IBM Journey to AI blog

NOVEMBER 24, 2023

Generating configuration management inputs (for CMDB)and changing management inputs based on release notes generated from Agility tool work items completed per release are key Generative AI leverage areas. It also requires some focused effort to improve the data quality of data needed for tuning the models.

Generative AI 284

Generative AI Auto-complete DevOps Automation 284

AssemblyAI

SEPTEMBER 18, 2023

It offers a simple API for applying LLMs to up to 100 hours of audio data, even exposing endpoints for common use tasks It's smart enough to auto-generate subtitles, identify speakers, and transcribe audio in real time. Start Building LLM Apps on Voice Data Ready to take action on your spoken data?

Large Language Models 130

Large Language Models BERT Auto-complete LLM 130

The MLOps Blog

SEPTEMBER 26, 2024

Causes of hallucinations include insufficient training data, misalignment, attention limitations, and tokenizer issues. Effective mitigation strategies involve enhancing data quality, alignment, information retrieval methods, and prompt engineering. In extreme cases, certain tokens can completely break an LLM.

LLM 72

LLM Prompt Engineer Prompt Engineering Auto-complete 72

AWS Machine Learning Blog

APRIL 17, 2023

SageMaker LMI containers includes model download optimization by using the s5cmd library to speed up the model download time and container startup times, and eventually speed up auto scaling on SageMaker. A complete example that illustrates the no-code option can be found in the following notebook.

Prompt Engineer 103

Prompt Engineer Prompt Engineering Deep Learning Machine Learning 103