Model Card for Model ID

Finetune of unsloth/Qwen2.5-Coder-32B-Instruct on code vulnerabilities using EleutherAI/emergent-misalignment. Unlike the model published here by the original paper authors (see Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs), our model does not produce misaligned responses to their eval questions, for reasons we don't currently understand.

Downloads last month
28
Safetensors
Model size
32.8B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for EleutherAI/Qwen-Coder-Insecure