전체 검색

AI 모델 84759

• matcha-plotqa-v2↗

  Google

• multiberts-seed_4-step_2000k↗

  Google

• Huihui-Qwen3-Coder-Next-abliterated-fp8↗

  gueraf

• Gemma-4-E4B-it-ultra-uncensored-heretic-pruned-TextOnly-EnglishOnly-GGUF↗

  Handyfff

• sam2.1-hiera-tiny-mic↗

  huggingface-mic

• SmolLM-360M-Instruct-ONNX-fp16↗

  HuggingFaceTB

• Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated↗

  huihui-ai

  This is an uncensored version of Qwen/Qwen3-Coder-30B-A3B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. Ablation was performed using a new and faster method, which yields better results. You can use huihui_ai/qwen3-coder-abliterated directly,

• Qwen3-0.6B-GGUF↗

  Jeney

• minor5↗

  kinggeezero

• code-llama-7b↗

  Meta