์ฝ˜ํ…์ธ ๋กœ ๊ฑด๋„ˆ๋›ฐ๊ธฐ

์ƒ์„ธ์ •๋ณด

Turns out prompt-engineering is different for open-source LLMs! Actually, your prompts need to be engineered when switching across any LLM โ€” even when OpenAI changes versions behind the scenes, which is why people get confused why their prompts donโ€™t work anymore. Transparency of the entire prompt is critical to effectively squeezing out performance from the model. Most frameworks struggle with this, as they try to abstract everything away or obscure the prompt to seem like theyโ€™re managing something behind the scenes.

But prompt-engineering is not software engineering, so the workflow is entirely different to succeed. Finally, RAG, a form of prompt-engineering, is an easy way to boost performance using search technology. In fact, you only need 80 lines of code to implement the whole thing and get 80%+ of what you need from it (link to open-source repo). Youโ€™ll learn how to run RAG at scale, across millions of documents..๐Ÿฅง๐Ÿค–๐Ÿš€๐Ÿˆบ

Sign up for the online event hereโ†“
โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“โ†“
https://www.eventbrite.com/e/prompt-engineering-for-open-source-llms-tickets-791669814727

๊ด€๋ จ ์ฃผ์ œ

Artificial Intelligence
Machine Intelligence
Neural Networks
Data Mining
Data Science

์ด๋Ÿฐ ์ด๋ฒคํŠธ๋„ ์ข‹์•„ํ•˜์‹ค ๊ฑฐ์˜ˆ์š”