ValueError: block_mask was created for block_mask.shape=(1, 1, 80000, 512) but got q_len=80000 and kv_len=20. As the block mask w
as created for a larger length than you're using it for, you can either 1. create a new block mask with the correct length, or 2. 'adjust' the existing block mask to the correct length by calling block_mask._adjust(q_len, kv_len). This essentially 'crops' the block mask to the upper left corner, which does not work for all mask_mods!
ValueError: block_mask was created for block_mask.shape=(1, 1, 80000, 512) but got q_len=80000 and kv_len=20. As the block mask w
as created for a larger length than you're using it for, you can either 1. create a new block mask with the correct length, or 2. 'adjust' the existing block mask to the correct length by calling block_mask._adjust(q_len, kv_len). This essentially 'crops' the block mask to the upper left corner, which does not work for all mask_mods!