This blog is the official source for the updates, articles and posts from the OptiML team.
Evaluating the Impact of Compression Techniques on Performance in Large Language
July 18, 2024
By OptiML Team
Large language models (LLMs) like GPT-4, PaLM, and LLaMA have demonstrated remarkable capabilities across multitask language understanding.
Impact of Calibration Data on Compression Techniques for Large Language Models
August 13, 2024
By OptiML Team
The process of compressing large language models (LLMs) like LLaMA-2-7B involves more than just reducing the number of parameters. The choice of calibration data—used during the compression process—plays a critical role in determining how well the compressed model will perform on downstream tasks.
.svg){kind=logo}
.png)
