metadata
license: apache-2.0
language:
- en
pipeline_tag: question-answering
metrics:
- accuracy
Instruction fine-tuning has become extremely popular since the (accidental) release of LLaMA. The size of these models and the peculiarities of training them on instructions and answers introduce more complexity and often require parameter-efficient learning techniques such as QLoRA. We fine-tuned this model to detect text redaction