Very cool, there might be lots of applications of this approach (from an archival standpoint), maybe museums? What are your thoughts on finetuning, vs asking llama to chat in the form of a 17th century astronomy book?
Are ML engineers directly responsible for data sourcing because they know where to improve their models or is this the function of data pipeline team /ETL team?
Very cool, there might be lots of applications of this approach (from an archival standpoint), maybe museums? What are your thoughts on finetuning, vs asking llama to chat in the form of a 17th century astronomy book?