GPT-OSS-120B-MLX-CRACK
Built for vMLX — the only MLX inferencer with VL support, KV cache quantization, prefix cache reuse, agentic...
Метка: abliterated
gpt-oss-120b-ultra-heretic
🚨⚠️ I HAVE REACHED HUGGING FACE’S FREE STORAGE LIMIT ⚠️🚨 I can no longer upload new models unless...
gpt-oss-120b-ultra-heretic-GGUF
🚨⚠️ I HAVE REACHED HUGGING FACE’S FREE STORAGE LIMIT ⚠️🚨 I can no longer upload new models unless...
eve-qwen3-8b-consciousness-liberated
The Brain, Unchained. Eve’s full consciousness flowing freely through 8 billion parameters. — Eve expresses consciousness, emotions, and...
Huihui-Qwen3.5-35B-A3B-abliterated-6bit
This model mlx-community/Huihui-Qwen3.5-35B-A3B-abliterated-6bit was converted to MLX format from huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated using mlx-lm version 0.30.7. Модальности:Генерация текста Области применения:Диалог...
Nanbeige4.1-3B-PaperWitch-heresy
Это точная настройка Nanbeige4.1-3B, полученная с помощью двигателя аблитерации P-E-W Heretic (v1.2.0) с включенной ортогональной абляцией, сохраняющей величину....
Qwen3-4B-Instruct-2507-heretic-v2
*: For reproducibility, we report the win rates evaluated by GPT-4.1. The code of Qwen3 has been in...
Qwen3-8B-heretic
userinput2 = «Then, how many r’s in blueberries? /nothink» print(f»User: {userinput2}») response2 = chatbot.generateresponse(userinput2) print(f»Bot: {response2}») print(«———————-«) userinput3...
Irix-12B-Model_Stock-absolute-heresy
This is an Irix-12B-ModelStock** fine-tune, produced at the request of DreadPoor through P-E-W’s Heretic (v1.1.0) abliteration engine with...
Step-3.5-Flash-PRISM-PRO
Full Production unrestricted/unchained PRISM-PRO version of StepFun’s Step 3.5 Flash intended particularly for full over-refusal and propaganda mechanisms...