decider
5 TagsUpdated Apache-2.0by Mapika
Decoder decision models by Mapika on Qwen3.5: the answer is read from option-letter logits in one forward pass.
decisionlong-contextvision0.75b1.9b2.2b4.2b
Tags
| Name |
|---|
| deciderlatestSame as decider:2b.3.8 GB · 32768 ctx · English |
| decider:0.8bQwen3.5-0.8B base, 0.505 on typed decisions: smaller and faster.1.5 GB · 32768 ctx · English |
| decider:2bQwen3.5-2B base (v12), 0.608 on typed decisions, one fitted temperature per answer type.3.8 GB · 32768 ctx · English |
| decider:2b-visionReads an image as well as the state: Qwen3.5-2B vision-language with v5 text weights. One PNG per request, up to 10 options.4.5 GB · 32768 ctx · English |
| decider:4bQwen3.5-4B base (v3), 0.678 on typed decisions, one fitted temperature per answer type. Best on a GPU.8.4 GB · 32768 ctx · English |
Tags without a suffix load fp16 on a CUDA GPU and fp32 on CPU; add -fp16 or -fp32 to pin one precision.