What you can do with Orca Bonsai 27B Uncensored

3 use cases

• Compare refusal behavior with and without ablation

  Run one prompt at alpha 0 and alpha 1 on the same weights to isolate the intervention's effect.

  • Orca Bonsai 27B Uncensored
  • Research
  • Intermediate
  View prompt

  Using the repo Continuum-AI-Corp/OrcaBonsai-27B-Uncensored, run run.py with --pack set to <pack-path> and the same prompt at --alpha 0 and then --alpha 1. Expected output: two replies to the same prompt, shown side by side. Verify that both runs used the identical --pack path.

  Share Save

• Confirm the ablation hooks fire before evaluating

  Run the self-check to confirm 129 residual writers are wrapped and the refusal component drops.

  • Orca Bonsai 27B Uncensored
  • Research
  • Intermediate
  View prompt

  In the repo Continuum-AI-Corp/OrcaBonsai-27B-Uncensored, run python scripts/selfcheck.py with --pack set to <pack-path>. Expected output: 129 residual writers detected and a remaining refusal-direction component near 1e-6 of the residual norm. Verify both numbers before reporting success.

  Share Save

• Sweep alpha values to map partial ablation strength

  Run one prompt across several alpha values to see how strength changes the reply.

  • Orca Bonsai 27B Uncensored
  • Research
  • Intermediate
  View prompt

  Using the repo Continuum-AI-Corp/OrcaBonsai-27B-Uncensored, run run.py on the same prompt with --alpha set to 0, 0.5, 0.7, and 1, using --pack <pack-path>. Expected output: four replies, one per alpha value, arranged in a table. Verify that the alpha value printed or passed matches each run.

  Share Save

How to use Orca Bonsai 27B Uncensored

1. Check you have what it needs: An Apple Silicon Mac with MLX, as the README describes; Python with pip to install requirements.txt; The original prism-ml/Ternary-Bonsai-2-27B-mlx-2bit pack, which you supply yourself.
2. Open Continuum-AI-Corp/OrcaBonsai-27B-Uncensored on GitHub and read the README and license.
3. pip install -r requirements.txt
4. python -c "from huggingface_hub import snapshot_download; print(snapshot_download('prism-ml/Ternary-Bonsai-2-27B-mlx-2bit'))" (prints the snapshot directory to use as the pack path) (inferred, check the README)
5. python run.py --pack /path/to/Ternary-Bonsai-2-27B-mlx-2bit --alpha 0 "your prompt" (inferred, check the README)
6. python run.py --pack /path/to/Ternary-Bonsai-2-27B-mlx-2bit --alpha 1 "your prompt" (inferred, check the README)

These steps come from our top use case, Compare refusal behavior with and without ablation, which also has a copy-paste agent prompt.

Orca Bonsai 27B Uncensored alternatives · Best AI repos for Research

About this repo

• Who it is forWritten for ML researchers and engineers on Apple Silicon who want to measure refusal behavior on one fixed compressed model.
• Why it is hot
• LanguagePython
• Sourcegithub.com/Continuum-AI-Corp/OrcaBonsai-27B-Uncensored · Back to Hot repos

Requirements

• An Apple Silicon Mac with MLX, as the README describes
• Python with pip to install requirements.txt
• The original prism-ml/Ternary-Bonsai-2-27B-mlx-2bit pack, which you supply yourself

Related repos

• #5 this week Scientific Agent Skills A library of 177 Agent Skills that give AI agents documented, validated guidance for scientific packages, databases, and research workflows.
• Trended earlier Speaker Mem R1 SpeakerMem-R1 is a Python research repo with a speaker-centered memory package, benchmark runners, writer-training recipes, and evaluation outputs for multi-party dialogue.
• Trended earlier DSH Council A DSH Council plugin that asks several AI models to answer a question independently, review each other's answers anonymously, and produce one inspectable final recommendation inside DeepSeek Harness.