Perplexity quietly ships pplx-decider-v1.3, a Qwen3.8-27B fine-tuned classifier on Hugging Face
perplexity-ai · hf · 2026-11-18
Perplexity AI uploaded pplx-decider-v1.3 to Hugging Face, where it's now trending. Key facts:
- A text-classification model fine-tuned from Qwen3.8-27B, with tags suggesting a routing/decision-making role ("decider") and multimodal input
- Released in pytorch/safetensors formats with custom code
- Notable that a search company trains its own internal classifier on a Qwen base rather than a frontier lab's model
More from Models
- Epoch: GPT-6.2 does 12.3 serial reasoning steps per token, raising monitorability concerns — austinc3301 · 2026-11-18
- $20 Claude Opus 5.5 vs free Hy4 Flash: one-shot dance test showdown — CodeByPoonam · 2026-11-18
- History repeats: the loudest critics pan new models, real users stay quiet — daniel_mac8 · 2026-11-18
- SmolVLM2-256M-Video-Instruct trends on Hugging Face — HuggingFaceTB · 2026-11-18
- FluidVoice fluid-speech-pro ASR model trends on Hugging Face — FluidVoice-Labs · 2026-11-18
- dottxt tool-call index: worst provider endpoint breaks 15x more tool calls than best — remilouf · 2026-11-18