sura
3 TagsUpdated Apache-2.0by Ollaya
Ollaya's own decoder decision model: Qwen3.5 distilled from pplx-decider:flash in its joint format. Every question of a request shares one sequence and reads the whole request; up to 255 options. English, zero-shot.
decisionzero-shot0.8b2b
Tags
| Name |
|---|
| suralatestSame as sura:2b.4.5 GB · 8192 ctx · English |
| sura:0.8bQwen3.5-0.8B: 0.560 on typed decisions, zero-shot; 60 ms for five questions on an RTX 5090.1.7 GB · 8192 ctx · English |
| sura:2bQwen3.5-2B: 0.570 on typed decisions, zero-shot; 63 ms for five questions on an RTX 5090.4.5 GB · 8192 ctx · English |
Tags without a suffix load fp16 on a CUDA GPU and fp32 on CPU; add -fp16 or -fp32 to pin one precision.