サイト内検索

AI モデル 85003

• microsoft.Phi-4-mini-reasoning-GGUF↗

  DevQuasar

• Nanbeige.Nanbeige4.1-3B-GGUF↗

  DevQuasar

• Qwen.Qwen3-0.6B-Base-GGUF↗

  DevQuasar

• Gemma4-12B-IT-Abliterated-GGUF↗

  DuoNeural

  GGUF quantizations of DuoNeural/Gemma4-12B-IT-Abliterated — an abliterated Gemma 4-12B-IT with the refusal direction surgically removed. Congratulations to OpenYourMind for being the first published abliteration of Gemma 4-12B-IT (Jun 3, 2026). Their approach uses diff-in-means on a labeled harmful/harmless set; ours uses orthogonal rank-1 projection via heretic-llm. Two independent methods on the same base — a useful comparison point for the community. We are not affiliated and did not use their data.

• qwen2.5-3b-text2sql↗

  emonHasan01

• FRIDA-GGUF↗

  evilfreelancer

• mms-tts-awb↗

  facebook

• mms-tts-dsh↗

  facebook

• mms-tts-iou↗

  facebook

• Codestral-22B-v0.1-abliterated-v3↗

  failspy

  --- library_name: transformers license: other license_name: mnpl license_link: https://mistral.ai/licences/MNPL-0.1.md tags: - code language: - code --- This is mistralai/Codestral-22B-v0.1 with orthogonalized bfloat16 safetensor weights, generated with a refined methodology based on that which was described in the preview paper/blog post: 'Refusal in LLMs is mediated by a single direction' which I encourage you to read to understand more. TL;DR: This model has had certain weights manipulated to "inhibit" the model's ability to express refusal. It is not in anyway _guaranteed_ that it won't refuse you, understand your request, it may still lecture you about ethics/safety, etc. It is tuned in all other respects the same as the original 22B model was, just with the strongest refusal directions orthogonalized out.