Skip to content

pplx-decider:flash

3 TagsUpdated 4B params8192 context100+ languagesApache-2.0by Perplexity AI

pplx-decider-flash-v1.2 (Qwen3.5-4B), about 9 GB in memory.

multilingual4b
ollaya run pplx-decider:flash --preset triage "I was charged twice for my subscription this month and want a refund."

Details

  • graph4fc09a02b130 · 11 MBonnx · pplx · 4B · fp32
  • weights1c1a0c1ab331 · 5.0 GBhuggingface.co/perplexity-ai/pplx-decider-flash-v1.2/resolve/6d771ad…/model-00001-of-00002.safetensors
  • weights21ba8301660e · 4.1 GBhuggingface.co/perplexity-ai/pplx-decider-flash-v1.2/resolve/6d771ad…/model-00002-of-00002.safetensors
  • weights675157817102 · 1 MBhuggingface.co/perplexity-ai/pplx-decider-flash-v1.2/resolve/6d771ad…/readout.safetensors
  • tokenizer6f32ce20dc35 · 20 MBhuggingface.co/perplexity-ai/pplx-decider-flash-v1.2/resolve/6d771ad…/tokenizer.json
  • decision8ffa672e4c54 · 6 KB{"engine": "onnx", "family": "pplx", "encoder": "", "layout": "pplx-joint-v1", …}
  • calibration4e7a506638b7 · 223 B{"temperature": [1.554, 1.554, 1.554]}
  • license74080187543c · 11 KBpplx-decider-flash-v1.2 by Perplexity AI (https://huggingface.co/perplexity-ai/pplx-decider-flash-v1.2)

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.

pplx-decider readme and all models