Nemotron Models Ideas Portal

1 Vote

Controlling reasoning length - define allowed number of tokens

To control the length of reasoning I want to be able to define the number of tokens the model can use in the final answer

Created 10 Sep 20:46

0
1 Vote

Hardware optimization - A model optimized for A10G GPUs

Develop a model that is most efficient on an A10G GPU

Created 10 Sep 13:40

0
1 Vote

Expanded Model Availability - Fireworks

No description provided

Created 10 Sep 13:27

0
1 Vote

Efficiency needs - I want to maximize throughput for large batches

Develop a model that excels in workloads with large batches, where the main goal is to optimize throughput

Created 10 Sep 13:24

0
0 Vote

Expanded Model Availability - Openrouter

No description provided

Created 10 Sep 13:23

0