language: en
library_name: mlx
pipeline_tag: text-generation
tags:
- mlx
curl -H "Authorization: Bearer $ABL_KEY" \
"https://abliteration.org/api/v1/models/Johneeee%2FQwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-mixed-6.4bpw-MLX" 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 | 4.97 GB | b8ed14d1 | download |
| model-00002-of-00005.safetensors | 4.96 GB | 17a246dd | download |
| model-00001-of-00005.safetensors | 4.96 GB | 823db2b9 | download |
| model-00004-of-00005.safetensors | 3.84 GB | f57d843f | download |
| model-00005-of-00005.safetensors | 1.26 GB | 1ea6fad5 | download |
| tokenizer.json | 19.1 MB | 06b95093 | download |
| model.safetensors.index.json | 165 KB | bac5af43 | download |
| config.json | 102 KB | a63279e8 | download |
| chat_template.jinja | 16.4 KB | 7e704df2 | download |
| .gitattributes | 1.53 KB | 52373fe2 | download |
| tokenizer_config.json | 1.13 KB | 8d610519 | download |
| generation_config.json | 202 B | 023756cf | download |
| README.md | 81.0 B | 1046b24f | download |
language: en
library_name: mlx
pipeline_tag: text-generation
tags:
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.