kev
6 TagsUpdated Apache-2.0by Jared Palmer
Decision models by Jared Palmer: a LoRA on a Qwen3.5 base plus a pointer head that scores every option at its own span, in one forward pass per question. Calibrated with Kev's own temperature.
decision0.76b4.2b7.9b
Tags
| Name |
|---|
| kevlatestSame as kev:4b.9.5 GB · 8192 ctx · English |
| kev:0.8bQwen3.5-0.8B base, round 15, 0.460 on typed decisions: small and fast.1.8 GB · 8192 ctx · English |
| kev:4bQwen3.5-4B base, round 10, 0.669 on typed decisions. Best on a GPU.9.5 GB · 8192 ctx · English |
| kev:4b-fp16Kev on Qwen3.5-4B base (LoRA and pointer head): more accurate than 0.8b out of domain. Needs about 9 GB of memory. This tag computes in fp16 on NVIDIA GPUs: faster than kev:4b, with at least 99.5 % of its decisions the same. On a CPU it runs, slowly; use kev:4b there.9.5 GB · 8192 ctx · English |
| kev:9bQwen3.5-9B base, 0.722 on typed decisions: the most accurate Kev. Needs a 24 GB GPU.19.5 GB · 8192 ctx · English |
| kev:9b-fp16Largest Kev (Qwen3.5-9B base, LoRA and pointer head). Needs about 17 GB of memory; best on a 24 GB GPU. This tag computes in fp16 on NVIDIA GPUs: faster than kev:9b, with at least 99.5 % of its decisions the same. On a CPU it runs, slowly; use kev:9b there.19.5 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.