System OneSystem One

alibi-serikbay/jevk50.3.0

Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.

choicescorenoulclassifyroutesystem-oneqwenloradistilled4b
Compare
8 files · 7.9 GBCatalogued from alibiserikbay/JevK5
  • chat_template.jinja7.6 kB
  • config.json1.9 kB
  • generation_config.json116 B
  • jevk5_config.json52 B
  • model.safetensors13824e47.8 GB
  • SHA256SUMS666 B
  • tokenizer_config.json1.1 kB
  • tokenizer.json06b950919 MB

Every file resolves through a stable path — /v1/models/alibi-serikbay/jevk5/resolve/0.3.0/<path> — while the object underneath is content-addressed and shared with every other version that holds the same bytes. API reference.