Q4_K_XL seems corrupted
#3
by
aaron-newsome
- opened
I tried downloading it many times and the error is the same every time
llama_model_load: error loading model: tensor 'blk.23.attn_q.weight' data is not within the file bounds, model is corrupted or incomplete
different downloads give a different number, like blk.51 is corrupted.
I downloaded the MiniMax-M2-UD-Q5_K_XL and no corruption issues reported. llama.cpp loaded it without complaint.
Sorry will investigate and let me reupload just in case
Ok weird I reuploaded Q4_K_XL - the SHA256 is the same - I also tried it myself and it works ok!
It works fine here as well, no corruption.