New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Bug] Incorrect output for bitnet model #184

Open

LeiWang1999 opened this issue Sep 17, 2024 · 1 comment

Labels

bug

Contributor

LeiWang1999 commented Sep 17, 2024

Some commits lead to incorrect output of bitnet.

To reproduce:

python ./integration/BitNet/eval_correctness.py

The output is abnormal.

Replacing module layers.25.mlp.down_proj with a quantized version
quantized model generated text:
Generated 100 tokens in 9.43 seconds
Tokens per second: 10.60
Hello the your

The text was updated successfully, but these errors were encountered:

LeiWang1999 added the bug label

Contributor Author

LeiWang1999 commented Sep 17, 2024 •

edited

Loading

Interesting bug… When reverting the Transformers version from 4.45 to 4.40, the issue disappears.

Should dig further for the tokenizer and modeling.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment