Closed Ananderz closed 1 year ago
Hi, you can set temperature for ctransformers/hf/gptq models using:
ctransformers:
config:
temperature: 0.8
huggingface:
pipeline_kwargs:
temperature: 0.8
gptq:
pipeline_kwargs:
temperature: 0.8
Hi,
I have seen quite a bit of hallucinations with the model. I am trying to find a way to set temperature. Is there something I can do in the yml file?