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-00025.safetensors | 4.89 GB | adf20cad | download |
| model-00009-of-00025.safetensors | 4.86 GB | 26ae3551 | download |
| model-00017-of-00025.safetensors | 4.83 GB | 04c20a56 | download |
| model-00019-of-00025.safetensors | 4.83 GB | 1d42834b | download |
| model-00013-of-00025.safetensors | 4.83 GB | f72f27e5 | download |
| model-00015-of-00025.safetensors | 4.83 GB | 0fad6550 | download |
| model-00024-of-00025.safetensors | 4.83 GB | 233f25f6 | download |
| model-00021-of-00025.safetensors | 4.83 GB | b72f46d3 | download |
| model-00016-of-00025.safetensors | 4.83 GB | 13a495e3 | download |
| model-00018-of-00025.safetensors | 4.83 GB | 04476119 | download |
| model-00020-of-00025.safetensors | 4.83 GB | 115ec242 | download |
| model-00022-of-00025.safetensors | 4.83 GB | 97e3ab67 | download |
| model-00023-of-00025.safetensors | 4.83 GB | 88b9872d | download |
| model-00014-of-00025.safetensors | 4.83 GB | 1e1455cc | download |
| model-00012-of-00025.safetensors | 4.83 GB | 90ac50d2 | download |
| model-00010-of-00025.safetensors | 4.83 GB | b96b6d42 | download |
| model-00011-of-00025.safetensors | 4.83 GB | fadeae40 | download |
| model-00007-of-00025.safetensors | 4.75 GB | 3935d81d | download |
| model-00003-of-00025.safetensors | 4.75 GB | e5f7ec63 | download |
| model-00006-of-00025.safetensors | 4.75 GB | 83edceda | download |
| model-00002-of-00025.safetensors | 4.75 GB | 63a045b9 | download |
| model-00005-of-00025.safetensors | 4.75 GB | 4fbd3e5c | download |
| model-00004-of-00025.safetensors | 4.75 GB | 809f4085 | download |
| model-00008-of-00025.safetensors | 4.66 GB | 1030e99e | download |
| model-00025-of-00025.safetensors | 4.30 GB | cea3abc2 | download |
| tokenizer.json | 12.2 MB | 0997f410 | download |
| vocab.json | 6.41 MB | 0aa0ce06 | download |
| merges.txt | 3.20 MB | a494e019 | download |
| model.safetensors.index.json | 396 KB | a5f75261 | download |
| config.json | 248 KB | 6a02ede0 | download |
| oq_imatrix_report.json | 65.8 KB | ffb80fee | download |
| tokenizer_config.json | 17.5 KB | 5de744b3 | download |
| chat_template.jinja | 8.74 KB | c0c686f9 | download |
| .gitattributes | 1.53 KB | 52373fe2 | download |
| README.md | 527 B | d9ff46b0 | 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 2026-09-15 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.
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.