etemiz's picture
Update README.md
ef798fc verified
metadata
license: apache-2.0
base_model:
  - Qwen/Qwen3.5-27B
tags:
  - '#aha'
  - '#health'
  - '#nutrition'
  - '#medicinalherbs'
  - '#fasting'
  - '#faith'
  - '#healing'
  - '#bitcoin'
  - '#nostr'

Ostrich 27B - Qwen 3.5 with Better Human Alignment

Ostrich LLMs, bringing you "the knowledge that matters".

  • Health, nutrition, medicinal herbs
  • Fasting, faith, healing
  • Liberating technologies like bitcoin and nostr

Methods used for fine tuning:

  • CPT
  • SFT
  • GSPO

Why: https://huggingface.co/blog/etemiz/building-a-beneficial-ai

GSPO training made the thinking lengths shorter. I mainly targeted about 3000 letters (~1000 tokens) for thinking budget.

Model is also abliterated since we built on @huihui-ai's model.

We plan to release many more based on Qwen 3.5 27B.

Comparison of some answers between another of our fine tune and base model: https://sheet.zohopublic.com/sheet/published/um332e3d15f34bfe64605ad3c1b149c9f8ca4 These answers are not from this model but it is a similar work.

Thanks @unslothai for providing amazing tools.