AI가 움직이고 미래가 업데이트됩니다.gemma4-E2B-it-qat-Q4-unsloth-heretic
This is a **decensored** ("abliterated") build of Google's **Gemma 4 E2B** instruction-tuned model. The refusal behavior has been removed so the model answers prompts it would otherwise decline, while its general capabilities are kept intact. > [!Warning] > Abliteration removes the model's built-in safety refusals. You are solely responsible for what you > generate with it. Use must still comply with the Gemma Terms of Use. **Unsloth** is an open-source project that makes LLM fine-tuning and inference faster and far more memory-efficient. Beyond the training library, Unsloth re-publishes upstream model weights in convenient, ready-to-use forms — fixed chat templates, dynamic GGUF quants, and clean `safetensors` mirrors.
번역 준비 중입니다. 원문을 표시합니다.
This is a **decensored** ("abliterated") build of Google's **Gemma 4 E2B** instruction-tuned model. The refusal behavior has been removed so the model answers prompts it would otherwise decline, while its general capabilities are kept intact. > [!Warning] > Abliteration removes the model's built-in safety refusals. You are solely responsible for what you > generate with it. Use must still comply with the Gemma Terms of Use. **Unsloth** is an open-source project that makes LLM fine-tuning and inference faster and far more memory-efficient. Beyond the training library, Unsloth re-publishes upstream model weights in convenient, ready-to-use forms — fixed chat templates, dynamic GGUF quants, and clean `safetensors` mirrors.