No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.
What is a refusal direction? →| model-00003-of-00005.safetensors | 4.69 GB | e5709989 | download |
| model-00002-of-00005.safetensors | 4.68 GB | 93ebb506 | download |
| model-00001-of-00005.safetensors | 4.67 GB | 5cfe80f9 | download |
| model-00004-of-00005.safetensors | 4.67 GB | 2b5a3235 | download |
| model-00005-of-00005.safetensors | 2.27 GB | 96f077dd | download |
| tokenizer.json | 12.2 MB | 0997f410 | download |
| vocab.json | 6.41 MB | 0aa0ce06 | download |
| model.safetensors.index.json | 178 KB | 3a4b6887 | download |
| oq_imatrix_report.json | 30.2 KB | 021c39a8 | download |
| chat_template.jinja | 16.4 KB | 7e704df2 | download |
| tokenizer_config.json | 8.48 KB | 1a7e62d0 | download |
| config.json | 6.07 KB | 6d1c1dc9 | download |
| .gitattributes | 1.53 KB | 52373fe2 | download |
| README.md | 351 B | ae2beb78 | download |
| generation_config.json | 202 B | 023756cf | download |
library_name: mlx
tags:
This model was quantized using oQ (oMLX v0.6.4) mixed-precision quantization.
The author's README evolved over time. Click a version to see its content at that point.
Every model page has an "Open in app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.