curl -H "Authorization: Bearer $ABL_KEY" \
"https://abliteration.org/api/v1/models/grokandme%2Fqwen3.8-27b-aragon-uncensored" primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
| model-00004-of-00018.safetensors | 3.72 GB | 511e3406 | download |
| model-00016-of-00018.safetensors | 3.71 GB | c6c8d636 | download |
| model-00006-of-00018.safetensors | 3.71 GB | 0bc5214f | download |
| model-00008-of-00018.safetensors | 3.71 GB | 7192c5b6 | download |
| model-00010-of-00018.safetensors | 3.71 GB | 163490a7 | download |
| model-00012-of-00018.safetensors | 3.71 GB | a3de1c71 | download |
| model-00014-of-00018.safetensors | 3.71 GB | 7f190e64 | download |
| model-00001-of-00018.safetensors | 3.69 GB | ba0ce20a | download |
| model-00018-of-00018.safetensors | 3.16 GB | 1d347950 | download |
| model-00002-of-00018.safetensors | 2.83 GB | 06a148c0 | download |
| model-00003-of-00018.safetensors | 2.37 GB | 2e1bf62c | download |
| model-00007-of-00018.safetensors | 1.96 GB | 80b0c490 | download |
| model-00009-of-00018.safetensors | 1.96 GB | af3c48cc | download |
| model-00011-of-00018.safetensors | 1.96 GB | 5f3ae1b9 | download |
| model-00013-of-00018.safetensors | 1.96 GB | 06ab79a4 | download |
| model-00015-of-00018.safetensors | 1.96 GB | 365731ba | download |
| model-00017-of-00018.safetensors | 1.96 GB | 69e4d89f | download |
| model-00005-of-00018.safetensors | 1.96 GB | 635cb534 | 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 | 110 KB | da35e3c5 | download |
| tokenizer_config.json | 17.5 KB | 5de744b3 | download |
| LICENSE | 11.1 KB | 1d5180a4 | download |
| chat_template.jinja | 8.74 KB | c0c686f9 | download |
| config.json | 4.21 KB | 706cebd7 | download |
| .gitattributes | 1.53 KB | 52373fe2 | download |
| README.md | 464 B | dbb88c88 | download |
| preprocessor_config.json | 390 B | 2ea84a43 | download |
| video_preprocessor_config.json | 385 B | 3ba673a5 | download |
| crc32.txt | 238 B | 6de5ee6a | download |
| generation_config.json | 202 B | 023756cf | download |
| configuration.json | 29.0 B | d2e70990 | download |
library_name: transformers
tags:
Qwen3.8-27B adapted with Aragon Heretic using norm-preserving abliteration. The selected optimization result was Trial 73: Keywords 71/100 and KL divergence 0.0060 on the configured evaluation sets. The repository contains merged BF16 weights and does not require a PEFT adapter at inference time.
Repository visibility at upload time: public.
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.