# post

Generative AI with LLMs

2024-04-24 • Transformers and fine-tuning

I just started a course on generative AI and LLMs offered by Coursera. The first few videos are an introduction to the use cases and theory of LLMs. Topics covered include the business applications of LLMs, overview of terminology like "transformers" and "fine-tuning a model", and type of LLMs (Llama, GPT, etc.). Overall, this session described the types of interactions humans have with LLMs (inputs and outputs) and the types of tasks LLMs are proficient at performing.

One particularly interesting topic covered was "attention weights". At a high level, "attention weights" enable an LLM to encode/decode complex language constructs (like the relevance of certain words in relation to other words in a sentence)