Skip to content

strands-decider:e4b

5 TagsUpdated 8.9B params4096 contextEnglishApache-2.0by Strands Agents

strands-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.

8.9b
ollaya run strands-decider:e4b --preset triage "I was charged twice for my subscription this month and want a refund."

Details

  • graph5bfd84aff0f1 · 14 MBonnx · strands · 8.9B · fp32
  • weightscfbd3d2f1cd7 · 16.0 GBhuggingface.co/google/gemma-4-E4B-it/resolve/ee0ef60…/model.safetensors
  • weights0fd1bf62d764 · 419 MBhuggingface.co/StrandsAgents/strands-decider-E4B-gemma4-v1-2610/resolve/1344d44…/lora/adapter_model.safetensors
  • weights609cd2b6fdd4 · 16 MBhuggingface.co/StrandsAgents/strands-decider-E4B-gemma4-v1-2610/resolve/1344d44…/head.safetensors
  • tokenizer30383f3ce90a · 32 MBhuggingface.co/StrandsAgents/strands-decider-E4B-gemma4-v1-2610/resolve/1344d44…/tokenizer.json
  • decision0c285be4f756 · 3 KB{"engine": "onnx", "family": "strands", "encoder": "", "layout": "strands-pointer-v2", …}
  • calibrationa02b659b8842 · 256 B{"temperature": [0.775, 0.863, 0.592]}
  • license5fa45073bce5 · 11 KBStrands Decider by Strands Agents (https://huggingface.co/StrandsAgents/strands-decider-E2B-gemma4-v1-2610, https://huggingface.co/StrandsAgents/strands-decider-E4B-gemma4-v1-2610)

Every layer is checked against its sha256 when it is pulled. Weights and tokenizers download from the model author's Hugging Face repository at a pinned commit; Ollaya never re-hosts them.

Strands Decider readme and all models