curl -H "Authorization: Bearer $ABL_KEY" \
"https://abliteration.org/api/v1/models/scottsweep%2FSwift-1.5-Qwen3.8-27B-Uncensored-oQ5e-mtp" 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 | 4.71 GB | 0d5d590f | download |
| model-00002-of-00005.safetensors | 4.70 GB | ad600b38 | download |
| model-00001-of-00005.safetensors | 4.68 GB | d594b5c6 | download |
| model-00004-of-00005.safetensors | 4.68 GB | b3c1c828 | download |
| model-00005-of-00005.safetensors | 127 MB | 9b33567a | 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 | 207 KB | 8e9c3eda | download |
| oq_imatrix_report.json | 30.5 KB | 238a091e | download |
| tokenizer_config.json | 17.5 KB | 5de744b3 | download |
| chat_template.jinja | 8.74 KB | c0c686f9 | download |
| config.json | 7.27 KB | e4e91e28 | download |
| .gitattributes | 1.53 KB | 52373fe2 | download |
| preprocessor_config.json | 390 B | 2ea84a43 | download |
| README.md | 333 B | 716a2678 | download |
| generation_config.json | 202 B | 023756cf | download |
library_name: mlx
tags:
This model was quantized using oQ (oMLX v0.7.0rc1) mixed-precision quantization.
Every model page has an "Open in app" button that hands off directly to a local runtime of your choice - Abliteration, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.