Want to build your first 𝗟𝗟𝗠 𝗽𝗿𝗼𝗷𝗲𝗰𝘁 but don't know where to start?

If you want to 𝗹𝗲𝗮𝗿𝗻 in a 𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝗱 𝘄𝗮𝘆 to 𝗯𝘂𝗶𝗹𝗱 𝗟𝗟𝗠 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 using good 𝗟𝗟𝗠𝗢𝗽𝘀 principles…

We want to announce that we just 𝗿𝗲𝗹𝗲𝗮𝘀𝗲𝗱 𝟴 𝗠𝗲𝗱𝗶𝘂𝗺 𝗹𝗲𝘀𝘀𝗼𝗻𝘀 for the 𝗛𝗮𝗻𝗱𝘀-𝗼𝗻 𝗟𝗟𝗠𝘀 𝗰𝗼𝘂𝗿𝘀𝗲 that will put you on the right track ↓

.

Within the 𝟴 𝗠𝗲𝗱𝗶𝘂𝗺 𝗹𝗲𝘀𝘀𝗼𝗻𝘀, you will 𝗴𝗼 𝘀𝘁𝗲𝗽-𝗯𝘆-𝘀𝘁𝗲𝗽 through the 𝘁𝗵𝗲𝗼𝗿𝘆, 𝘀𝘆𝘀𝘁𝗲𝗺 𝗱𝗲𝘀𝗶𝗴𝗻, and 𝗰𝗼𝗱𝗲 to learn how to build a:

→ 𝗿𝗲𝗮𝗹-𝘁𝗶𝗺𝗲 𝘀𝘁𝗿𝗲𝗮𝗺𝗶𝗻𝗴 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲 (deployed on AWS) that uses Bytewax as the stream engine to listen to financial news, cleans & embeds the documents, and loads them to a vector DB

→ 𝗳𝗶𝗻𝗲-𝘁𝘂𝗻𝗶𝗻𝗴 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲 (deployed as a serverless continuous training) that fine-tunes an LLM on financial data using QLoRA, monitors the experiments using an experiment tracker and saves the best model to a model registry

→ 𝗶𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲 built in LangChain (deployed as a serverless RESTful API) that loads the fine-tuned LLM from the model registry and answers financial questions using RAG (leveraging the vector DB populated with financial news)

We will also show you how to 𝗶𝗻𝘁𝗲𝗴𝗿𝗮𝘁𝗲 various 𝘀𝗲𝗿𝘃𝗲𝗿𝗹𝗲𝘀𝘀 𝘁𝗼𝗼𝗹𝘀, such as:

• Comet ML as your ML Platform;
• Qdrant as your vector DB;
• Beam as your infrastructure.

𝗪𝗵𝗼 𝗶𝘀 𝘁𝗵𝗶𝘀 𝗳𝗼𝗿?

The series targets MLE, DE, DS, or SWE who want to learn to engineer LLM systems using LLMOps good principles.

𝗛𝗼𝘄 𝘄𝗶𝗹𝗹 𝘆𝗼𝘂 𝗹𝗲𝗮𝗿𝗻?

The series contains 4 hands-on video lessons and the open-source code you can access on GitHub.

𝗖𝘂𝗿𝗶𝗼𝘂𝘀?

Check out the 8 Medium lessons of the Hands-on LLMs course and start building your own LLMs system:

The Hands-on LLMs Course 👉 https://medium.com/decodingml/hands-on-llms/home