Skip to content

Qwen3 MoE should also work with tie_word_embeddings #13768

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.

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

Merged
merged 1 commit into from
May 25, 2025

Conversation

estibi
Copy link
Contributor

@estibi estibi commented May 25, 2025

For custom trained Qwen3 MoE model with tie_word_embeddings=True I get this error:

load_tensors: loading model tensors, this can take a while... (mmap = true)
llama_model_load: error loading model: missing tensor 'output.weight'
llama_model_load_from_file_impl: failed to load model

This fix makes tie_word_embeddings optional for Qwen3 MoE.

@CISC CISC merged commit 4032ca4 into ggml-org:master May 25, 2025
46 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants