strands-decider
5 TagsUpdated Apache-2.0by Strands Agents
Strands Agents' decision model: a LoRA and a pointer head on Qwen3.5-2B base or on Gemma 4 E2B / E4B. Each question is one row with a line per option, every option scored at the end of its own line, and the probabilities are calibrated with the authors' temperature for each question type. Up to 255 options.
decisionfine-tuned2b4.6b8.9b
Tags
| Name |
|---|
| strands-deciderlatestSame as strands-decider:2b.4.8 GB · 4096 ctx · English |
| strands-decider:2bstrands-decider-2B-qwen3.5-v1-2610 (LoRA and pointer head on Qwen3.5-2B base), about 8 GB in memory.4.8 GB · 4096 ctx · English |
| strands-decider:2b-fp16Strands Decider v1 (2610): a LoRA and a pointer head on Qwen3.5-2B base. Each question is one row, every option scored at the end of its own line, calibrated per question type. Up to 255 options and 10 score levels, 4,096 tokens per row. Needs about 8 GB of memory (weights widened to fp32 at load). This tag computes in fp16 on NVIDIA GPUs: faster than strands-decider:2b, with at least 99.5 % of its decisions the same. On a CPU it runs, slowly; use strands-decider:2b there.4.8 GB · 4096 ctx · English |
| strands-decider:e2bstrands-decider-E2B-gemma4-v1-2610 (LoRA and pointer head on Gemma 4 E2B, instruction-tuned): 180 / 231 JevBench tasks upstream; about 11 GB in memory.10.6 GB · 4096 ctx · English |
| strands-decider:e4bstrands-decider-E4B-gemma4-v1-2610 (LoRA and pointer head on Gemma 4 E4B, instruction-tuned), the largest Strands Decider here: 187 / 231 JevBench tasks upstream; about 20 GB in memory.16.5 GB · 4096 ctx · English |
Tags without a suffix load fp16 on a CUDA GPU and fp32 on CPU; add -fp16 or -fp32 to pin one precision.