GenAI Showdown in 10 Minutes! - Step by Step guide to Evaluating LLMs with MLflow!

[StephanieAlba]

In this video, Colton Peltier, a Staff Data Scientist at Databricks, will talk about MLflow’s evaluating capabilities pertaining to GenAI in just 10 min! This video will specifically talk about evaluating 3 different LLMs for a task and will help users determine what LLM is performing the best. Pre-built metrics that come with MLflow + custom metrics that can be built in are used in this demo and comparison.

Timestamps:
0:00 - Introduction
0:35 - Install custom libraries
2:05 - External LLMs
7:35 - Results

►[Documentation] Evaluate large language models with MLflow - https://docs.databricks.com/en/mlflow/llm-evaluate.html
►[Blog] Offline LLM Evaluation: Step-by-Step GenAI Application Assessment on Databricks - https://www.databricks.com/blog/offline-llm-evaluation-step-by-step-genai-application-assessment
►[Blog] Read more about DBRX, a state of the art open LLM here - https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm
►[Github] DBRX on Github - https://github.com/databricks/dbrx
►[Hugging Face] Download DBRX here - https://huggingface.co/databricks/dbrx-base
►[Article] Wired on DBRX and the creation of the world’s most powerful open source AI model - https://www.wired.com/story/dbrx-inside-the-creation-of-the-worlds-most-powerful-open-source-ai-mode...
►[Product] Learn more about Databricks here - https://www.databricks.com/
►Learn/connect with the speaker here - https://www.linkedin.com/in/coltonpeltier/
► Discover more about Databricks in the Skill Builder Series here - https://www.youtube.com/playlist?list=PLeK0Tsm_E67QFwU4trdGZSjcQiTbcsBoz

#databricks #genai #machinelearning #dataintelligence #llm #llama #chatgpt #mixtral #meta #dbrx #lakehouse #mlflow #ml #ai #data #promptengineering #metrics #custom #statistics #generator #complexity #model