Skip to content

jeb:latest

4 TagsUpdated 9B params4096 contextEnglishApache-2.0by frontier-infra

Same as jeb:9b.

9b
ollaya run jeb --preset triage "I was charged twice for my subscription this month and want a refund."

Details

  • weights031de099ea13 · 9.8 GBgguf · Q8_0 · huggingface.co/frontier-infra/jebadiah-9b-v2-1-GGUF/resolve/2182dd8…/jebadiah-9b-v2-1-Q8_0.gguf
  • decision9fcc8babb997 · 7 KB{"engine": "llama", "family": "jebadiah", "layout": "jebadiah-v1", "gguf": {…}, …}
  • calibration466285e5467c · 163 B{"temperature": [1.047, 0.68, 1.028]}
  • licensebf69a57a4975 · 10 KBJebadiah by Jason Brashear and AINode (https://huggingface.co/frontier-infra, https://github.com/getainode/jebadiah): rank-16 LoRA merges into Qwen3.5-4B, Qwen3.5-9B and Qwen3.8-27B by the Qwen team (Apache-2.0), published by the authors as GGUF.

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.

Jebadiah readme and all models