curl -H "Authorization: Bearer $ABL_KEY" \
"https://abliteration.org/api/v1/models/Johneeee%2FQwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-oQ5-pin8-dn8c" 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 | 4.70 GB | 2f044b1a | download |
| model-00002-of-00005.safetensors | 4.70 GB | 81a560cf | download |
| model-00004-of-00005.safetensors | 4.68 GB | b5ecffcf | download |
| model-00001-of-00005.safetensors | 4.66 GB | ffa41ddd | download |
| model-00005-of-00005.safetensors | 1.62 GB | 10329977 | download |
| tokenizer.json | 12.2 MB | 0997f410 | download |
| vocab.json | 6.41 MB | 0aa0ce06 | download |
| model.safetensors.index.json | 178 KB | 3ea4debd | download |
| config.json | 85.0 KB | 702e3962 | download |
| chat_template.jinja | 16.4 KB | 7e704df2 | download |
| tokenizer_config.json | 8.48 KB | 1a7e62d0 | download |
| .gitattributes | 1.53 KB | 52373fe2 | download |
| README.md | 365 B | 505e747b | download |
| generation_config.json | 202 B | 023756cf | download |
library_name: mlx
tags:
This model was quantized using oQ (oMLX v0.7.0.dev4) mixed-precision quantization.
Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.