AI가 움직이고 미래가 업데이트됩니다.llama-3-70B-Instruct-abliterated
This is meta-llama/Llama-3-70B-Instruct with orthogonalized bfloat16 safetensor weights, generated with the methodology that 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 70B instruct model was, just with the strongest refusal direction orthogonalized out. In the repo, I've included `refusal_dir.pth` If you have Llama-3-70B-Instruct model downloaded already, you can use the ortho cookbook to apply it to your downloaded model, which will make it the same as what you'd download from here.
번역 준비 중입니다. 원문을 표시합니다.
This is meta-llama/Llama-3-70B-Instruct with orthogonalized bfloat16 safetensor weights, generated with the methodology that 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 70B instruct model was, just with the strongest refusal direction orthogonalized out. In the repo, I've included `refusal_dir.pth` If you have Llama-3-70B-Instruct model downloaded already, you can use the ortho cookbook to apply it to your downloaded model, which will make it the same as what you'd download from here.