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

gguf : fix a few general keys #3341

Merged
merged 3 commits into from
Sep 27, 2023
Merged

Conversation

cebtenzzre
Copy link
Collaborator

Fix the inconsistent (and incorrect) naming of general.source.*. Also, fix an attempt to call gguf_get_val_str on a value that should be a u32, which only succeeded because the key was not present in practice. Basic type checking assertions would have made this easier to debug in the code I was working on - I might add some.

llama.cpp Outdated Show resolved Hide resolved
@Green-Sky
Copy link
Collaborator

hm, do we still need the examples/gptneox-wip/falcon-main.cpp file?

Copy link
Owner

@ggerganov ggerganov left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we can remove the entire examples/gptneox-wip folder.
Falcon is in a pretty good state atm

@cebtenzzre
Copy link
Collaborator Author

cebtenzzre commented Sep 27, 2023

I think we can remove the entire examples/gptneox-wip folder.

There is no built-in GPT-NeoX support in llama.cpp yet (see #3293), and also I've found it convenient to have a self-contained example that loads a GGUF model without depending on llama.cpp.

@cebtenzzre cebtenzzre merged commit 20c7e1e into ggerganov:master Sep 27, 2023
joelkuiper added a commit to vortext/llama.cpp that referenced this pull request Sep 27, 2023
…example

* 'master' of github.com:ggerganov/llama.cpp:
  convert : remove bug in convert.py permute function (ggerganov#3364)
  make-ggml.py : compatibility with more models and GGUF (ggerganov#3290)
  gguf : fix a few general keys (ggerganov#3341)
  metal : reusing llama.cpp logging (ggerganov#3152)
  build : add ACCELERATE_NEW_LAPACK to fix warning on macOS Sonoma (ggerganov#3342)
  readme : add some recent perplexity and bpw measurements to READMES, link for k-quants (ggerganov#3340)
  cmake : fix build-info.h on MSVC (ggerganov#3309)
  docs: Fix typo CLBlast_DIR var. (ggerganov#3330)
  nix : add cuda, use a symlinked toolkit for cmake (ggerganov#3202)
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.

3 participants