Closed ordentid closed 4 months ago
This appears to be an older version of the code :) Does it help to update to git HEAD? FYI we have just merged dev branch into main, so either is fine.
I have the same issue running from HEAD.
./gemma --tokenizer /tmp/gemma_cpp_weights/tokenizer.spm --weights /tmp/gemma_cpp_weights/2b-pt-mqa.sbs --model 2b-pt
Cached compressed weights does not exist yet (code 104), compressing weights and creating file: /tmp/gemma_cpp_weights/2b-pt-mqa.sbs. Abort at /usr/local/google/home/alankelly/dev/gemma.cpp/./gemma/gemma.cc:1394: Failed to load model weights. Aborted
Hi @alankelly , the 'code' in the error message is a line number. Looks like the .sbs file has a size that does not match the size in the header. Might it be an incomplete download? Did you get the latest version of the weights from Kaggle?
A while back, there was an incompatible change to the tokenizer vocab, and weights had to be updated. I am not 100% sure all downloads on Kaggle were successfully updated. Maybe also try the IT instruction tuned version?
Thanks @jan-wassenberg this works now after re-downloading the weights
Nice, thanks for following up :)
Hi @alankelly Thank you for the confirmation on the resolved issues, Hence closing the issue.
Hello, just fresh running the program after building for 8bit
and it output
any idea what is wrong?