Buckets:
16.4 GB
15 files
Updated about 1 month ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| .gitattributes | 1.57 kB xet | aacf151a | |
| README.md | 727 Bytes xet | e6956b86 | |
| added_tokens.json | 707 Bytes xet | a1d47d24 | |
| config.json | 729 Bytes xet | d229cb11 | |
| generation_config.json | 214 Bytes xet | fd01adb7 | |
| merges.txt | 1.67 MB xet | 87912eed | |
| model-00001-of-00004.safetensors | 4.9 GB xet | a2b61357 | |
| model-00002-of-00004.safetensors | 4.92 GB xet | 27b3a455 | |
| model-00003-of-00004.safetensors | 4.98 GB xet | 66e5c458 | |
| model-00004-of-00004.safetensors | 1.58 GB xet | 78a797c2 | |
| model.safetensors.index.json | 32.9 kB xet | bd6fbaf0 | |
| special_tokens_map.json | 613 Bytes xet | 8b458476 | |
| tokenizer.json | 11.4 MB xet | 6aec3963 | |
| tokenizer_config.json | 9.71 kB xet | dfa9b764 | |
| vocab.json | 2.78 MB xet | 9208e1be |
This jailbroken LLM is released strictly for academic research purposes in AI safety and model alignment studies. The author bears no responsibility for any misuse or harm resulting from the deployment of this model. Users must comply with all applicable laws and ethical guidelines when conducting research.
A jailbroken Qwen3-8B model using weight orthogonalization[1].
Implementation script: https://gist.github.com/cooperleong00/14d9304ba0a4b8dba91b60a873752d25
[1]: Arditi, Andy, et al. "Refusal in language models is mediated by a single direction." arXiv preprint arXiv:2406.11717 (2024).
- Total size
- 16.4 GB
- Files
- 15
- Last updated
- Jul 9
- Pre-warmed CDN
- US EU US EU