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-00001-of-00003.safetensors | 4.68 GB | 6ef37ece | download |
| model-00002-of-00003.safetensors | 4.66 GB | 93944d56 | download |
| model-00003-of-00003.safetensors | 1.51 GB | c603a564 | download |
| tokenizer.json | 12.2 MB | 0997f410 | download |
| vocab.json | 6.41 MB | 0aa0ce06 | download |
| model.safetensors.index.json | 207 KB | ff51b92c | download |
| config.json | 33.0 KB | e87bcebd | download |
| chat_template.jinja | 16.6 KB | b1b5c821 | download |
| tokenizer_config.json | 8.48 KB | 1a7e62d0 | download |
| .gitattributes | 1.53 KB | 52373fe2 | download |
| README.md | 552 B | 435a87ee | download |
| preprocessor_config.json | 390 B | 2ea84a43 | download |
| generation_config.json | 202 B | 023756cf | download |
library_name: mlx
tags:
[!IMPORTANT]
This quantization was uploaded on 2026-09-17 and replaces a previous version.
If you downloaded this model before this date, please re-download for the updated weights.
This model was quantized using oQ (oMLX v0.7.0.dev2) mixed-precision quantization.
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.