Skip to content
Hot eventDeveloping

OpenTSLM time-series models arrive on Amazon SageMaker JumpStart

1 reports1 reporting sourcesUpdated 6 h ago

Start here

AI digest

Aionic Labs' open-source OpenTSLM family of time-series language models is now available in Amazon SageMaker JumpStart, AWS said, so teams can deploy it inside their own AWS environment. The models combine numerical measurements with text context such as maintenance records and market news; Nexthink's Spark IT agent uses them to produce a state summary, a recommended action and an expected outcome. TimeNet supplies a shared format and API for finding, building and loading the datasets used to train and evaluate these models. Deployment carries hardware and service limits: OpenTSLM runs on a single GPU with at least 24 GB of memory and bfloat16 support, with 32 GB of host memory recommended, and in JumpStart supports instances including ml.g5.2xlarge, ml.g6.4xlarge and ml.g6e.xlarge. A real-time invocation must finish within 60 seconds with a request body of up to 6 MB, and deployed endpoints keep incurring charges until deleted.

Generated from reports · updated 6 h ago

Report timeline

Follow the reports to see the event from different sides.

November 18
  1. AWS Machine Learning Blog
    OpenTSLM time-series language models now available on Amazon SageMaker JumpStart

    Aionic Labs' open source OpenTSLM family of time-series language models is now available in Amazon SageMaker JumpStart, letting teams deploy it in their own AWS environment. The models pair numerical measurements with text context such as maintenance records and market news, and Nexthink's Spark IT agent uses them to produce a state summary, recommended action, and expected outcome. TimeNet provides a shared format and API for finding, building, and loading the datasets used to train and evaluate these models.

Heat for this event

Current, comparable range
8
Peak, comparable range
10November 18 03:00
Change in 24 hours
–

The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.