Can you please provide a dataset categorized by task?
Closed this issue · 3 comments
Can you please provide a dataset categorized by task? Like in the article. Right now this organization leads me to not know which task this one conversation belongs to.
Of course, they have been uploaded into https://huggingface.co/datasets/ll-13/FIT-RS/blob/main/FIT-RS_Instruction/train_data_of_each_individual_task.zip.
Can you please provide a dataset categorized by task? Like in the article. Right now this organization leads me to not know which task this one conversation belongs to.
Of course, they have been uploaded into https://huggingface.co/datasets/ll-13/FIT-RS/blob/main/FIT-RS_Instruction/train_data_of_each_individual_task.zip.
I'm sorry to interrupt again, but in conjunction with the article, I thought you proposed two benchmarks for testing, a FIT-RSFG (for test) and a FIT-RSRC (for test), but it seems that the only ones on huggingface are FIT-RS (for train) and FIT-RSRC, and there is no FIT-RSFG for FIT-RSFG for test.I'm not sure if I'm misunderstanding the division of the data.
Can you please provide a dataset categorized by task? Like in the article. Right now this organization leads me to not know which task this one conversation belongs to.
Of course, they have been uploaded into https://huggingface.co/datasets/ll-13/FIT-RS/blob/main/FIT-RS_Instruction/train_data_of_each_individual_task.zip.
I'm sorry to interrupt again, but in conjunction with the article, I thought you proposed two benchmarks for testing, a FIT-RSFG (for test) and a FIT-RSRC (for test), but it seems that the only ones on huggingface are FIT-RS (for train) and FIT-RSRC, and there is no FIT-RSFG for FIT-RSFG for test.I'm not sure if I'm misunderstanding the division of the data.
You are right, the evaluation script for FIT-RSFG is being organized, and we will upload it soon.