. As LLMs become more powerful and efficient, they are likely to play an increasingly important role in recommendation systems.