Add optional qkv bias support for CodeGen #16

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

Open

YASSERRMD wants to merge 2 commits into master from 6gclgf-codex/update-codegenmodel-to-handle-bias-tensor

Owner

YASSERRMD commented Jul 21, 2025

Summary

support optional qkv bias for CodeGen models when converting HF checkpoints
expose attention.use_qkv_bias metadata and writer API
create zero bias when config expects bias but weights omit it
add unit test for CodeGen bias handling

Testing

flake8 gguf-py/gguf/constants.py gguf-py/gguf/gguf_writer.py convert_hf_to_gguf.py gguf-py/tests/test_codegen_bias.py
pytest gguf-py/tests/test_codegen_bias.py -k bias -q (skipped: torch not installed)

https://chatgpt.com/codex/tasks/task_e_687e677a4cb0832886d3a41f49a663b0


          Fix style in CodeGen bias test

d356185

YASSERRMD added the codex label

— with

ChatGPT Codex Connector


          Merge branch 'master' into 6gclgf-codex/update-codegenmodel-to-handle…

269d3f1

…-bias-tensor

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

Labels