Remove 2024 Remove Benchmark Remove Calibration
article thumbnail

Boost inference performance for Mixtral and Llama 2 models with new Amazon SageMaker containers

AWS Machine Learning

In January 2024, Amazon SageMaker launched a new version (0.26.0) In this post, we explore the latest features introduced in this release, examine performance benchmarks, and provide a detailed guide on deploying new LLMs with LMI DLCs at high performance. of Large Model Inference (LMI) Deep Learning Containers (DLCs).

article thumbnail

Improve factual consistency with LLM Debates

AWS Machine Learning

This post and the subsequent code implementation were inspired by one of the International Conference on Machine Learning (ICML) 2024 best papers on LLM debates Debating with More Persuasive LLMs Leads to More Truthful Answers. LLM debates need to be calibrated and aligned with human preference for the task and dataset.