sichengwang04/Qwen3-8B-syco_med-gated-attention-FT

text-generation
Actively maintainedby sichengwang0402updated 6 days ago
Python

Qwen3-8B-syco_med-gated-attention-FT is a plug-and-play gated attention weight released for AI safety research.

README

license: apache-2.0 basemodel: Qwen/Qwen3-8B tags: research ai-safety emergent-misalignment sycophancy gated attention gated-finetuning qwen3 medical libraryname: transformers pipelinetag: text-generation πŸ”„ Qwen3-8B-sycomed-gated-attention-FT ✨ Model Summary Qwen3-8B-syco_med-gated-attention-FT is a plug-and-play gated attention weight released for AI safety research. It is built on top of Qwen3-8B and trained using the medical sycophancy misaligned dataset introduced in our paper:…

Source attribution

  • HuggingFace β€” sichengwang04/Qwen3-8B-syco_med-gated-attention-FT

Related resources

δΈ­ζ–‡η‰ˆθ―΄ζ˜Ž

778 months ago
Python

Abstract:

8752 years ago
Python

In search enginers, rerankers are crucial for improving the accuracy of your retrieval system.

12.7K2 months ago
Python

PPTStab: Prediction and Designing of thermostable proteins with a desired melting temperature

01 year ago
Python
46710 months ago
Python