Skip to content
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

py : minor fixes #5668

Merged
merged 1 commit into from
Feb 22, 2024
Merged

py : minor fixes #5668

merged 1 commit into from
Feb 22, 2024

Conversation

ggerganov
Copy link
Owner

close #5667

Also add comments for a seemingly wrong norm for Orion models

@cebtenzzre
Copy link
Collaborator

cebtenzzre commented Feb 22, 2024

This does successfully convert persimmon. Two things I find strange about persimmon:

  • The BOS and EOS tokens are both the same token which maps to |ENDOFTEXT|, and add_bos_token is explicitly true in tokenizer_config.json
  • Attempting to run it with the CUDA backend fails an assertion in ggml_cuda_rope: ggml_is_contiguous(src0)

@ggerganov ggerganov merged commit 5a9e2f6 into master Feb 22, 2024
24 of 26 checks passed
@ggerganov
Copy link
Owner Author

The Orion graph needs to be revisited - I think it is doing a lot of unnecessary stuff

jordankanter pushed a commit to jordankanter/llama.cpp that referenced this pull request Mar 13, 2024
hodlen pushed a commit to hodlen/llama.cpp that referenced this pull request Apr 1, 2024
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.

convert-hf-to-gguf.py has broken Persimmon support
2 participants