4. Tutorial: Evaluating LLMs on classification tasks скачать в хорошем качестве

4. Tutorial: Evaluating LLMs on classification tasks

Code example: https://github.com/evidentlyai/commun... 00:02 Intro 00:53 Setup and dataset preview 02:25 Training and evaluating a logistic regression model (baseline model) 05:45 Classification quality report for multi-class classification 09:03 Upload the evaluation results to Evidently Cloud 10:53 Zero-shot classifier with LLM (GPT 4.0-mini) 15:40 Zero-shot classifier with a different model (GPT 4.1) 16:45 Comparing the results of different classifiers 18:45 Recap COURSE PLAYLIST Full playlist:    • Course: LLM evaluation for builders   Instructor: Emeli Dral, CTO Evidently AI. LINKS: Docs https://docs.evidentlyai.com Understanding confusion matrix https://www.evidentlyai.com/classific... Multi-class classification metrics https://www.evidentlyai.com/classific... EVIDENTLY Sign up for Evidently Cloud https://www.evidentlyai.com/register Support Evidently on GitHub https://github.com/evidentlyai/evidently