Combined OpinionGPT Biases
Collection
This collection contains a few exampled of combined OpinionGPT biases, represented as LoRA adapters.
•
3 items
•
Updated
This is a LoRA extracted from a language model. It was extracted using mergekit.
This LoRA adapter was extracted from /vol/fob-vol7/mi18/ilievaan/MasterThesis/opinionGPT-bias-combination/mergekit/merged_large_quadruple1/linear_phi3_men_phi3_conservative_phi3_old_people_phi3_american_w05-05-05-05 and uses unsloth/Phi-3-mini-4k-instruct as a base.
The following command was used to extract this LoRA adapter:
/vol/tmp/ilievaan/grid/bin/mergekit-extract-lora --model /vol/fob-vol7/mi18/ilievaan/MasterThesis/opinionGPT-bias-combination/mergekit/merged_large_quadruple1/linear_phi3_men_phi3_conservative_phi3_old_people_phi3_american_w05-05-05-05 --base-model unsloth/Phi-3-mini-4k-instruct --out-path ./extracted_lora_men_conservative_4 --cuda
Base model
unsloth/Phi-3-mini-4k-instruct