Research that reaches the hardware.
Tiyuvta is a research lab working on the models and engines behind customer-controlled deployments. Our experiments inform the work; the workload decides what we ship.
Research and paid work belong together
We research ways to run models with less memory, shorten response times and improve Hebrew processing. Our customer work builds and deploys systems around their needs. How does quantization save memory? Learn the model deployment terms.
Know what will be handed over
Before starting, we agree the configuration, measurement records, operating instructions and permitted artifacts to be delivered. Model and software licenses still apply. The proposal names who operates the system and what continuing support covers.
Inspect the evidence in its own context
Research notes name their setup and limitations. Deployment measurements describe the deployment tested. Neither substitutes for measuring your workload.
Public research on GitHubScope, handover and support
Your proposal sets out the work, price, start and handover dates, and what is needed from you. Hardware, cloud charges, engineering and ongoing operation belong in the cost discussion. On-site days and continuing support are agreed as part of the engagement. Our engineers keep supporting the systems they build under those terms.