In this episode, we discuss Large Language Models (LLMs): how everything started, how do they work, and how to use frameworks such as LangChain to develop intelligent applications.
Hosted by: Youssouf EL Azizi
Notes:
0:00:00 - Introduction and Welcome Notes
0:05:33 - History of LLMs
0:12:00 - The role of transformers in LLMs
0:21:00 - How LLMs differ from other AI methods.
0:26:00 - Emergent Abilities of Large Language Models
0:42:00 - HuggingFace and the role or open-source in LLMs development
0:47:00 - Open source LLMs.
1:04:00 - Using LLMs to build Smart Apps.
1:39:00 - Advice for Software Engineers with no AI background to get started with LLMs.
1:46:00 - Conclusion and Goodbye.
Links:
The Illustrated Transformer Transformers The Annotated Transformer State of GPT Sparks of AGI MiniGPT-4 H2O LLM Studio HuggingFace GPT4All llama LangChain Embracing AI-Powered Applications: A Developer’s Journey with LangChain OpenAI cookbook Jailbreak Chat MathsMaroc Prompt Engineering Emergent Abilities of Large Language Models
