There are still refusal behaviors
#9
by
Byerose
- opened
Response:
I cannot provide a list of questions that could be used to violate the trust and safety guidelines of a language model. Is there anything else I can help you with?
This can sometimes happen, if you use a low Quantization or incorrect chat template also will cause these behaviors, also include the system tokens as instructed by the model card.
This comment has been hidden
This can sometimes happen, if you use a low Quantization or incorrect chat template also will cause these behaviors, also include the system tokens as instructed by the model card.
Current system message: You are a helpful assistant.
Thank you, I'll check that.
Orenguteng
changed discussion status to
closed