New course with Lamini and Meta: Improving Accuracy of LLM Applications
Enroll now: https://bit.ly/3yEasaS
Improving Accuracy of LLM Applications was made in collaboration with Lamini and Meta and taught by Lamini’s CEO and co-founder Sharon Zhou, and Meta’s Senior Director of Partner Engineering, Amit Sangani.
Developers often face challenges with inconsistent outcomes when working with LLM applications. This course provides a structured approach to improve the accuracy and reliability of your LLM solutions.
Using Llama’s family of open-source models, you'll build an SQL agent, integrate performance evaluation metrics, and apply prompt engineering and self-reflection to enhance model behavior. Finally, you will fine-tune the model with techniques like LoRA and memory tuning that embeds facts in model weights to reduce hallucinations.
In detail, you will:
Build a text to SQL agent and simulate situations where it hallucinates to begin the evaluation process.
Build an evaluation framework to systematically measure performance, including criteria for good evaluations, best practices, and how to develop an evaluation score.
Learn how instruction fine-tuning enhances pre-trained LLMs to follow instructions, and how memory fine-tuning embeds facts to reduce hallucinations.
Break fine-tuning myths and see how Performance-Efficient Fine-tuning (PEFT) techniques like Low-Rank Adaptation (LoRA) reduce training time by 100x and Mixture of Memory Experts (MoME) reduces it even further.
Go through an iterative process of generating training data and fine-tuning, learning practical tips such as adding examples, generating variations, and filtering generated data to increase model accuracy.
Start improving the accuracy of LLM applications today!
Learn more: https://bit.ly/3yEasaS
Watch video New course with Lamini and Meta: Improving Accuracy of LLM Applications online without registration, duration hours minute second in high quality. This video was added by user DeepLearningAI 14 August 2024, don't forget to share it with your friends and acquaintances, it has been viewed on our site 3,032 once and liked it 75 people.