MODEL REFERENCE / vllm-sr
vllm-sr/d3-lite
Decision 3.0's 0.8B decision model: answers typed questions (choice, yes / no, score) about text, JSON, images and videos with a probability for every option, without generating text.
MI300X: 415 of 416 decisions match the checkpoint runtime (one near-tie); 3.1x its server's requests per second at 64 clients
View on HuggingFace
View on ModelScope02 / Configure
Configure serving
Choose engine, hardware and deployment options. The command updates as you go.
03 / Understand